Relevant bibliographies by topics / Thermodynamics-based Neural Networks

Academic literature on the topic 'Thermodynamics-based Neural Networks'

Author: Grafiati
Published: 10 December 2022
Last updated: 28 January 2023

Create a spot-on reference in APA, MLA, Chicago, Harvard, and other styles

Select a source type:

Contents

Consult the lists of relevant articles, books, theses, conference reports, and other scholarly sources on the topic 'Thermodynamics-based Neural Networks.'

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 "Thermodynamics-based Neural Networks"

1

Masi, Filippo, Ioannis Stefanou, Paolo Vannucci, and Victor Maffi-Berthier. "Thermodynamics-based Artificial Neural Networks for constitutive modeling." Journal of the Mechanics and Physics of Solids 147 (February 2021): 104277. http://dx.doi.org/10.1016/j.jmps.2020.104277.

Full text
APA, Harvard, Vancouver, ISO, and other styles
2

Masi, Filippo, and Ioannis Stefanou. "Multiscale modeling of inelastic materials with Thermodynamics-based Artificial Neural Networks (TANN)." Computer Methods in Applied Mechanics and Engineering 398 (August 2022): 115190. http://dx.doi.org/10.1016/j.cma.2022.115190.

Full text
APA, Harvard, Vancouver, ISO, and other styles
3

Huang, Shenglin, Zequn He, Bryan Chem, and Celia Reina. "Variational Onsager Neural Networks (VONNs): A thermodynamics-based variational learning strategy for non-equilibrium PDEs." Journal of the Mechanics and Physics of Solids 163 (June 2022): 104856. http://dx.doi.org/10.1016/j.jmps.2022.104856.

Full text
APA, Harvard, Vancouver, ISO, and other styles
4

Zhao, Liang, Chunyang Mo, Tingting Sun, and Wei Huang. "Aero Engine Gas-Path Fault Diagnose Based on Multimodal Deep Neural Networks." Wireless Communications and Mobile Computing 2020 (October 3, 2020): 1–10. http://dx.doi.org/10.1155/2020/8891595.

Full text
Abstract:
Aeroengine, served by gas turbine, is a highly sophisticated system. It is a hard task to analyze the location and cause of gas-path faults by computational-fluid-dynamics software or thermodynamic functions. Thus, artificial intelligence technologies rather than traditional thermodynamics methods are widely used to tackle this problem. Among them, methods based on neural networks, such as CNN and BPNN, cannot only obtain high classification accuracy but also favorably adapt to aeroengine data of various specifications. CNN has superior ability to extract and learn the attributes hiding in properties, whereas BPNN can keep eyesight on fitting the real distribution of original sample data. Inspired by them, this paper proposes a multimodal method that integrates the classification ability of these two excellent models, so that complementary information can be identified to improve the accuracy of diagnosis results. Experiments on several UCR time series datasets and aeroengine fault datasets show that the proposed model has more promising and robust performance compared to the typical and the state-of-the-art methods.
APA, Harvard, Vancouver, ISO, and other styles
5

Morán-Durán, Andrés, Albino Martínez-Sibaja, José Pastor Rodríguez-Jarquin, Rubén Posada-Gómez, and Oscar Sandoval González. "PEM Fuel Cell Voltage Neural Control Based on Hydrogen Pressure Regulation." Processes 7, no. 7 (July 10, 2019): 434. http://dx.doi.org/10.3390/pr7070434.

Full text
Abstract:
Fuel cells are promising devices to transform chemical energy into electricity; their behavior is described by principles of electrochemistry and thermodynamics, which are often difficult to model mathematically. One alternative to overcome this issue is the use of modeling methods based on artificial intelligence techniques. In this paper is proposed a hybrid scheme to model and control fuel cell systems using neural networks. Several feature selection algorithms were tested for dimensionality reduction, aiming to eliminate non-significant variables with respect to the control objective. Principal component analysis (PCA) obtained better results than other algorithms. Based on these variables, an inverse neural network model was developed to emulate and control the fuel cell output voltage under transient conditions. The results showed that fuel cell performance does not only depend on the supply of the reactants. A single neuro-proportional–integral–derivative (neuro-PID) controller is not able to stabilize the output voltage without the support of an inverse model control that includes the impact of the other variables on the fuel cell performance. This practical data-driven approach is reliably able to reduce the cost of the control system by the elimination of non-significant measures.
APA, Harvard, Vancouver, ISO, and other styles
6

Mahmoud, Saida Saad Mohamed, Gennaro Esposito, Giuseppe Serra, and Federico Fogolari. "Generalized Born radii computation using linear models and neural networks." Bioinformatics 36, no. 6 (November 6, 2019): 1757–64. http://dx.doi.org/10.1093/bioinformatics/btz818.

Full text
Abstract:
Abstract Motivation Implicit solvent models play an important role in describing the thermodynamics and the dynamics of biomolecular systems. Key to an efficient use of these models is the computation of generalized Born (GB) radii, which is accomplished by algorithms based on the electrostatics of inhomogeneous dielectric media. The speed and accuracy of such computations are still an issue especially for their intensive use in classical molecular dynamics. Here, we propose an alternative approach that encodes the physics of the phenomena and the chemical structure of the molecules in model parameters which are learned from examples. Results GB radii have been computed using (i) a linear model and (ii) a neural network. The input is the element, the histogram of counts of neighbouring atoms, divided by atom element, within 16 Å. Linear models are ca. 8 times faster than the most widely used reference method and the accuracy is higher with correlation coefficient with the inverse of ‘perfect’ GB radii of 0.94 versus 0.80 of the reference method. Neural networks further improve the accuracy of the predictions with correlation coefficient with ‘perfect’ GB radii of 0.97 and ca. 20% smaller root mean square error. Availability and implementation We provide a C program implementing the computation using the linear model, including the coefficients appropriate for the set of Bondi radii, as Supplementary Material. We also provide a Python implementation of the neural network model with parameter and example files in the Supplementary Material as well. Supplementary information Supplementary data are available at Bioinformatics online.
APA, Harvard, Vancouver, ISO, and other styles
7

Zhang, Yi, Junfu Fan, Mengzhen Zhang, Zongwen Shi, Rufei Liu, and Bing Guo. "A Recurrent Adaptive Network: Balanced Learning for Road Crack Segmentation with High-Resolution Images." Remote Sensing 14, no. 14 (July 7, 2022): 3275. http://dx.doi.org/10.3390/rs14143275.

Full text
Abstract:
Road crack segmentation based on high-resolution images is an important task in road service maintenance. The undamaged road surface area is much larger than the damaged area on a highway. This imbalanced situation yields poor road crack segmentation performance for convolutional neural networks. In this paper, we first evaluate the mainstream convolutional neural network structure in the road crack segmentation task. Second, inspired by the second law of thermodynamics, an improved method called a recurrent adaptive network for a pixelwise road crack segmentation task is proposed to solve the extreme imbalance between positive and negative samples. We achieved a flow between precision and recall, similar to the conduction of temperature repetition. During the training process, the recurrent adaptive network (1) dynamically evaluates the degree of imbalance, (2) determines the positive and negative sampling rates, and (3) adjusts the loss weights of positive and negative features. By following these steps, we established a channel between precision and recall and kept them balanced as they flow to each other. A dataset of high-resolution road crack images with annotations (named HRRC) was built from a real road inspection scene. The images in HRRC were collected on a mobile vehicle measurement platform by high-resolution industrial cameras and were carefully labeled at the pixel level. Therefore, this dataset has sufficient data complexity to objectively evaluate the real performance of convolutional neural networks in highway patrol scenes. Our main contribution is a new method of solving the data imbalance problem, and the method of guiding model training by analyzing precision and recall is experimentally demonstrated to be effective. The recurrent adaptive network achieves state-of-the-art performance on this dataset.
APA, Harvard, Vancouver, ISO, and other styles
8

Lam, Stephen, Yu Shi, and Thomas Beck. "Modeling Solvation Thermodynamics in Molten Salts with Quasichemical Theory and Ab Initio-Accurate Deep Learning-Accelerated Simulations." ECS Meeting Abstracts MA2022-01, no. 46 (July 7, 2022): 1956. http://dx.doi.org/10.1149/ma2022-01461956mtgabs.

Full text
Abstract:
Molten salts are a promising class of ionic liquids used in advanced energy applications including next-generation nuclear reactors, batteries, and solar thermal energy storage. In these applications, understanding corrosion processes and predicting phase behavior remains a critical challenge. This requires accurate prediction of the solvation thermodynamics of ionic species in a variety of chemical and configurational states. In this work, we fundamentally address these challenges by combining quasichemical theory (QCT), ab initio simulation with density functional theory (DFT), and neural network interatomic potentials (NNIP) to accurately predict the solvation free energy of solute ions in molten salt. Ab initio data is used to train neural networks that learn the environment-dependent atomic forces and energies. This enables acceleration of atomistic simulation by more than three orders of magnitude. Using chemically accurate and highly efficient neural network-based molecular simulations, we perform free energy calculations within the QCT framework. Namely, QCT provides an exact partitioning of the free energy that includes contributions from 1) formation of a cavity in solution, 2) insertion of a solute ion into the cavity, and 3) relaxation of the cavity surrounding the solute ion. This requires simulations in timescales totaling tens of nanoseconds. As such, using AIMD alone is impractical for exploring a wide range of solutes, compositions, and thermodynamic conditions. In this work, we show that the NNIPs can accurately predict molten salt thermodynamics and local coordination structures. We provide a demonstration of the combined methods (DFT-NNIP-QCT) on molten NaCl, in which we obtain the total excess potentials of Na+ and Cl- ions, and perform corrections to errors in electrostatic energy caused by finite size of the simulation cell. The calculated excess chemical potential for Na+/Cl− was predicted to be -161.7±10.6 kcal/mol, which is consistent with previous calculations and an experimental value of -163.5 kcal/mol from thermochemical tables. These results provide initial validation of the methods for predicting excess chemical potentials, which can be directly exploited for the determination of solute chemistry, and the solubility of dissolved gases and metallic ions in molten salts. This provides motivation for the use of these methods to understanding solute chemistry in a wide range of molten salt systems in advanced energy applications.
APA, Harvard, Vancouver, ISO, and other styles
9

Njegovanović, Ana. "Mind Theory and the Role of Financial Decision and Process Role of Optogenetics." Financial Markets, Institutions and Risks 4, no. 1 (2020): 40–50. http://dx.doi.org/10.21272/fmir.4(1).40-50.2020.

Full text
Abstract:
This paper is devoted to the study of functional relationships between behavioral finance, in particular when making decisions in the financial market, and the theory of reason and optogenetics. The purpose of this paper is to analyze the interaction of financial decision-making processes with the key principles of the mental state model (theory of mind) and define the role of optogenetics. The author notes that the use of the theory of reason in behavioral finance allows us to consider the key characteristics of the mental state of the subject of economic relations (thoughts, perceptions, desires, intentions, feelings have an internal mentalistic and experimental content). The author notes that decision-making at any level characterizes the complex network of scientific industries that allow us to understand the complexity of financial decision-making and the role and significance of the laws of thermodynamics and entropy. Modeling neural networks (based on the experimental approach), the paper presents the results of research in the context of analyzing behavioral changes in our brain under the following scenarios: at the stage of awareness of certain processes; if we participate (or do not) participate in these processes. The following conclusions are made in the paper: for the normal states of anxiety, the greatest number of possible configurations of interactions between brain networks, which represent the highest values of entropy is characteristic. These results are obtained from the study of a small number of participants in the experiment, but give an objective assessment and understanding of the complexity of the research and the guidance that include a scientific basis in the process of solving problems in the financial sphere (as an example: when trading in the financial market). Keywords: behavioral finance; theory of mind, financial decision making, optogenetics.
APA, Harvard, Vancouver, ISO, and other styles
10

Gorkowski, Kyle, Thomas C. Preston, and Andreas Zuend. "Relative-humidity-dependent organic aerosol thermodynamics via an efficient reduced-complexity model." Atmospheric Chemistry and Physics 19, no. 21 (October 30, 2019): 13383–407. http://dx.doi.org/10.5194/acp-19-13383-2019.

Full text
Abstract:
Abstract. Water plays an essential role in aerosol chemistry, gas–particle partitioning, and particle viscosity, but it is typically omitted in thermodynamic models describing the mixing within organic aerosol phases and the partitioning of semivolatile organics. In this study, we introduce the Binary Activity Thermodynamics (BAT) model, a water-sensitive reduced-complexity model treating the nonideal mixing of water and organics. The BAT model can process different levels of physicochemical mixture information enabling its application in the thermodynamic aerosol treatment within chemical transport models, the evaluation of humidity effects in environmental chamber studies, and the analysis of field observations. It is capable of using organic structure information including O:C, H:C, molar mass, and vapor pressure, which can be derived from identified compounds or estimated from bulk aerosol properties. A key feature of the BAT model is predicting the extent of liquid–liquid phase separation occurring within aqueous mixtures containing hydrophobic organics. This is crucial to simulating the abrupt change in water uptake behavior of moderately hygroscopic organics at high relative humidity, which is essential for capturing the correct behavior of organic aerosols serving as cloud condensation nuclei. For gas–particle partitioning predictions, we complement a volatility basis set (VBS) approach with the BAT model to account for nonideality and liquid–liquid equilibrium effects. To improve the computational efficiency of this approach, we trained two neural networks; the first for the prediction of aerosol water content at given relative humidity, and the second for the partitioning of semivolatile components. The integrated VBS + BAT model is benchmarked against high-fidelity molecular-level gas–particle equilibrium calculations based on the AIOMFAC (Aerosol Inorganic-Organic Mixtures Functional groups Activity Coefficient) model. Organic aerosol systems derived from α-pinene or isoprene oxidation are used for comparison. Predicted organic mass concentrations agree within less than a 5 % error in the isoprene case, which is a significant improvement over a traditional VBS implementation. In the case of the α-pinene system, the error is less than 2 % up to a relative humidity of 94 %, with larger errors past that point. The goal of the BAT model is to represent the bulk O:C and molar mass dependencies of a wide range of water–organic mixtures to a reasonable degree of accuracy. In this context, we discuss that the reduced-complexity effort may be poor at representing a specific binary water–organic mixture perfectly. However, the averaging effects of our reduced-complexity model become more representative when the mixture diversity increases in terms of organic functionality and number of components.
APA, Harvard, Vancouver, ISO, and other styles
More sources

Book chapters on the topic "Thermodynamics-based Neural Networks"

1

Masi, Filippo, Ioannis Stefanou, Paolo Vannucci, and Victor Maffi-Berthier. "Material Modeling via Thermodynamics-Based Artificial Neural Networks." In Springer Proceedings in Mathematics & Statistics, 308–29. Cham: Springer International Publishing, 2021. http://dx.doi.org/10.1007/978-3-030-77957-3_16.

Full text
APA, Harvard, Vancouver, ISO, and other styles
2

Machado Cavalcanti, Fabio, Camila Emilia Kozonoe, Kelvin André Pacheco, and Rita Maria de Brito Alves. "Application of Artificial Neural Networks to Chemical and Process Engineering." In Deep Learning Applications. IntechOpen, 2021. http://dx.doi.org/10.5772/intechopen.96641.

Full text
Abstract:
The accelerated use of Artificial Neural Networks (ANNs) in Chemical and Process Engineering has drawn the attention of scientific and industrial communities, mainly due to the Big Data boom related to the analysis and interpretation of large data volumes required by Industry 4.0. ANNs are well-known nonlinear regression algorithms in the Machine Learning field for classification and prediction and are based on the human brain behavior, which learns tasks from experience through interconnected neurons. This empirical method can widely replace traditional complex phenomenological models based on nonlinear conservation equations, leading to a smaller computational effort – a very peculiar feature for its use in process optimization and control. Thereby, this chapter aims to exhibit several ANN modeling applications to different Chemical and Process Engineering areas, such as thermodynamics, kinetics and catalysis, process analysis and optimization, process safety and control, among others. This review study shows the increasing use of ANNs in the area, helping to understand and to explore process data aspects for future research.
APA, Harvard, Vancouver, ISO, and other styles
3

Sutherland, Clint, Abeni Marcano, and Beverly Chittoo. "Artificial Neural Network-Genetic Algorithm Prediction of Heavy Metal Removal Using a Novel Plant-Based Biosorbent Banana Floret: Kinetic, Equilibrium, Thermodynamics and Desorption Studies." In Desalination and Water Treatment. InTech, 2018. http://dx.doi.org/10.5772/intechopen.74398.

Full text
APA, Harvard, Vancouver, ISO, and other styles

Conference papers on the topic "Thermodynamics-based Neural Networks"

1

Müller, S. "Thermodynamics Based Artificial Neural Networks Based Homogenization of Composite Materials." In VIII Conference on Mechanical Response of Composites. CIMNE, 2021. http://dx.doi.org/10.23967/composites.2021.117.

Full text
APA, Harvard, Vancouver, ISO, and other styles
2

Zhu, Qilun, Robert Prucka, Shu Wang, Michael Prucka, and Hussein Dourra. "Control Oriented Modelling of Engine IMEP Variation." In ASME 2016 Internal Combustion Engine Division Fall Technical Conference. American Society of Mechanical Engineers, 2016. http://dx.doi.org/10.1115/icef2016-9342.

Full text
Abstract:
Engine cycle-by-cycle combustion variation is a potential source of emissions and drivability issues in automobiles, and has become an important concern for engine control engineers. The nature of turbulent combustion in IC engines means that combustion variations cannot be eliminated completely. Furthermore, it is inevitable for the engine to run at conditions with high combustion variations in most vehicle applications. For example, during gear shifts spark timing can be changed dramatically to help track the fast transitions of torque demand, often resulting in high Coefficient of Variation in Indicated Mean Effective Pressure (COV of IMEP). Under these circumstances, the control engineers have to weigh between combustion variation and other performance demands (i.e. fast torque tracking). An accurate online estimation of COV of IMEP can be beneficial to this process. A calibrated map of COV of IMEP versus engine operating conditions can be an option for engines with few control actuators. As the number of control actuators increases, combustion variation modelling using inputs with physical representations becomes favorable due to the potential for reduced calibration effort. However, since COV of IMEP is a stochastic variable describing the distribution of IMEP output, it can only be modelled empirically. This research proposes a control-oriented real-time COV of IMEP model based on an Artificial Neural Network (ANN) and inputs from turbulent combustion research. The effects of premixed turbulent combustion variation are analyzed with flame regime analysis in this research after a brief introduction of the experimental setup and engine information. In-cylinder thermodynamics are then evaluated to reveal how the changes of heat release transform into the variation of cylinder pressure, producing COV of IMEP. A range of model input parameters are assessed to determine the set that produces the most accurate prediction of IMEP variation with minimal computational requirements. An Artificial Neural Network (ANN) is applied to capture the nonlinear coupled correlations between COV of IMEP and model inputs. The ANN is combined with a regression pretreatment to reduce network size and improve extrapolation stability. This computationally efficient single-layer three-neuron ANN COV of IMEP model achieved 0.29% normalized Root Mean Square Error (RMSE). Dynamometer tests show that the model performs well outside the training region.
APA, Harvard, Vancouver, ISO, and other styles
3

Emami, Mostafa, Mohammad H. Rahimian, and Saeed Alem Varzane Esfehani. "Second Law Analysis of Fully Developed Convection in a Helical Coiled Tube Under Constant Wall Temperature Using a CFD-ANN Approach." In ASME 2010 10th Biennial Conference on Engineering Systems Design and Analysis. ASMEDC, 2010. http://dx.doi.org/10.1115/esda2010-24402.

Full text
Abstract:
The present paper analyses the second law of thermodynamics in a fully developed forced convection in the horizontal helical coiled tube under constant wall temperature. The influence of non-dimensional parameters such as Reynolds number (Re), coil-to-tube ratio (δ) and coil pitch (λ) are inspected on the entropy generation. According to the literature, the coil pitch has a minor effect on the entropy generation compared with Re and δ. Using a CFD tool is a common classical method to find the optimal Reynolds Number and coil-to-tube ratio (δ) based on the entropy generation minimization principal. This approach requires lots of time and resources while the innovative implementation of an Artificial Neural Network (ANN) reduces the simulation time considerably. The data pool generated by the CFD tool is used to train the ANN. As less data is needed to train the ANN in comparison to classical CFD based method, the performance of ANN-CFD optimization approach enhances. As entropy generation minimization principal is applied during the optimization, Nusselt number and friction factor are required to evaluate the entropy generation; these parameters are obtained through a numerical simulation and then are used to train the ANN. The ANN can predict these parameters as a function of different Re numbers and coil-to-tube ratios during optimization. Several different architectures of ANNs were evaluated and parametric studies were performed to optimize network design for the best prediction of the variables. The results obtained from the ANN are compared with the available experimental data to show the network reasonable accuracy.
APA, Harvard, Vancouver, ISO, and other styles
You might also be interested in the extended bibliographies on the topic 'Thermodynamics-based Neural Networks' for particular source types:
Journal articles
We offer discounts on all premium plans for authors whose works are included in thematic literature selections. Contact us to get a unique promo code!

To the bibliography