Academic literature on the topic 'Hybrid physics-data driven models'
Create a spot-on reference in APA, MLA, Chicago, Harvard, and other styles
Consult the lists of relevant articles, books, theses, conference reports, and other scholarly sources on the topic 'Hybrid physics-data driven models.'
Next to every source in the list of references, there is an 'Add to bibliography' button. Press on it, and we will generate automatically the bibliographic reference to the chosen work in the citation style you need: APA, MLA, Harvard, Chicago, Vancouver, etc.
You can also download the full text of the academic publication as pdf and read online its abstract whenever available in the metadata.
Journal articles on the topic "Hybrid physics-data driven models"
1
Zhang, C., H. Xue, G. Dong, H. Jing, and S. He. "RUNOFF ESTIMATION BASED ON HYBRID-PHYSICS-DATA MODEL." ISPRS Annals of the Photogrammetry, Remote Sensing and Spatial Information Sciences V-3-2022 (May 17, 2022): 347–52. http://dx.doi.org/10.5194/isprs-annals-v-3-2022-347-2022.
Full textAbstract:
Abstract. Runoff estimations play an important role in water resource planning and management. Existing hydrological models can be divided into physical models and data-driven models. Although the physical model contains certain physical knowledge and can be well generalized to new scenarios, the application of physical models is limited by the high professional knowledge requirements, difficulty in obtaining data and high computational costs. The data-driven model can fit the observed data well, but the estimation may not be physically consistent. In this letter, we propose a hybrid physical data (HPD) model combining physical model and deep learning model for runoff estimation. The model uses the output of a physical hydrological model together with the driving factors as another input of the neural network to estimate the monthly runoff of the upper Heihe River Basin in China. We show that the use of the HPD model improves the quality of runoff estimation, and results in high R2, NSE values of 0.969, and a low RMSE value of 9.645. It is indicated that the new model had an excellent learning capability to simulate runoff and flexible ability to extract complex relevant information; At the same time, the estimation capacity of peak runoff is optimized.
2
Groves, Declan, and Andy Way. "Hybrid data-driven models of machine translation." Machine Translation 19, no. 3-4 (November 2, 2006): 301–23. http://dx.doi.org/10.1007/s10590-006-9015-5.
Full text
3
Jørgensen, Ulrik, Pauline Røstum Belingmo, Brian Murray, Svein Peder Berge, and Armin Pobitzer. "Ship route optimization using hybrid physics-guided machine learning." Journal of Physics: Conference Series 2311, no. 1 (July 1, 2022): 012037. http://dx.doi.org/10.1088/1742-6596/2311/1/012037.
Full textAbstract:
Abstract This paper presents a method for energy efficient weather routing of a ferry in Norway. Historical operational data from the ferry and environmental data are used to develop two models that predict the energy consumption. The first is a purely data-driven linear regression energy model, while the second is as a hybrid model, combining physical models with data-driven models using machine learning techniques. With an established energy model, it is possible to develop a route optimization that proposes efficient routes with less energy usage compared to fixed speed and heading control.
4
Sun, Jian, Kristopher A. Innanen, and Chao Huang. "Physics-guided deep learning for seismic inversion with hybrid training and uncertainty analysis." GEOPHYSICS 86, no. 3 (March 19, 2021): R303—R317. http://dx.doi.org/10.1190/geo2020-0312.1.
Full textAbstract:
The determination of subsurface elastic property models is crucial in quantitative seismic data processing and interpretation. This problem is commonly solved by deterministic physical methods, such as tomography or full-waveform inversion. However, these methods are entirely local and require accurate initial models. Deep learning represents a plausible class of methods for seismic inversion, which may avoid some of the issues of purely descent-based approaches. However, any generic deep learning network capable of relating each elastic property cell value to each sample in a seismic data set would require a very large number of degrees of freedom. Two approaches might be taken to train such a network: first, by invoking a massive and exhaustive training data set and, second, by working to reduce the degrees of freedom by enforcing physical constraints on the model-data relationship. The second approach is referred to as “physics-guiding.” Based on recent progress in wave theory-designed (i.e., physics-based) networks, we have developed a hybrid network design, involving deterministic, physics-based modeling and data-driven deep learning components. From an optimization standpoint, a data-driven model misfit (i.e., standard deep learning) and now a physics-guided data residual (i.e., a wave propagation network) are simultaneously minimized during the training of the network. An experiment is carried out to analyze the trade-off between two types of losses. Synthetic velocity building is used to examine the potential of hybrid training. Comparisons demonstrate that, given the same training data set, the hybrid-trained network outperforms the traditional fully data-driven network. In addition, we perform a comprehensive error analysis to quantitatively compare the fully data-driven and hybrid physics-guided approaches. The network is applied to the SEG salt model data, and the uncertainty is analyzed, to further examine the benefits of hybrid training.
5
Yun, Seong-Jin, Jin-Woo Kwon, and Won-Tae Kim. "A Novel Digital Twin Architecture with Similarity-Based Hybrid Modeling for Supporting Dependable Disaster Management Systems." Sensors 22, no. 13 (June 24, 2022): 4774. http://dx.doi.org/10.3390/s22134774.
Full textAbstract:
Disaster management systems require accurate disaster monitoring and prediction services to reduce damages caused by natural disasters. Digital twins of natural environments can provide the services for the systems with physics-based and data-driven disaster models. However, the digital twins might generate erroneous disaster prediction due to the impracticability of defining high-fidelity physics-based models for complex natural disaster behavior and the dependency of data-driven models on the training dataset. This causes disaster management systems to inappropriately use disaster response resources, including medical personnel, rescue equipment and relief supplies, to ensure that it may increase the damages from the natural disasters. This study proposes a digital twin architecture to provide accurate disaster prediction services with a similarity-based hybrid modeling scheme. The hybrid modeling scheme creates a hybrid disaster model that compensates for the errors of physics-based prediction results with a data-driven error correction model to enhance the prediction accuracy. The similarity-based hybrid modeling scheme reduces errors from the data dependency of the hybrid model by constructing a training dataset using similarity assessments between the target disaster and the historical disasters. Evaluations in wildfire scenarios show that the digital twin decreases prediction errors by approximately 50% compared with those of the existing schemes.
6
Wang, Jinjiang, Yilin Li, Robert X. Gao, and Fengli Zhang. "Hybrid physics-based and data-driven models for smart manufacturing: Modelling, simulation, and explainability." Journal of Manufacturing Systems 63 (April 2022): 381–91. http://dx.doi.org/10.1016/j.jmsy.2022.04.004.
Full text
7
Belov, Sergei, Sergei Nikolaev, and Ighor Uzhinsky. "Hybrid Data-Driven and Physics-Based Modeling for Gas Turbine Prescriptive Analytics." International Journal of Turbomachinery, Propulsion and Power 5, no. 4 (November 9, 2020): 29. http://dx.doi.org/10.3390/ijtpp5040029.
Full textAbstract:
This paper presents a methodology for predictive and prescriptive analytics of a gas turbine. The methodology is based on a combination of physics-based and data-driven modeling using machine learning techniques. Combining these approaches results in a set of reliable, fast, and continuously updating models for prescriptive analytics. The methodology is demonstrated with a case study of a jet-engine power plant preventive maintenance and diagnosis of its flame tube. The developed approach allows not just to analyze and predict some problems in the combustion chamber, but also to identify a particular flame tube to be repaired or replaced and plan maintenance actions in advance.
8
Fernandes, Pedro Henrique Evangelista, Giovanni Corsetti Silva, Diogo Berta Pitz, Matteo Schnelle, Katharina Koschek, Christof Nagel, and Vinicius Carrillo Beber. "Data-Driven, Physics-Based, or Both: Fatigue Prediction of Structural Adhesive Joints by Artificial Intelligence." Applied Mechanics 4, no. 1 (March 8, 2023): 334–55. http://dx.doi.org/10.3390/applmech4010019.
Full textAbstract:
Here, a comparative investigation of data-driven, physics-based, and hybrid models for the fatigue lifetime prediction of structural adhesive joints in terms of complexity of implementation, sensitivity to data size, and prediction accuracy is presented. Four data-driven models (DDM) are constructed using extremely randomized trees (ERT), eXtreme gradient boosting (XGB), LightGBM (LGBM) and histogram-based gradient boosting (HGB). The physics-based model (PBM) relies on the Findley’s critical plane approach. Two hybrid models (HM) were developed by combining data-driven and physics-based approaches obtained from invariant stresses (HM-I) and Findley’s stress (HM-F). A fatigue dataset of 979 data points of four structural adhesives is employed. To assess the sensitivity to data size, the dataset is split into three train/test ratios, namely 70%/30%, 50%/50%, and 30%/70%. Results revealed that DDMs are more accurate, but more sensitive to dataset size compared to the PBM. Among different regressors, the LGBM presented the best performance in terms of accuracy and generalization power. HMs increased the accuracy of predictions, whilst reducing the sensitivity to data size. The HM-I demonstrated that datasets from different sources can be utilized to improve predictions (especially with small datasets). Finally, the HM-I showed the highest accuracy with an improved sensitivity to data size.
9
Al Rashdan, Ahmad Y., Hany S. Abdel-Khalik, Kellen M. Giraud, Daniel G. Cole, Jacob A. Farber, William W. Clark, Abenezer Alemu, Marcus C. Allen, Ryan M. Spangler, and Athi Varuttamaseni. "A Qualitative Strategy for Fusion of Physics into Empirical Models for Process Anomaly Detection." Energies 15, no. 15 (August 3, 2022): 5640. http://dx.doi.org/10.3390/en15155640.
Full textAbstract:
To facilitate the automated online monitoring of power plants, a systematic and qualitative strategy for anomaly detection is presented. This strategy is essential to provide credible reasoning on why and when an empirical versus hybrid (i.e., physics-supported) approach should be used and to determine the ideal mix of these two approaches for a defined anomaly detection scope. Empirical methods are usually based on pattern, statistical, and causal inference. Hybrid methods include the use of physics models to train and test data methods, reduce data dimensionality, reduce data-model complexity, augment data, and reduce empirical uncertainty; hybrid methods also include the use of data to tune physics models. The presented strategy is driven by key decision points related to data relevance, simple modeling feasibility, data inference, physics-modeling value, data dimensionality, physics knowledge, method of validation, performance, data availability, and suitability for training and testing, cause-effect, entropy inference, and model fitting. The strategy is demonstrated through a pilot use case for the application of anomaly detection to capture a valve packing leak at the high-pressure coolant injection system of a nuclear power plant.
10
Cain, Sahar, Ali Risheh, and Negin Forouzesh. "A Physics-Guided Neural Network for Predicting Protein–Ligand Binding Free Energy: From Host–Guest Systems to the PDBbind Database." Biomolecules 12, no. 7 (June 29, 2022): 919. http://dx.doi.org/10.3390/biom12070919.
Full textAbstract:
Calculation of protein–ligand binding affinity is a cornerstone of drug discovery. Classic implicit solvent models, which have been widely used to accomplish this task, lack accuracy compared to experimental references. Emerging data-driven models, on the other hand, are often accurate yet not fully interpretable and also likely to be overfitted. In this research, we explore the application of Theory-Guided Data Science in studying protein–ligand binding. A hybrid model is introduced by integrating Graph Convolutional Network (data-driven model) with the GBNSR6 implicit solvent (physics-based model). The proposed physics-data model is tested on a dataset of 368 complexes from the PDBbind refined set and 72 host–guest systems. Results demonstrate that the proposed Physics-Guided Neural Network can successfully improve the “accuracy” of the pure data-driven model. In addition, the “interpretability” and “transferability” of our model have boosted compared to the purely data-driven model. Further analyses include evaluating model robustness and understanding relationships between the physical features.
Dissertations / Theses on the topic "Hybrid physics-data driven models"
1
Hussain, Mukhtar. "Data-driven discovery of mode switching conditions to create hybrid models of cyber-physical systems." Thesis, Queensland University of Technology, 2022. https://eprints.qut.edu.au/235043/1/Mukhtar_Hussain_Thesis.pdf.
Full textAbstract:
Models are essential tools for evaluating a system’s behaviour under different scenarios. However, in industrial practice pre-existing models of cyber-physical systems (CPSs) are not always available because CPSs can be legacy systems which are subject to changes and upgrades over time that may not be well documented. System identification addresses the problem by creating models from the external observation of a system. This research is concerned with hybrid system identification of CPSs, i.e., building models of dynamic systems switching between different operating modes. This thesis presents methods for discovering data-driven mode switching conditions essential for building such models.
2
Ajib, Balsam. "Data-driven building thermal modeling using system identification for hybrid systems." Thesis, Ecole nationale supérieure Mines-Télécom Lille Douai, 2018. http://www.theses.fr/2018MTLD0006/document.
Full textAbstract:
Le secteur du bâtiment est un consommateur énergétique majeur, par conséquent, un cadre d’actions a été décidé au niveau international dans le but de limiter son impact. Afin de mettre en œuvre ces mesures, il est nécessaire d’avoir à disposition des modèles offrants une description fiable du comportement thermique des bâtiments. A cet effet, cette thèse propose l’application d’une nouvelle technique guidée par les données pour la modélisation thermique des bâtiments en se basant sur l’approche des systèmes hybrides, caractérisés par des dynamiques continues et événementielles. Ce choix est motivé par le fait qu’un bâtiment est un système complexe caractérisé par des phénomènes non-linéaires et l’apparition de différents événements. On utilise les modèles affines par morceaux ou PWARX pour l’identification de systèmes hybrides. C’est une collection de sous-modèles affines représentant chacun une configuration caractérisée par une dynamique particulière. Le manuscrit commence par un état de l’art sur les principales techniques de modélisation thermique des bâtiments. Ensuite, le choix d’une approche hybride est motivé par une interprétation mathématique basée sur les équations d’un circuit thermique. Ceci est suivi par une brève présentation des modèles hybrides et une description détaillée de la méthodologie utilisée. On montre ensuite comment utiliser la technique SVM pour classifier les nouvelles données. Enfin, l’intégration des modèles PWARX dans une boucle de contrôle hybride afin d’estimer le gain en performance énergétique d’un bâtiment après rénovation est présentée. La méthodologie est validée en utilisant des données issues de cas d’études variésThe building sector is a major energy consumer, therefore, a framework of actions has been decided on by countries worldwide to limit its impact. For implementing such actions, the availability of models providing an accurate description of the thermal behavior of buildings is essential. For this purpose, this thesis proposes the application of a new data-driven technique for modeling the thermal behavior of buildings based on a hybrid system approach. Hybrid systems exhibit both continuous and discrete dynamics. This choice is motivated by the fact that a building is a complex system characterized by nonlinear phenomena and the occurrence of different events. We use a PieceWise AutoRegressive eXogeneous inputs (PWARX) model for the identification of hybrid systems. It is a collection of sub-models where each sub-model is an ARX equation representing a certain configuration in the building characterized by its own dynamics. This thesis starts with a state-of-the-art on building thermal modeling. Then, the choice of a hybrid system approach is motivated by a mathematical interpretation based on the equations derived from an RC thermal circuit of a building zone. This is followed by a brief background about hybrid system identification and a detailed description of the PWARX methodology. For the prediction phase, it is shown how to use the Support Vector Machine (SVM) technique to classify new data to the right sub-model. Then, it is shown how to integrate these models in a hybrid control loop to estimate the gain in the energy performance for a building after insulation work. The performance of the proposed technique is validated using data collected from various test cases
3
CIPOLLINI, FRANCESCA. "Data-Driven and Hybrid Methods for Naval Applications." Doctoral thesis, Università degli studi di Genova, 2020. http://hdl.handle.net/11567/989847.
Full textAbstract:
The goal of this PhD thesis is to study, design and develop data analysis methods for naval applications. Data analysis is improving our ways to understand complex phenomena by profitably taking advantage of the information laying behind a collection of data. In fact, by adopting algorithms coming from the world of statistics and machine learning it is possible to extract valuable information, without requiring specific domain knowledge of the system generating the data. The application of such methods to marine contexts opens new research scenarios, since typical naval problems can now be solved with higher accuracy rates with respect to more classical techniques, based on the physical equations governing the naval system. During this study, some major naval problems have been addressed adopting state-of-the-art and novel data analysis techniques: condition-based maintenance, consisting in assets monitoring, maintenance planning, and real-time anomaly detection; energy and consumption monitoring, in order to reduce vessel consumption and gas emissions; system safety for maneuvering control and collision avoidance; components design, in order to detect possible defects at design stage. A review of the state-of-the-art of data analysis and machine learning techniques together with the preliminary results of the application of such methods to the aforementioned problems show a growing interest in these research topics and that effective data-driven solutions can be applied to the naval context. Moreover, for some applications, data-driven models have been used in conjunction with domain-dependent methods, modelling physical phenomena, in order to exploit both mechanistic knowledge of the system and available measurements. These hybrid methods are proved to provide more accurate and interpretable results with respect to both the pure physical or data-driven approaches taken singularly, thus showing that in the naval context it is possible to offer new valuable methodologies by either providing novel statistical methods or improving the state-of-the-art ones.
4
SELICATI, VALERIA. "Innovative thermodynamic hybrid model-based and data-driven techniques for real time manufacturing sustainability assessment." Doctoral thesis, Università degli studi della Basilicata, 2022. http://hdl.handle.net/11563/157566.
Full textAbstract:
This doctoral thesis is the result of the supervision and collaboration of the University of Basilicata, the Polytechnic of Bari, and the enterprise Master Italy s.r.l.
The main research lines explored and discussed in the thesis are: sustainability in general and, more specifically, manufacturing sustainability, the Industry 4.0 paradigm linked to smart (green) manufacturing, model-based assessment techniques of manufacturing processes, and data-driven analysis methodologies. These seemingly unrelated topics are handled throughout the thesis in such a way that it reveal how strongly interwoven and characterised by transversality they are.
The goal of the PhD programme was to design and validate innovative assessment models in order to investigate the nature of manufacturing processes and rationalize the relationships and correlations between the different stages of the process. This composite model may be utilized as a tool in political decision-making about the long-term development of industrial processes and the continuous improvement of manufacturing processes. The overarching goal of this research is to provide strategies for real-time monitoring of manufacturing performance and sustainability based on hybrid thermodynamic models of the first and second order, as well as those based on data and machine learning. The proposed model is tested on a real industrial case study using a systemic approach: the phases of identifying the requirements, data inventory (materials, energetic, geometric, physical, economic, social, qualitative, quantitative), modelling, analysis, ad hoc algorithm adjustment (tuning), implementation, and validation are developed for the aluminium alloy die-casting processes of Master Italy s.r.l., a southern Italian SME which designs and produces the accessories and metal components for windows since 1986.
The thesis digs in the topic of the sustainability of smart industrial processes from each and every perspective, including both the quantity and quality of resources used throughout the manufacturing process's life cycle. Traditional sustainability analysis models (such as life cycle analysis, LCA) are combined with approaches based on the second law of thermodynamics (exergetic analysis); they are then complemented by models based on information technology (big-data analysis). A full analysis of the potential of each strategy, whether executed alone or in combination, is provided. Following a summary of the metrics relevant for determining the degree of sustainability of industrial processes, the case study is demonstrated using modelling and extensive analysis of the processes, namely aluminium alloy die casting. After assessing the sustainability of production processes using a model-based approach, we move on to the real-time application of machine learning analyses with the goal of identifying downtime and failures during the production cycle and predicting their occurrence well in advance using real-time process thermodynamic parameter values and automatic learning. Finally, the thesis suggests the use of integrated models on various case studies, such as laser deposition processes and the renovation of existing buildings, to demonstrate the multidisciplinarity and transversality of these issues.
The thesis reveals fascinating findings derived from the use of a hybrid method to assessing the sustainability of manufacturing processes, combining exergetic analysis with life cycle assessment. The proposed theme is completely current and relevant to the most recent developments in the field of industrial sustainability, combining traditional model-based approaches with innovative approaches based on the collection of big data and its analysis using the most appropriate machine learning methodologies. Furthermore, the thesis demonstrates a highly promising application of machine learning approaches to real-time data collected in order to identify any fault source in the manufacturing line beginning with sustainability measures generated from exergetic analysis and life cycle analysis. As such, it unquestionably represents an advancement above earlier information depicted in the initial state of the art. In actuality, manufacturing companies that implement business strategies based on smart models and key enabling technologies today have a higher market value in terms of quality, customisation, flexibility, and sustainability.
5
MIGLIANTI, LEONARDO PIETRO. "Modelling of the cavitating propeller noise by means of semi-empirical and data driven approaches." Doctoral thesis, Università degli studi di Genova, 2020. http://hdl.handle.net/11567/1004161.
Full textAbstract:
Historically, the mitigation of the ship radiated noise in the water was a prerogative of naval ships due to quiet requirements.
In the last decades, the need for merchant ships and pleasure craft to ensure high standards of comfort on board in terms of on board radiated noise and structural vibrations lead also, indirectly, towards the reduction of underwater radiated noise.
Nowadays, the greater awareness about the damages to the marine ecosystem as a result of the ship noise pollution is leading governments and international institutions towards the study of possible limits to acoustic emissions, which could be applied, to different levels, to protected marine areas and to more general navigation routes.
Propeller, when cavitating, is the main source of radiated noise for conventional ships together with the engines; propeller cavitation, contrarily to machinery, is not linked to single frequencies, being a broadband noise. Its reduction is thus becoming one of the objectives in new propellers design.
One of the most effective and common way to assess the propeller cavitation noise is by experimental tests in model scale. This procedure is rather expensive and time consuming, thus it is rather difficult to include it in an iterative design loop.
The aim of the present PhD thesis is the development of semi-empirical methods for the prediction of the propeller cavitating noise, in order to provide the designer with a tool capable of allowing prediction of underwater radiated noise at early design stages. Moreover, the same method can be applied in order to enhance the capability of prediction of underwater radiated noise from model scale tests, allowing to obtain indications also for operating conditions not directly reproducible due to scaling effects.
Attention has been devoted to the most common cavitation phenomena, i.e. back sheet cavitation and tip vortex.
The considered methods are derived from physical formulations available in literature and purely data driven models coming from the machine learning field, exploiting also the advantages of their combination in hybrid models.
In order to build and test the noise models, a dataset of propeller cavitating noise has been collected and processed, including relevant information on the input characteristics (i.e. propeller geometry, working point, ship wake description) and corresponding radiated noise.
The experimental campaigns have been performed at the cavitation tunnel of the University of Genoa, considering three controllable pitch propellers in twin screw configuration.
The dataset has been exploited to build different models of increasing complexity, to predict the radiated noise spectrum.
The methodologies proposed allowed to obtain encouraging results providing a valuable basis for further investigations and developments of this approach.
6
Eker, Ömer F. "A hybrid prognostic methodology and its application to well-controlled engineering systems." Thesis, Cranfield University, 2015. http://dspace.lib.cranfield.ac.uk/handle/1826/9269.
Full textAbstract:
This thesis presents a novel hybrid prognostic methodology, integrating physics-based and data-driven prognostic models, to enhance the prognostic accuracy, robustness, and applicability. The presented prognostic methodology integrates the short-term predictions of a physics-based model with the longer term projection of a similarity-based data-driven model, to obtain remaining useful life estimations. The hybrid prognostic methodology has been applied on specific components of two different engineering systems, one which represents accelerated, and the other a nominal degradation process. Clogged filter and fatigue crack propagation failure cases are selected as case studies. An experimental rig has been developed to investigate the accelerated clogging phenomena whereas the publicly available Virkler fatigue crack propagation dataset is chosen after an extensive literature search and dataset analysis. The filter clogging experimental rig is designed to obtain reproducible filter clogging data under different operational profiles. This data is thought to be a good benchmark dataset for prognostic models. The performance of the presented methodology has been evaluated by comparing remaining useful life estimations obtained from both hybrid and individual prognostic models. This comparison has been based on the most recent prognostic evaluation metrics. The results show that the presented methodology improves accuracy, robustness and applicability. The work contained herein is therefore expected to contribute to scientific knowledge as well as industrial technology development.
7
Wileman, Andrew John. "An investigation into the prognosis of electromagnetic relays." Thesis, Cranfield University, 2016. http://dspace.lib.cranfield.ac.uk/handle/1826/13665.
Full textAbstract:
Electrical contacts provide a well-proven solution to switching various loads in a wide variety of applications, such as power distribution, control applications, automotive and telecommunications. However, electrical contacts are known for limited reliability due to degradation effects upon the switching contacts due to arcing and fretting. Essentially, the life of the device may be determined by the limited life of the contacts. Failure to trip, spurious tripping and contact welding can, in critical applications such as control systems for avionics and nuclear power application, cause significant costs due to downtime, as well as safety implications. Prognostics provides a way to assess the remaining useful life (RUL) of a component based on its current state of health and its anticipated future usage and operating conditions. In this thesis, the effects of contact wear on a set of electromagnetic relays used in an avionic power controller is examined, and how contact resistance combined with a prognostic approach, can be used to ascertain the RUL of the device. Two methodologies are presented, firstly a Physics based Model (PbM) of the degradation using the predicted material loss due to arc damage. Secondly a computationally efficient technique using posterior degradation data to form a state space model in real time via a Sliding Window Recursive Least Squares (SWRLS) algorithm. Health monitoring using the presented techniques can provide knowledge of impending failure in high reliability applications where the risks associated with loss-of-functionality are too high to endure. The future states of the systems has been estimated based on a Particle and Kalman-filter projection of the models via a Bayesian framework. Performance of the prognostication health management algorithm during the contacts life has been quantified using performance evaluation metrics. Model predictions have been correlated with experimental data. Prognostic metrics including Prognostic Horizon (PH), alpha-Lamda (α-λ), and Relative Accuracy have been used to assess the performance of the damage proxies and a comparison of the two models made.
8
Kleman, Björn, and Henrik Lindgren. "Evaluation of model-based fault diagnosis combining physical insights and neural networks applied to an exhaust gas treatment system case study." Thesis, Linköpings universitet, Fordonssystem, 2021. http://urn.kb.se/resolve?urn=urn:nbn:se:liu:diva-176650.
Full textAbstract:
Fault diagnosis can be used to early detect faults in a technical system, which means that workshop service can be planned before a component is fully degraded. Fault diagnosis helps with avoiding downtime, accidents and can be used to reduce emissions for certain applications. Traditionally, however, diagnosis systems have been designed using ad hoc methods and a lot of system knowledge. Model-based diagnosis is a systematic way of designing diagnosis systems that is modular and offers high performance. A model-based diagnosis system can be designed by making use of mathematical models that are otherwise used for simulation and control applications. A downside of model-based diagnosis is the modeling effort needed when no accurate models are available, which can take a large amount of time. This has motivated the use of data-driven diagnosis. Data-driven methods do not require as much system knowledge and modeling effort though they require large amounts of data and data from faults that can be hard to gather. Hybrid fault diagnosis methods combining models and training data can take advantage of both approaches decreasing the amount of time needed for modeling and does not require data from faults. In this thesis work a combined data-driven and model-based fault diagnosis system has been developed and evaluated for the exhaust treatment system in a heavy-duty diesel engine truck. The diagnosis system combines physical insights and neural networks to detect and isolate faults for the exhaust treatment system. This diagnosis system is compared with another system developed during this thesis using only model-based methods. Experiments have been done by using data from a heavy-duty truck from Scania. The results show the effectiveness of both methods in an industrial setting. It is shown how model-based approaches can be used to improve diagnostic performance. The hybrid method is showed to be an efficient way of developing a diagnosis system. Some downsides are highlighted such as the performance of the system developed using data-driven and model-based methods depending on the quality of the training data. Future work regarding the modularity and transferability of the hybrid method can be done for further evaluation.
9
Mesbahi, Tedjani. "Influence des stratégies de gestion d’une source hybride de véhicule électrique sur son dimensionnement et sa durée de vie par intégration d’un modèle multi-physique." Thesis, Ecole centrale de Lille, 2016. http://www.theses.fr/2016ECLI0004/document.
Full textAbstract:
Ce mémoire contribue à l’amélioration des performances d’une source de stockage hybride embarquée alimentant un véhicule électrique. La solution investiguée est composée de l’association de batteries Li-ion et de super condensateurs, dans le but d’obtenir, par rapport aux solutions classiques, un gain en masse et en durée de vie pour une certaine plage d’autonomie du véhicule. Notre objectif est de mettre à profit l’utilisation de nouvelles méthodes de gestion de la source hybride et de quantifier le gain obtenu. Un modèle multi-physique incluant les aspects électrique, thermique et vieillissement a été développé et intégré dans l’algorithme de gestion d’énergie afin d’évaluer la dégradation progressive des performances des éléments de stockage au cours des cycles de conduite selon la stratégie de gestion implantée. De nouvelles stratégies de gestion ayant pour objectif d’agir sur la durée de vie ont été évaluées. Leur impact sur les performances de la source en termes de masse, coût et durée de vie a pu être quantifié et montre bien que par une meilleure gestion des puissances, il est possible de mieux utiliser le stockeur hybride, ouvrant ainsi la voie à de nouvelles approches de gestion d’énergie pour ces systèmesThis thesis contributes to the improvement of hybrid embedded source performances supplies an electric vehicle. The studied solution is composed of Li-ion batteries and supercapacitors hybridization, with an aim to achieve improved performances in terms of weight and lifetime over traditional solutions. Our main goal is to take the best advantage of new energy management strategies of the hybrid embedded source and quantify obtained improvements. A multi-physic model including electric, thermal and aging behaviors is developed and integrated into the algorithm of energy management in order to evaluate the gradual degradation of storage components performances during driving cycles and implemented control strategy. New energy management strategies intended to act on the lifetime of hybrid embedded source have been evaluated. Their impact on the performances of the source in terms of weight, cost and lifetime has been quantified and clearly shows that it is possible to make better use of hybrid embedded source thanks to a good power sharing, thus opening the way to new approaches of energy management for these systems
10
Rautela, Mahindra Singh. "Hybrid Physics-Data Driven Models for the Solution of Mechanics Based Inverse Problems." Thesis, 2023. https://etd.iisc.ac.in/handle/2005/6123.
Full textAbstract:
Inverse problems pose a significant challenge as they aim to estimate the causal factors that result in a measured response. However, the responses are often truncated, partially available, and corrupted by measurement noise, rendering the problems ill-posed, and may have multiple or no solutions. Solving such problems using regularization transforms them into a family of well-posed functions. While physics-based models are interpretable, they operate under approximations and assumptions. Data-driven models such as machine learning and deep learning have shown promise in solving mechanics-based inverse problems, but they lack robustness, convergence, and generalization when operating under partial information, compromising the interpretability and explainability of their predictions. To overcome these challenges, hybrid physics-data-driven models can be formulated by integrating prior knowledge of physical laws, expert knowledge, spatial invariances, empirically validated rules, etc., acting as a regularizing agent to select a more feasible solution space. This approach improves prediction accuracy, robustness, generalization, interpretability, and explainability of the data-driven models. In this dissertation, we propose various physics-data-driven models to solve inverse problems related to engineering mechanics by integrating prior knowledge and its representation into a data-driven pipeline at different stages. We have used these hybrid models to solve six different inverse problems, such as leakage estimation of a pressurized habitat, estimating dispersion relations of a waveguide, structural damage identification, filtering temperature effects in guided waves, material property prediction, and guided wave generation and material design.
The dissertation presents a detailed overview of inverse problems, definitions of the six inverse problems, and the motivation behind using hybrid models for their solution. Six different hybrid models, such as adaptive model calibration, physics-informed neural networks, inverse deep surrogate, deep latent variable, and unsupervised representation learning models, are formulated, and arranged on different levels of a pyramid, showing the trade-off between autonomy and explainability. All these new methods are designed with practical implementation in mind. The first model uses an adaptive real-time calibration framework to estimate the severity of leaks in a pressurized deep space habitat before they become a threat to the crew and habitat. The second model utilizes a physics-informed neural network to estimate the speed of wave propagation in a waveguide from limited experimental observations. The third model uses deep surrogate models to solve structural damage identification and material property prediction problems. The fourth model proposes a domain knowledge-based data augmentation scheme for ultrasonic guided waves-based damage identification. The fifth model uses unsupervised feature learning to solve guided waves-based structural anomaly detection and filtering the temperature effects on guided waves. The final model employs a deep latent variable model for structural anomaly detection, guided wave generation, and material design problems. Overall, the thesis demonstrates the effectiveness of hybrid models that combine prior knowledge with machine learning techniques to address a wide range of inverse problems. These models offer faster, more accurate, and more automated solutions to these problems than traditional methods.
Books on the topic "Hybrid physics-data driven models"
1
Perez, Gerald Augusto Corzo. Hybrid Models for Hydrological Forecasting : Integration of Data-Driven and Conceptual Modelling Techniques: UNESCO-IHE PhD Thesis. Taylor & Francis Group, 2017.
Find full text
2
Lægreid, Per. New Public Management. Oxford University Press, 2017. http://dx.doi.org/10.1093/acrefore/9780190228637.013.159.
Full textAbstract:
New Public Management (NPM) reforms have been around in many countries for over the past 30 years. NPM is an ambiguous, multifaceted, and expanded concept. There is not a single driving force behind it, but rather a mixture of structural and polity features, national historical-institutional contexts, external pressures, and deliberate choices from political and administrative executives. NPM is not the only show in town, and contextual features matter. There is no convergence toward one common NPM model, but significant variations exist between countries, government levels, policy areas, tasks, and over time. Its effects have been found to be ambiguous, inconclusive, and contested. Generally, there is a lack of reliable data on results and implications, and there is some way to go before one can claim evidence-based policymaking in this field. There is more knowledge regarding NPM’s effects on processes and activities than on outcome, and reliable comparative data on variations over time and across countries are missing. NPM has enhanced managerial accountability and accountability to users and customers, but has this success been at the expense of political accountability? New trends in reforms, such as whole-of-government, have been added to NPM, thereby making public administration more complex and hybrid.
Book chapters on the topic "Hybrid physics-data driven models"
1
Araghinejad, Shahab. "Hybrid Models and Multi-model Data Fusion." In Data-Driven Modeling: Using MATLAB® in Water Resources and Environmental Engineering, 253–65. Dordrecht: Springer Netherlands, 2013. http://dx.doi.org/10.1007/978-94-007-7506-0_8.
Full text
2
Abdulali, Arsen, and Seokhee Jeon. "Haptic Software Design." In Springer Series on Touch and Haptic Systems, 537–85. Cham: Springer International Publishing, 2022. http://dx.doi.org/10.1007/978-3-031-04536-3_12.
Full textAbstract:
AbstractThis chapter reviews design concepts of haptic modeling and rendering software. The main focus lies in realistic kinesthetic and tactile haptic models for virtual and augmented reality based on the data collected from physical objects. We consider both data-driven algorithms providing a black-box action-response mapping and measurement-based approaches identifying parameters of physics-based models. To show the research landscape and highlight ongoing research challenges, we introduce a series of state-of-the-art methods including data-driven models with deterministic and stochastic responses, physics-based simulation using optimization-based FEM solver, and hybrid approaches of combining the concepts of both data-driven and physics-based methods. These examples also cover a wide range of haptic properties, i.e., modeling and rendering of elasticity and plasticity, tool deformation, and haptic textures.
3
Traini, Emiliano, Giulia Bruno, and Franco Lombardi. "Design of a Physics-Based and Data-Driven Hybrid Model for Predictive Maintenance." In Advances in Production Management Systems. Artificial Intelligence for Sustainable and Resilient Production Systems, 536–43. Cham: Springer International Publishing, 2021. http://dx.doi.org/10.1007/978-3-030-85914-5_57.
Full text
4
Valeti, Bhavana, and Shamim N. Pakzad. "Uncertainty Propagation in a Hybrid Data-Driven and Physics-Based Submodeling Method for Refined Response Estimation." In Model Validation and Uncertainty Quantification, Volume 3, 349–59. Cham: Springer International Publishing, 2020. http://dx.doi.org/10.1007/978-3-030-47638-0_38.
Full text
5
Wilde, A. S., S. Gellrich, M. Mennenga, T. Abraham, and C. Herrmann. "Data-Driven Business Models for Life Cycle Technologies: Exemplary Planning for Hybrid Components." In Lecture Notes in Production Engineering, 488–96. Cham: Springer International Publishing, 2021. http://dx.doi.org/10.1007/978-3-030-78424-9_54.
Full text
6
Pohlkötter, Fabian J., Dominik Straubinger, Alexander M. Kuhn, Christian Imgrund, and William Tekouo. "Unlocking the Potential of Digital Twins." In Advances in Automotive Production Technology – Towards Software-Defined Manufacturing and Resilient Supply Chains, 190–99. Cham: Springer International Publishing, 2023. http://dx.doi.org/10.1007/978-3-031-27933-1_18.
Full textAbstract:
AbstractIncreasing competitive pressure is confronting the automotive industry with major challenges. As a result, conventional reactive maintenance is being transformed into predictive maintenance. In this context, wearing and aging effects no longer lead to plant failure since they are predicted at an earlier stage based on comprehensive data analysis.Furthermore, the evolution towards Smart Factory has given rise to virtual commissioning in the planning phase of production plants. In this process, a Hardware-in-the-Loop (HiL) system combines the real controls (e.g., PLC) and a virtual model of the plant. These HiL systems are used to simulate commissioning activities in advance, thus saving time and money during actual commissioning. The resulting complex virtual models are not further used in the series production.This paper builds upon virtual commissioning models to develop a Digital Twin, which provides inputs for predictive maintenance. The resulting approach is a methodology for building a hybrid predictive maintenance system. A hybrid prediction model combines the advantages of data-driven and physical models. Data-driven models analyse and predict wearing patterns based on real machine data. Physical models are used to reproduce the behaviour of a system. From the simulation of the hybrid model, additional insights for the predictions can be derived.The conceptual methodology for a hybrid predictive maintenance system is validated by the successful implementation in a bottleneck process of the electric engine production for an automotive manufacturer. Ultimately, an outlook on further possible applications of the hybrid model is presented.
7
Hasanov, Fakhri J., Frederick L. Joutz, Jeyhun I. Mikayilov, and Muhammad Javid. "KGEMM Methodology." In SpringerBriefs in Economics, 21–24. Cham: Springer International Publishing, 2023. http://dx.doi.org/10.1007/978-3-031-12275-0_4.
Full textAbstract:
AbstractThis chapter briefly describes the methodological framework KGEMM uses. KGEMM is a hybrid model, i.e., it brings together theoretical and empirical coherences at some degree. Put differently, KGEMM nests “theory-driven” and “data-driven” approaches as suggested by Hendry (2018), among others, and employed by modelers in building semi-structural macroeconometric models (e.g., see Jelić and Ravnik 2021; Gervais and Gosselin 2014; Bulligan et al. 2017). For this purpose, it uses an equilibrium correction modeling (ECM) framework, in which the long-run relationships follow economic theories, and the short-run relationships are mainly data-driven (see Pagan 2003a, b inter alia). Hara et al. (2009) and Yoshida (1990), among others, note that ECM-based MEMs provide realistic results as their equilibrium correction mechanisms help stabilize long-term projections and capture short-term fluctuations more than other models while Engle et al. (1989) find the forecast performance of ECM more accurate.
8
Camargo, Manuel, Marlon Dumas, and Oscar González-Rojas. "Learning Accurate Business Process Simulation Models from Event Logs via Automated Process Discovery and Deep Learning." In Advanced Information Systems Engineering, 55–71. Cham: Springer International Publishing, 2022. http://dx.doi.org/10.1007/978-3-031-07472-1_4.
Full textAbstract:
AbstractBusiness process simulation is a well-known approach to estimate the impact of changes to a process with respect to time and cost measures – a practice known as what-if process analysis. The usefulness of such estimations hinges on the accuracy of the underlying simulation model. Data-Driven Simulation (DDS) methods leverage process mining techniques to learn process simulation models from event logs. Empirical studies have shown that, while DDS models adequately capture the observed sequences of activities and their frequencies, they fail to accurately capture the temporal dynamics of real-life processes. In contrast, generative Deep Learning (DL) models are better able to capture such temporal dynamics. The drawback of DL models is that users cannot alter them for what-if analysis due to their black-box nature. This paper presents a hybrid approach to learn process simulation models from event logs wherein a (stochastic) process model is extracted via DDS techniques, and then combined with a DL model to generate timestamped event sequences. An experimental evaluation shows that the resulting hybrid simulation models match the temporal accuracy of pure DL models, while partially retaining the what-if analysis capability of DDS approaches.
9
Precup, Radu-Emil, Raul-Cristian Roman, and Ali Safaei. "Hybrid Model-Free and Model-Free Adaptive Fuzzy Controllers." In Data-Driven Model-Free Controllers, 259–342. Boca Raton: CRC Press, 2021. http://dx.doi.org/10.1201/9781003143444-7.
Full text
10
Precup, Radu-Emil, Raul-Cristian Roman, and Ali Safaei. "Hybrid Model-Free and Model-Free Adaptive Virtual Reference Feedback Tuning Controllers." In Data-Driven Model-Free Controllers, 211–57. Boca Raton: CRC Press, 2021. http://dx.doi.org/10.1201/9781003143444-6.
Full textConference papers on the topic "Hybrid physics-data driven models"
1
Chinesta, F., E. Cueto, and J. Duval. "Physics-based and data-driven hybrid modeling: when data enrich models and models render data smarter." In 9th edition of the International Conference on Computational Methods for Coupled Problems in Science and Engineering. CIMNE, 2021. http://dx.doi.org/10.23967/coupled.2021.068.
Full text
2
Zalavadia, Hardikkumar, Utkarsh Sinha, Prithvi Singh, and Sathish Sankaran. "Discovery of Unconventional Reservoir Flow Physics for Production Forecasting Through Hybrid Data-Driven and Physics Models." In SPE Western Regional Meeting. SPE, 2023. http://dx.doi.org/10.2118/213004-ms.
Full textAbstract:
Abstract Routinely analyzing producing well performance in unconventional field is critical to maintain their profitability. In addition to continuous analysis, there is an increasing need to develop models that are scalable across entire field. Pure data-driven approaches, such as DCA, are prevalent but fail to capture essential physical elements, compounded by lack of key operational parameters such as pressures and fluid property changes across large number of wells. Traditional models such as numerical simulations face a scalability challenge to extend to large well counts with rapid pace of operations. Other widely used method is rate transient analysis (RTA), which requires identification of flow regimes and mechanistic model assumptions, making it interpretive and non-conducive to field-scale applications. The objective in this study is to build data-driven and physics-constrained reservoir models from routine data (rates and pressures) for pressure-aware production forecasting. We propose a hybrid data-driven and physics informed model based on sparse nonlinear regression (SNR) for identifying rate-pressure relationships in unconventionals. Hybrid SNR is a novel framework to discover governing equations underlying fluid flow in unconventionals, simply from production and pressure data, leveraging advances in sparsity techniques and machine learning. The method utilizes a library of data-driven functions along with information from standard flow-regime equations that form the basis for traditional RTA. However, the model is not limited to fixed known relationships of pressure and rates that are applicable only under certain assumptions (e.g. planar fractures, single-phase flowing conditions etc.). Complex, non-uniform fractures, and multi-phase flow of fluids do not follow the same diagnostics behavior but exhibits more complex behavior not explained by analytical equations. The hybrid SNR approach identifies these complexities from combination of the most relevant pressure and time features that explain the phase rates behavior for a given well, thus enables forecasting the well for different flowing pressure/operating conditions. In addition, the method allows identification of dominant flow regimes through highest contributing terms without performing typical line fitting procedure. The method has been validated against synthetic model with constant and varying bottom hole pressures. The results indicate good model accuracies to identify relevant set of features that dictate rate-pressure behavior and perform production forecasts for new bottom-hole pressure profiles. The method is robust since it can be applied to any well with different fluid types, flowing conditions and does not require any mechanistic fracture or simulation model assumptions and hence applicable to any reservoir complexity. The novelty of the method is that the hybrid SNR can resolve several modes that govern the flow process simultaneously that can provide physical insights on the prevailing multiple complex flow regimes.
3
Erge, Oney, and Eric van Oort. "Hybrid Physics-Based and Data-Driven Modeling for Improved Standpipe Pressure Prediction." In SPE/IADC International Drilling Conference and Exhibition. SPE, 2021. http://dx.doi.org/10.2118/204094-ms.
Full textAbstract:
Abstract During drilling operations, it is common to see pump pressure spikes when flow is initiated, including after a connection or after a prolonged break in drilling operations. It is important to be able to predict the magnitude of such pressure spikes to avoid compromising wellbore integrity. This study shows how a hybrid approach using data-driven machine learning coupled with physics-based modeling can be used to accurately predict the magnitude of pressure spikes. To model standpipe pressure behavior, machine learning techniques were combined with physics-based models via a rule-based, stochastic decision-making algorithm. To start, neural networks and deep learning models were trained using time-series drilling data. From there, physics-based equations that model the pressure required to break the mud's gel strength as well as the flow of non-Newtonian fluids through the entire circulation system were used to simulate standpipe pressure. Then, these two highly different methods for predicting/modeling standpipe pressure were combined by a hidden Markov model using a set of rules and transition probabilities. By combining machine learning and physics-based approaches, the best features of each model are leveraged by the hidden Markov model, yielding a more accurate and robust prediction of pressure. A similar result is not achievable with a purely data-driven black-box model, because it lacks a connection to the underlying physics. Our study highlights how drilling data analysis can be optimally leveraged. The overarching conclusion: hybrid modeling can more accurately predict pump pressure spikes and capture the transient events at flow initiation when compared to physics-based or machine learning models used in isolation. Moreover, the approach is not limited to pressure behavior but can be applied to a wide range of well construction operations. The proposed approach is easy to implement and the details of implementation are presented in this study. Being able to accurately model and manage the pressure response during drilling operations is essential, especially for wells drilled in narrow-margin environments. Pressure can be more accurately predicted through our proposed hybrid modeling, leading to safer, more optimized operations.
4
Kovalev, Dmitry, Sergey Safonov, Klemens Katterbauer, and Alberto Marsala. "Hybrid Physics-Constrained and Data-Driven Approach for Interwell Saturation Estimation from Well Logs." In Abu Dhabi International Petroleum Exhibition & Conference. SPE, 2021. http://dx.doi.org/10.2118/207457-ms.
Full textAbstract:
Abstract Combining physics-based models for well log analysis with artificial intelligence (AI) advanced algorithms is crucial for wellbore studies. Data-driven methods do not generalize well and lack theoretical knowledge accumulated in the field. Estimating well saturation significantly improves if predictions from physical models are used to constrain data-driven algorithms in outlined primary fluid channels and other important points of interest. Saturation propagations in the reservoirs interwell region also generalize better under using combination of models. This work addresses combined usage of theoretical and data-driven models by aggregating them into single hybrid model. Multiple physical and data-driven models are under study, their parameters are optimized using observations. Weighted sum is used to predict water saturation at every point with weights being recomputed at each step. Model outputs are compared in terms accuracy and cumulative loss. A synthesized reservoir box model encompassing volumetric interwell porosity, resistivity and saturation data is used for the validation of the algorithms. Aggregated model for estimating interwell saturation shows improved prediction accuracy compared both to physics-based or data-driven approaches separately.
5
Zalavadia, Hardikkumar, Metin Gokdemir, Utkarsh Sinha, Prithvi Singh, and Sathish Sankaran. "Real Time Artificial Lift Timing and Selection Using Hybrid Data-Driven and Physics Models." In SPE Western Regional Meeting. SPE, 2023. http://dx.doi.org/10.2118/213040-ms.
Full textAbstract:
Abstract Artificial lift is the backbone of unconventional field production. Lifting oil and gas in an optimal manner and economically is one of the most challenging phases of field development with depleting reservoir energy. Traditional approaches of lift selection are not sufficient to manage unconventional wells effectively, with high decline rates initially. It is of prime interest to understand production behavior under different lift conditions since the decision on timing and design of lift method are crucial for optimizing the well performance. This paper presents an artificial-lift timing and selection (ALTS) methodology based on a hybrid data-driven and physics-based workflow to maximize the value of unconventional oil and gas assets. Our formulation employs a reduced physics model that is based on identification of Dynamic Drainage Volume (DDV) using commonly measured data (daily production rates and wellhead pressure) to calculate reservoir pressure depletion, transient productivity index (PI) and dynamic inflow performance relationship (IPR). Transient PI as the forecasting variable allows normalizing both surface pressure effects and considers phase behavior, thus reducing noise. The PI-based forecasting method is used to predict future IPRs and subsequently oil, water, and gas rates for any bottom hole pressure condition. The workflow allows estimating well deliverability under different artificial lift types and design parameters. The ALTS workflow was applied to real field cases for wells flowing under different operating conditions to optimize the best strategy to produce the well amongst several candidate scenarios. Transient PI and dynamic IPR results provided valuable insights on how and when to select different AL systems. The workflow is run periodically with everchanging subsurface and wellbore conditions against each candidate scenario with various pump models and other operating parameters (pressure, speed etc.). The method was applied to several wells in a hindcasting mode to evaluate lost production opportunity and validate the results. In certain cases, the optimal recommendation pointed to selecting a different artificial lift system than the chosen method in the field to significantly improve long term well performance. In addition, optimal artificial lift operating point recommendations are made for wells including optimal gas lift rates for gas lifted wells, optimal pump unit selection and speed for wells on ESP and SRP. The proposed method allows predicting future unconventional reservoir IPR consistently and has allowed continuous evaluation of artificial lift timing and selection scenarios for multiple lift types and designs in unconventional reservoirs. This can transform incumbent practices based on broad field heuristics, which are often ad hoc, inefficient, and manually intensive, towards well-specific ALTS analysis to improve field economics. Continuous application of this process is shown to improve production, reduce deferred production and increase life of lift equipment.
6
Nagao, Masahiro, Wenyue Sun, and Sathish Sankaran. "Data-Driven Discovery of Physics for Reservoir Surveillance." In SPE Western Regional Meeting. SPE, 2022. http://dx.doi.org/10.2118/209300-ms.
Full textAbstract:
Abstract Understanding well production performance in hydrocarbon reservoirs in a timely manner is essential for closed loop reservoir management, improving operational efficiency, and maximizing value. It is desirable to have a robust and scalable method for estimating well productivity index and reservoir pressure, which can be applied in a practical and automated manner. Traditional surveillance methods are interpretive and do not scale for manual surveillance of either large fields or those with large data volumes. In this work, we propose a machine learning approach to discover physics that can be built using routine field measurements (downhole pressure and rates) and used for estimating well productivity, real-time production rates, pressure depletion and short-term forecasts. The relationship between rates and pressure evolution is guided by nonlinear diffusivity equation. We seek methods for projecting the nonlinear state problem onto a linear (or weakly linear) space based on several methods – namely, time delay embedding, physics-inspired features, and dynamic mode decomposition (DMD). This augments the information contained in the system state with measurements of the state history. We also developed a background signal decomposition method to extrapolate routine buildup pressure data to estimate average reservoir pressure based on two different methods – optDMD (optimized DMD) and SINDy (sparse identification of nonlinear dynamics). The background signal decomposition method was validated on several heterogeneous reservoir cases to estimate average reservoir pressure from buildup data, where our results outperformed traditional methods. In cases where multiphase flow meter rates were available, the proposed hybrid reservoir model was used to predict pressure with a virtual shut-in simulation. By offsetting the need for shutting in the well and associated production deferment, the virtual shut-in predictions were used to estimate reservoir properties. The results were validated on both pressures and pressure derivatives, typically used for pressure transient analysis. Next, we observed that the model can be used to provide accurate multiphase production rate forecasting (virtual metering) by reversing the model inputs and outputs. Based on the hybrid model, a workflow for tracking reservoir properties was developed to capture the decline of average reservoir pressure and productivity index, which was applied to both synthetic and field cases with reasonable accuracy. The proposed hybrid reservoir modeling approach automates routine surveillance at field scale with high computational efficiency. By learning from natural operational variations continuously, it decreases planned downtime and associated production loss. It also enables detecting well performance issues much earlier to plan timely remedial actions. It provides a practical way of combining data-driven methods with our understanding of physics, while keeping the analysis interpretable and enabling closed loop reservoir management.
7
Stoffel, Phillip, Charlotte Loffler, Steffen Eser, Alexander Kumpel, and Dirk Muller. "Combining Data-driven and Physics-based Process Models for Hybrid Model Predictive Control of Building Energy Systems." In 2022 30th Mediterranean Conference on Control and Automation (MED). IEEE, 2022. http://dx.doi.org/10.1109/med54222.2022.9837277.
Full text
8
Michael, Andreas. "A Hybrid Data-Driven/Physics-Based Approach for Near-Wellbore Hydraulic Fracture Modeling." In SPE Hydraulic Fracturing Technology Conference and Exhibition. SPE, 2023. http://dx.doi.org/10.2118/212355-ms.
Full textAbstract:
Abstract Variables affecting the near-wellbore region of a fractured well have a big impact on its post-stimulation well performance. Optimal hydraulic fracture (HF) initiation and early-phase propagation results in minimal near-wellbore tortuosity, decreasing the likelihood of screenouts and maximizing the resultant well productivity. While most predictive models for the HF geometry produced in a stimulation treatment consider the far-field region, the near-wellbore vicinity should be an integral part of a properly-engineered reservoir exploitation strategy, impacting the treatment's design and execution. In this work, a hybrid data-driven/physics-based approach is elaborated for modeling HF initiation and early-phase propagation from perforated horizontal wells. An optimization scheme via oriented perforating is presented using the developed hybrid model, considering the orientation of the induced HF initiation (longitudinal or transverse with respect to a well drilled along the minimum horizontal in-situ principal stress) and the resultant formation breakdown pressure (FBP); the highest the wellbore pressure reached during the treatment. Transverse HF initiation (and early-phase propagation) is ideal for wells drilled in low-permeability "tight" formations, while FBP minimization decreases the overall on-site horsepower requirements for the stimulation treatment. The demonstrated optimization scheme is applied separately to the in-situ stress states of seven prolific shale plays from the U.S. and Argentina, suggesting oriented-perforating strategies targeting the promotion of transverse HF initiation in two of these (Barnett and Marcellus), while targeting FBP minimization in the remaining five (Bakken, Fayetteville, Haynesville, Niobrara, and Vaca Muerta). The effectiveness of such oriented-perforating strategies can potentially be compromised by fracturing fluid leakage around the borehole's circumference, which is shown to hinder transverse HF initiation. The hybrid model is also used to estimate fracture initiation pressure (FIP) values for the seven shale plays studied, indicating significant discrepancies with analytical expressions used to approximate these FIPs in modern-day HF computational simulations. Finally, the framework is set for expanding this modeling approach over a range of in-situ stress states, incorporating data-driven (numerically-derived) aggregate correction factors to compensate for inaccuracies in the analytical approximations, which comprise the physics-based core of the proposed hybrid model. The impact of perforation geometry was not addressed in this study.
9
Sinha, Utkarsh, Hardikkumar Zalavadia, and Sathish Sankaran. "Physics Guided Data Driven Model to Forecast Production Rates in Liquid Wells." In SPE Oklahoma City Oil and Gas Symposium. SPE, 2023. http://dx.doi.org/10.2118/213103-ms.
Full textAbstract:
Abstract In the development of shale plays, significant emphasis has been laid on forecasting well performance based on rates and finding the expected ultimate recoveries. Specifically, forecasting producing gas-oil-ratio (GOR) over the long term has been problematic, given the complexities and uncertainties in modeling a muti-stage fractured horizontal well in the unconventional reservoir. In this work, we propose a hybrid model which is capable of accurately forecasting multiphase flow rates. The proposed hybrid forecasting modeling is an amalgamation of data-centric methodology blended with physics-based principles, using easily available inputs such as production rates, flowing pressure, and fluid properties. The proposed method is a two-step procedure – (1) detect the inflection point up to which the gas produced is only the solution gas using an automated trajectory detection procedure, imposing physics-based constraints (2), apply the material balance to calculate dynamic drainage volume, average reservoir pressure, and productivity index that are used to forecast well performance in the future. The proposed approach also handles changing artificial lift strategies and hence changing bottom hole pressure conditions, which is a practical consideration since most unconventional wells experience operational changes throughout their lifecycle. The automated trajectory detection procedure consistently captures the inflection point for all wells and is robust to scale for all well types. The history-matched multiphase flow model parameters are blind-tested to validate the model. The proposed technique extrapolates reservoir pressure depletion based on established trends to forecast GOR trends with reasonable accuracy at an extremely low computational cost. The proposed hybrid model overcomes (1) deficiencies of pure data-driven approaches, where changes in operating conditions are not properly represented and the forecasts are not physically consistent, (2) limitations of analytical models, where the assumptions are too many/strict to represent the real-life performance of a multifracture horizontal well, and (3) complexities of numerical simulation models, which are expensive, time-consuming and requires too many inputs for initialization. Additionally, the proposed hybrid model provides a robust and scalable method to identify future GOR trends to support the pace of operations and data-driven decision-making.
10
Kaneko, Tatsuya, Ryota Wada, Masahiko Ozaki, and Tomoya Inoue. "Combining Physics-Based and Data-Driven Models for Estimation of WOB During Ultra-Deep Ocean Drilling." In ASME 2018 37th International Conference on Ocean, Offshore and Arctic Engineering. American Society of Mechanical Engineers, 2018. http://dx.doi.org/10.1115/omae2018-78229.
Full textAbstract:
Offshore drilling with drill string over 10,000m long has many technical challenges. Among them, the challenge to control the weight on bit (WOB) between a certain range is inevitable for the integrity of drill pipes and the efficiency of the drilling operation. Since WOB cannot be monitored directly during drilling, the tension at the top of the drill string is used as an indicator of the WOB. However, WOB and the surface measured tension are known to show different features. The deviation among the two is due to the dynamic longitudinal behavior of the drill string, which becomes stronger as the drill string gets longer and more elastic. One feature of the difference is related to the occurrence of high-frequency oscillation. We have analyzed the longitudinal behavior of drill string with lumped-mass model and captured the descriptive behavior of such phenomena. However, such physics-based models are not sufficient for real-time operation. There are many unknown parameters that need to be tuned to fit the actual operating conditions. In addition, the huge and complex drilling system will have non-linear behavior, especially near the drilling annulus. These features will only be captured in the data obtained during operation. The proposed hybrid model is a combination of physics-based models and data-driven models. The basic idea is to utilize data-driven techniques to integrate the obtained data during operation into the physics-based model. There are many options on how far we integrate the data-driven techniques to the physics-based model. For example, we have been successful in estimating the WOB from the surface measured tension and the displacement of the drill string top with only recurrent neural networks (RNNs), provided we have enough data of WOB. Lack of WOB measurement cannot be avoided, so the amount of data needs to be increased by utilizing results from physics-based numerical models. The aim of the research is to find a good combination of the two models. In this paper, we will discuss several hybrid model configurations and its performance.
Reports on the topic "Hybrid physics-data driven models"
1
Dargazany, Roozbeh, Emad Poshtan, Hamid Mohammadi, William Mars, Mamoon Shaafaey, and Yang Chen. A Hybrid Physics-Based, Data-Driven Approach to Model Damage Accumulation in Corrosion of Polymeric Adhesives. Office of Scientific and Technical Information (OSTI), December 2023. http://dx.doi.org/10.2172/1961542.
Full text
2
Balasubramaniam, K. S., D. C. Norquist, T. Henry, and M. Kirk. Physics of Solar Flares and Development of Statistical and Data Driven Models. Fort Belvoir, VA: Defense Technical Information Center, September 2013. http://dx.doi.org/10.21236/ada591356.
Full text
3
Selvaraju, Ragul, Hari Shankar, and Hariharan Sankarasubramanian. Metamodel Generation for Frontal Crash Scenario of a Passenger Car. SAE International, September 2020. http://dx.doi.org/10.4271/2020-28-0504.
Full textAbstract:
A frontal impact scenario was simulated using a Finite Element Model of a Hybrid III 50th percentile male (LSTC, Livermore CA) along with seatbelt, steering system and driver airbags. The boundary conditions included acceleration pulse to the seat and the outputs including injury measures in terms of Head Injury Criterion (HIC), Normalized Neck Injury Criterion (NIJ) and Chest Severity Index (CSI) were extracted from the simulations. The kinematics of the Hybrid III were validated against the kinematics of post mortem human surrogates (PMHS) available in the literature. Using the validated setup, metamodels were generated by creating a design of varying different parameters and recording the responses for each design. First, the X and Z translation of dummy along the seat is provided as input for which there was no variation in the head injury criterion (HIC). Next, the input pulse to the seat is parameterized along with the seatbelt loading and the results are obtained respectively. The outputs, in terms of injury measures, are generated in the form of metamodels as a function of the parameters. The occupant model used for the frontal crash scenario in LS-Dyna is validated against the previously available crash experimental data. A total of 100 design points was generated with a varying combination of parameters. An increase in various injury measures was observed with an increase in the scale factor of the acceleration pulse. Also, it was found that chest severity index increased with an increase in the scale factor of the seat belt loading force.
4
Selvaraju, Ragul, Hari Shankar, and Hariharan Sankarasubramanian. Metamodel Generation for Frontal Crash Scenario of a Passenger Car. SAE International, September 2020. http://dx.doi.org/10.4271/2020-28-0504.
Full textAbstract:
A frontal impact scenario was simulated using a Finite Element Model of a Hybrid III 50th percentile male (LSTC, Livermore CA) along with seatbelt, steering system and driver airbags. The boundary conditions included acceleration pulse to the seat and the outputs including injury measures in terms of Head Injury Criterion (HIC), Normalized Neck Injury Criterion (NIJ) and Chest Severity Index (CSI) were extracted from the simulations. The kinematics of the Hybrid III were validated against the kinematics of post mortem human surrogates (PMHS) available in the literature. Using the validated setup, metamodels were generated by creating a design of varying different parameters and recording the responses for each design. First, the X and Z translation of dummy along the seat is provided as input for which there was no variation in the head injury criterion (HIC). Next, the input pulse to the seat is parameterized along with the seatbelt loading and the results are obtained respectively. The outputs, in terms of injury measures, are generated in the form of metamodels as a function of the parameters. The occupant model used for the frontal crash scenario in LS-Dyna is validated against the previously available crash experimental data. A total of 100 design points was generated with a varying combination of parameters. An increase in various injury measures was observed with an increase in the scale factor of the acceleration pulse. Also, it was found that chest severity index increased with an increase in the scale factor of the seat belt loading force.
5
Pettit, Chris, and D. Wilson. A physics-informed neural network for sound propagation in the atmospheric boundary layer. Engineer Research and Development Center (U.S.), June 2021. http://dx.doi.org/10.21079/11681/41034.
Full textAbstract:
We describe what we believe is the first effort to develop a physics-informed neural network (PINN) to predict sound propagation through the atmospheric boundary layer. PINN is a recent innovation in the application of deep learning to simulate physics. The motivation is to combine the strengths of data-driven models and physics models, thereby producing a regularized surrogate model using less data than a purely data-driven model. In a PINN, the data-driven loss function is augmented with penalty terms for deviations from the underlying physics, e.g., a governing equation or a boundary condition. Training data are obtained from Crank-Nicholson solutions of the parabolic equation with homogeneous ground impedance and Monin-Obukhov similarity theory for the effective sound speed in the moving atmosphere. Training data are random samples from an ensemble of solutions for combinations of parameters governing the impedance and the effective sound speed. PINN output is processed to produce realizations of transmission loss that look much like the Crank-Nicholson solutions. We describe the framework for implementing PINN for outdoor sound, and we outline practical matters related to network architecture, the size of the training set, the physics-informed loss function, and challenge of managing the spatial complexity of the complex pressure.
6
Seale, Maria, Natàlia Garcia-Reyero, R. Salter, and Alicia Ruvinsky. An epigenetic modeling approach for adaptive prognostics of engineered systems. Engineer Research and Development Center (U.S.), July 2021. http://dx.doi.org/10.21079/11681/41282.
Full textAbstract:
Prognostics and health management (PHM) frameworks are widely used in engineered systems, such as manufacturing equipment, aircraft, and vehicles, to improve reliability, maintainability, and safety. Prognostic information for impending failures and remaining useful life is essential to inform decision-making by enabling cost versus risk estimates of maintenance actions. These estimates are generally provided by physics-based or data-driven models developed on historical information. Although current models provide some predictive capabilities, the ability to represent individualized dynamic factors that affect system health is limited. To address these shortcomings, we examine the biological phenomenon of epigenetics. Epigenetics provides insight into how environmental factors affect genetic expression in an organism, providing system health information that can be useful for predictions of future state. The means by which environmental factors influence epigenetic modifications leading to observable traits can be correlated to circumstances affecting system health. In this paper, we investigate the general parallels between the biological effects of epigenetic changes on cellular DNA to the influences leading to either system degradation and compromise, or improved system health. We also review a variety of epigenetic computational models and concepts, and present a general modeling framework to support adaptive system prognostics.
7
Seale, Maria, R. Salter, Natàlia Garcia-Reyero,, and Alicia Ruvinsky. A fuzzy epigenetic model for representing degradation in engineered systems. Engineer Research and Development Center (U.S.), September 2022. http://dx.doi.org/10.21079/11681/45582.
Full textAbstract:
Degradation processes are implicated in a large number of system failures, and are crucial to understanding issues related to reliability and safety. Systems typically degrade in response to stressors, such as physical or chemical environmental conditions, which can vary widely for identical units that are deployed in different places or for different uses. This situational variance makes it difficult to develop accurate physics-based or data-driven models to assess and predict the system health status of individual components. To address this issue, we propose a fuzzy set model for representing degradation in engineered systems that is based on a bioinspired concept from the field of epigenetics. Epigenetics is concerned with the regulation of gene expression resulting from environmental or other factors, such as toxicants or diet. One of the most studied epigenetic processes is methylation, which involves the attachment of methyl groups to genomic regulatory regions. Methylation of specific genes has been implicated in numerous chronic diseases, so provides an excellent analog to system degradation. We present a fuzzy set model for characterizing system degradation as a methylation process based on a set-theoretic representation for epigenetic modeling of engineered systems. This model allows us to capture the individual dynamic relationships among a system, environmental factors, and state of health.
8
Ruvinsky, Alicia, Maria Seale, R. Salter, and Natàlia Garcia-Reyero. An ontology for an epigenetics approach to prognostics and health management. Engineer Research and Development Center (U.S.), March 2023. http://dx.doi.org/10.21079/11681/46632.
Full textAbstract:
Techniques in prognostics and health management have advanced considerably in the last few decades, enabled by breakthroughs in computational methods and supporting technologies. These predictive models, whether data-driven or physics-based, target the modeling of a system’s aggregate performance. As such, they generalize assumptions about the modelled system’s components, and are thus limited in their ability to represent individual components and the dynamic environmental factors that affect composite system health. To address this deficiency, we have developed an epigenetics-inspired knowledge representation for engineered system state that encompasses components and environmental factors. Epigenetics is concerned with explaining how environmental factors affect the expression of an organism’s genetic material. The field has derived important in-sights into the development and progression of disease states based on how environmental factors impact genetic material, causing variations in how a gene is expressed. The health of an engineered system is similarly influenced by its environment. A foundation for a new approach to prognostics based on epigenetics must begin by representing the entities and relationships of an engineered system from the perspective of epigenetics. This paper presents an ontology for an epigenetics-inspired representation of an engineered system. An ontology describing the epigenetics of an engineered system will enable the composition of a formal model and the incremental development of a more robust, causal reasoning system.