Academic literature on the topic 'Conditional-based monitoring'
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 'Conditional-based monitoring.'
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 "Conditional-based monitoring"
1
Sutan, Anwar, and Jason Laidlaw. "Conditional Based Monitoring of an Three Column Gas Chromatograph." Measurement and Control 45, no. 7 (September 2012): 215–21. http://dx.doi.org/10.1177/002029401204500704.
Full text
2
Rao, Jingzhi, Cheng Ji, Jiatao Wen, Jingde Wang, and Wei Sun. "Nonstationary Process Monitoring Based on Alternating Conditional Expectation and Cointegration Analysis." Processes 10, no. 10 (October 4, 2022): 2003. http://dx.doi.org/10.3390/pr10102003.
Full textAbstract:
Traditional multivariate statistical methods, which are often used to monitor stationary processes, are not applicable to nonstationary processes. Cointegration analysis (CA) is considered an effective method to deal with nonstationary variables. If there is a cointegration relationship among the nonstationary series in the system, it indicates that a stable long-term dynamic equilibrium relationship exists among these variables. However, due to the complexity of modern industrial processes, there are nonlinear relations between variables, which are not considered by the traditional linear cointegration theory. Alternating conditional expectation (ACE) can perform nonlinear transformation on these variables to maximize the linear correlation of the transformed variables. It will be helpful to deal with the nonlinear relations by modeling with transformed variables. In this work, a new monitoring strategy based on ACE and CA is proposed. The data are first transformed by an ACE algorithm, CA is performed after that, and then monitoring statistics are calculated to determine whether the system is faulty. The strategy is applied to the monitoring of a simulation case and a catalytic reforming unit in a petrochemical company. The results show that the strategy can realize the monitoring of nonstationary process, with a higher fault detection rate and a lower false alarm rate compared with the monitoring strategy based on traditional cointegration theory.
3
Shi, Binbin, Rongli Fan, Lijuan Zhang, Jie Huang, Neal Xiong, Athanasios Vasilakos, Jian Wan, and Lei Zhang. "A Joint Extraction System Based on Conditional Layer Normalization for Health Monitoring." Sensors 23, no. 10 (May 16, 2023): 4812. http://dx.doi.org/10.3390/s23104812.
Full textAbstract:
Natural language processing (NLP) technology has played a pivotal role in health monitoring as an important artificial intelligence method. As a key technology in NLP, relation triplet extraction is closely related to the performance of health monitoring. In this paper, a novel model is proposed for joint extraction of entities and relations, combining conditional layer normalization with the talking-head attention mechanism to strengthen the interaction between entity recognition and relation extraction. In addition, the proposed model utilizes position information to enhance the extraction accuracy of overlapping triplets. Experiments on the Baidu2019 and CHIP2020 datasets demonstrate that the proposed model can effectively extract overlapping triplets, which leads to significant performance improvements compared with baselines.
4
Lee, Jin Oh, Min Soo Kang, Jeong Hun Shin, and Kil Sung Lee. "The Effect of Interactive Pedometer with New Algorithm on 10,000 Step Goal Attainments." Key Engineering Materials 345-346 (August 2007): 873–76. http://dx.doi.org/10.4028/www.scientific.net/kem.345-346.873.
Full textAbstract:
The pedometer, an objective assessment of measuring step counts, has often been used to motivate individuals to increase their ambulatory physical activity. Minimal contact pedometer-based intervention (MCPBI) is gaining in popularity because they are simple and inexpensive. MCPBI is based on self-monitoring by the participants; however, one limitation of using the self-monitoring approach was the participant attrition (i.e., dropout), which makes it difficult to achieve the successful intervention. A new algorithm for pedometer-based intervention, the systematic-monitoring based on conditional feedback, was designed to increase awareness and allow participants to more successfully attain their step goals. Thus, the purpose of this study was to examine the effect of the systematic-monitoring based on conditional feedback algorithm on 10,000 step goal attainments. The study result can be used to design more comprehensive pedometer-based physical activity interventions to increase individuals’ overall health status.
5
Parikh, Pranav J., and Marco Santello. "Role of human premotor dorsal region in learning a conditional visuomotor task." Journal of Neurophysiology 117, no. 1 (January 1, 2017): 445–56. http://dx.doi.org/10.1152/jn.00658.2016.
Full textAbstract:
Conditional learning is an important component of our everyday activities (e.g., handling a phone or sorting work files) and requires identification of the arbitrary stimulus, accurate selection of the motor response, monitoring of the response, and storing in memory of the stimulus-response association for future recall. Learning this type of conditional visuomotor task appears to engage the premotor dorsal region (PMd). However, the extent to which PMd might be involved in specific or all processes of conditional learning is not well understood. Using transcranial magnetic stimulation (TMS), we demonstrate the role of human PMd in specific stages of learning of a novel conditional visuomotor task that required subjects to identify object center of mass using a color cue and to apply appropriate torque on the object at lift onset to minimize tilt. TMS over PMd, but not vertex, increased error in torque exerted on the object during the learning trials. Analyses of digit position and forces further revealed that the slowing in conditional visuomotor learning resulted from impaired monitoring of the object orientation during lift, rather than stimulus identification, thus compromising the ability to accurately reduce performance error across trials. Importantly, TMS over PMd did not alter production of torque based on the recall of learned color-torque associations. We conclude that the role of PMd for conditional learning is highly sensitive to the stage of learning visuomotor associations. NEW & NOTEWORTHY Conditional learning involves stimulus identification, motor response selection, response monitoring, memory encoding, and recall of the learned association. Premotor dorsal (PMd) has been implicated for conditional learning. However, the extent to which PMd might be involved in specific or all stages of conditional learning is not well understood. The novel finding of our study is that PMd appears to be involved with monitoring motor responses, a sensorimotor integration stage essential for conditional learning.
6
He, Hui, Zixuan Liu, Runhai Jiao, and Guangwei Yan. "A Novel Nonintrusive Load Monitoring Approach based on Linear-Chain Conditional Random Fields." Energies 12, no. 9 (May 11, 2019): 1797. http://dx.doi.org/10.3390/en12091797.
Full textAbstract:
In a real interactive service system, a smart meter can only read the total amount of energy consumption rather than analyze the internal load components for users. Nonintrusive load monitoring (NILM), as a vital part of smart power utilization techniques, can provide load disaggregation information, which can be further used for optimal energy use. In our paper, we introduce a new method called linear-chain conditional random fields (CRFs) for NILM and combine two promising features: current signals and real power measurements. The proposed method relaxes the independent assumption and avoids the label bias problem. Case studies on two open datasets showed that the proposed method can efficiently identify multistate appliances and detect appliances that are not easily identified by other models.
7
Wang, Guofeng, Xiaoliang Feng, and Chang Liu. "Bearing Fault Classification Based on Conditional Random Field." Shock and Vibration 20, no. 4 (2013): 591–600. http://dx.doi.org/10.1155/2013/943809.
Full textAbstract:
Condition monitoring of rolling element bearing is paramount for predicting the lifetime and performing effective maintenance of the mechanical equipment. To overcome the drawbacks of the hidden Markov model (HMM) and improve the diagnosis accuracy, conditional random field (CRF) model based classifier is proposed. In this model, the feature vectors sequences and the fault categories are linked by an undirected graphical model in which their relationship is represented by a global conditional probability distribution. In comparison with the HMM, the main advantage of the CRF model is that it can depict the temporal dynamic information between the observation sequences and state sequences without assuming the independence of the input feature vectors. Therefore, the interrelationship between the adjacent observation vectors can also be depicted and integrated into the model, which makes the classifier more robust and accurate than the HMM. To evaluate the effectiveness of the proposed method, four kinds of bearing vibration signals which correspond to normal, inner race pit, outer race pit and roller pit respectively are collected from the test rig. And the CRF and HMM models are built respectively to perform fault classification by taking the sub band energy features of wavelet packet decomposition (WPD) as the observation sequences. Moreover, K-fold cross validation method is adopted to improve the evaluation accuracy of the classifier. The analysis and comparison under different fold times show that the accuracy rate of classification using the CRF model is higher than the HMM. This method brings some new lights on the accurate classification of the bearing faults.
8
Sarfraz, Maryam, Najam ul Hassan, and Ateeba Atir. "COEFFICIENT OF VARIATION CONTROL CHART BASED ON CONDITIONAL EXPECTED VALUES FOR THE MONITORING OF CENSORED RAYLEIGH LIFETIMES." Pakistan Journal of Social Research 04, no. 03 (November 25, 2022): 1058–74. http://dx.doi.org/10.52567/pjsr.v4i03.1285.
Full textAbstract:
This article deals with the monitoring of type-I censored data using coefficient of variation (CV) control chart based on conditional expected values (CEVs) for Rayleigh lifetimes under type-I censoring. In particular, the censored data is replaced by the CEV to develop an efficient design structure. The main focus is to detect shifts in the mean of Rayleigh lifetimes assuming censored data. The performance of the proposed CEV based CV chart is evaluated by the average run length (ARL). Besides the simulation study, monitoring of a real-life dataset of 30 average daily wind speeds (in kilometers/hour) for the month of November 2007 at Elanora Heights is also discussed. Keywords: CEV, CV, type І censored, ARL, Average Run Length (ARL); Control Charts; Conditional Expected Values; type-I Censoring.
9
Zheng, Hongmei, and Xiaoli Qiao. "Reliability Analysis Method of Rotating Machinery Based on Conditional Random Field." Computational Intelligence and Neuroscience 2022 (October 3, 2022): 1–12. http://dx.doi.org/10.1155/2022/7326730.
Full textAbstract:
Rotating machinery is indispensable mechanical equipment in modern industrial production. However, rotating machinery is usually under heavy load. Due to the complexity of its structure and the severity of its working conditions, it is urgent to find effective condition monitoring methods and fault maintenance strategies for its safe and reliable operation. The conditional random field is derived from the maximum entropy model, which solves the problem of label bias and improves the convergence speed of model training. Combining Kriging theory and random field theory, this study proposes a three-dimensional conditional random field generation method based on failure time, applies this method to the comparison of measured data and other nonconditional random fields, and then analyzes the failure probability of rotating machinery in the failure process by combining the numerical calculation results and reliability theory. It is found that the conditional random field generation method can effectively describe the spatial variability of rotating machinery parameters. Compared with the nonconditional random field, the reliability index of rotating machinery failure time is improved by 0.8823, so the conditional random field can better describe the reliability of rotating machinery.
10
Yang, Yiping, Hongjian Zhu, and Dejian Lai. "Estimating Conditional Power for Sequential Monitoring of Covariate Adaptive Randomized Designs: The Fractional Brownian Motion Approach." Fractal and Fractional 5, no. 3 (September 8, 2021): 114. http://dx.doi.org/10.3390/fractalfract5030114.
Full textAbstract:
Conditional power based on classical Brownian motion (BM) has been widely used in sequential monitoring of clinical trials, including those with the covariate adaptive randomization design (CAR). Due to some uncontrollable factors, the sequential test statistics under CAR procedures may not satisfy the independent increment property of BM. We confirm the invalidation of BM when the error terms in the linear model with CAR design are not independent and identically distributed. To incorporate the possible correlation structure of the increment of the test statistic, we utilize the fractional Brownian motion (FBM). We conducted a comparative study of the conditional power under BM and FBM. It was found that the conditional power under FBM assumption was mostly higher than that under BM assumption when the Hurst exponent was greater than 0.5.
Dissertations / Theses on the topic "Conditional-based monitoring"
1
Tonelli, Daniel. "Management of Civil Infrastructure based on Structural Health Monitoring." Doctoral thesis, Università degli studi di Trento, 2020. http://hdl.handle.net/11572/272315.
Full textAbstract:
The interest in structural health monitoring (SHM) has grown considerably in the past half century, due to an explosive growth in the availability of new sensors, the development of powerful data analysis techniques, and the increasing number of civil infrastructure that are approaching or exceeding their initial design life. In SHM, we acquire observation on the behavior of a structure to understand its condition state, based on which we decide how to manage it properly. However, this optimistic view of SHM is in contrast with what happen in real life: infrastructure operators are typically skeptical about the capacity of monitoring to support decisions, and instead of following the suggestions provided by SHM, they often act based on their experience or common sense. The reason is that at present it is not fully clear how in practice to make decisions based on monitoring observation. To fill this gap between theory and practice, I propose to consider SHM as a logical process of making decision based on observation consisting of two steps: judgment, in which the condition state of structures is inferred based on SHM data, and decision, in which the optimal action is identified based on a rational and economic principle. From this perspective, a monitoring system should provide information that can improe he managers knoledge on he srcral condiion sae enough to allow them to make better decision on the structure management. Therefore, in designing a monitoring system, the design target must be the accuracy in the knowledge of structural state achieved analyzing the observations provided by it. However, when an engineer designs a monitoring system, the approach is often heuristic, with performance evaluation based on experience or common sense rather than on quantitative analysis. For this reason, I propose a performance-based monitoring system design, which is a quantitative method for the calculation of the expected performance of a monitoring solution a pre-posteriori and for checking it effectiveness in the design phase. It is based on the calculation of the monitoring capacity and the monitoring demand the counterparts of structural capacity and demand in the semi-probabilistic structural design, and like in structural design, the solution is satisfactory if the capacity is equal or better than the demand. The choice in whether to invest a limited budget on a monitoring system or in a retrofit is another critical choice for infrastructure managers: a retrofit work can increase the capacity and the safety of a structure, while sensors do not change the capacity, nor reduce the loads. Recently, the SHM-community has acknowledged that the benefit of installing a monitoring system can be properly quantified using the concept of Value of Information (VoI). A typical assumption in the VoI estimation is that a single decision-maker is in charge for decisions on both the investment in SHM for a structure, and its management based on SHM data. However, this process is usually more complex in the real world, with more individuals involved in the decision chain. Therefore, I formalize a rational method for quantifying the conditional value of information when two different actors are involved in the decision chain: the manager, who operate the structure based on monitoring data; and the owner, who chooses whether to install the monitoring system or not, before having access to these data. The results are particularly interested, showing that under appropriate conditions, the owner may be willing to pay to prevent the manager to use the monitoring system. Application to case studies are presented for all the research contribution presented in this doctoral thesis.
2
Tonelli, Daniel. "Management of Civil Infrastructure based on Structural Health Monitoring." Doctoral thesis, Università degli studi di Trento, 2020. http://hdl.handle.net/11572/272315.
Full textAbstract:
The interest in structural health monitoring (SHM) has grown considerably in the past half century, due to an explosive growth in the availability of new sensors, the development of powerful data analysis techniques, and the increasing number of civil infrastructure that are approaching or exceeding their initial design life. In SHM, we acquire observation on the behavior of a structure to understand its condition state, based on which we decide how to manage it properly. However, this optimistic view of SHM is in contrast with what happen in real life: infrastructure operators are typically skeptical about the capacity of monitoring to support decisions, and instead of following the suggestions provided by SHM, they often act based on their experience or common sense. The reason is that at present it is not fully clear how in practice to make decisions based on monitoring observation. To fill this gap between theory and practice, I propose to consider SHM as a logical process of making decision based on observation consisting of two steps: judgment, in which the condition state of structures is inferred based on SHM data, and decision, in which the optimal action is identified based on a rational and economic principle. From this perspective, a monitoring system should provide information that can improe he managers knoledge on he srcral condiion sae enough to allow them to make better decision on the structure management. Therefore, in designing a monitoring system, the design target must be the accuracy in the knowledge of structural state achieved analyzing the observations provided by it. However, when an engineer designs a monitoring system, the approach is often heuristic, with performance evaluation based on experience or common sense rather than on quantitative analysis. For this reason, I propose a performance-based monitoring system design, which is a quantitative method for the calculation of the expected performance of a monitoring solution a pre-posteriori and for checking it effectiveness in the design phase. It is based on the calculation of the monitoring capacity and the monitoring demand the counterparts of structural capacity and demand in the semi-probabilistic structural design, and like in structural design, the solution is satisfactory if the capacity is equal or better than the demand. The choice in whether to invest a limited budget on a monitoring system or in a retrofit is another critical choice for infrastructure managers: a retrofit work can increase the capacity and the safety of a structure, while sensors do not change the capacity, nor reduce the loads. Recently, the SHM-community has acknowledged that the benefit of installing a monitoring system can be properly quantified using the concept of Value of Information (VoI). A typical assumption in the VoI estimation is that a single decision-maker is in charge for decisions on both the investment in SHM for a structure, and its management based on SHM data. However, this process is usually more complex in the real world, with more individuals involved in the decision chain. Therefore, I formalize a rational method for quantifying the conditional value of information when two different actors are involved in the decision chain: the manager, who operate the structure based on monitoring data; and the owner, who chooses whether to install the monitoring system or not, before having access to these data. The results are particularly interested, showing that under appropriate conditions, the owner may be willing to pay to prevent the manager to use the monitoring system. Application to case studies are presented for all the research contribution presented in this doctoral thesis.
3
Legha, Daniel. "Predictive maintenance and remote diagnosis for electro-mechanical drives of Very High Speed Trains." Electronic Thesis or Diss., La Rochelle, 2023. http://www.theses.fr/2023LAROS015.
Full textAbstract:
L'objectif principal de cette recherche est de mettre en œuvre des méthodes de diagnostic prédictif et à distance pour les systèmes d'accessibilité du train, qui sont entraînés par des moteurs à courant continu. Ces systèmes sont les suivants : Les portes intérieures, le gap filler, la porte d'accès des passagers et l'ascenseur. La recherche aborde de multiples équations de maintenance prédictive et de télédiagnostic, telles que : Test de la tension de la courroie, pour tous les types de portes intérieures. Le bon état de la butée d'ouverture de la porte, pour tous les types de portes intérieures. Signature du bon fonctionnement des portes intérieures, à l'aide des signaux enregistrés dans le Big Data, tels que le courant et la tension du moteur, la position de la porte, la vitesse, les capteurs de position, la durée des cycles et d'autres informations contextuelles enregistrées sur le sous-système. Signature du bon fonctionnement du Gap Filler, qui a les mêmes objectifs que la signature du bon fonctionnement des portes intérieures. En ce qui concerne l'aspect théorique, la recherche vise à identifier un ensemble de modes de défaillance sélectionnés sur la base des signaux suivants : Courant du moteur, tension du moteur, position du moteur, vitesse du moteur, capteurs de position et données contextuelles telles que la température, l'inclinaison... La recherche vise à étudier les signaux en régime transitoire et non transitoire, avec et sans capteurs de position dans certains cas, avec une ingénierie des caractéristiques basée sur le domaine temporel, le domaine fréquentiel et le temps-fréquence. En outre, la recherche aborde les techniques d'apprentissage automatique pour la classification des données et des défaillances. L'objectif principal est de travailler sur des techniques basées sur le signal, et si possible, des recherches supplémentaires seront effectuées en utilisant des techniques basées sur le modèleThe main objective of this research is to implement predictive and remote diagnosis solutions for the train’s accessibility systems, which are driven by direct current motors. And these systems are the Internal Doors, the Gap Filler, the Passengers’ Access Door, and the Lift. The research tackles multiple predictive maintenance and remote diagnosis equations, such as: Test of the belt tension, for all the types of Internal Doors. The good condition of the door open stopper, for all types of Internal Doors. Signature of proper operation of Internal Doors, using the Big Data recorded signals such as the motor current, motor voltage, door position, speed, position sensors, cycles’ timings, and other contextual information recorded on the subsystem. Signature of proper operation of Gap Filler, which has the same objectives as the signature of proper operation of Internal Doors...Regarding the academic side, the research aims to identify a set of selected failure modes based on the following signals: Motor current, Motor Voltage, Motor position, Motor speed, Position sensors, and contextual data such as the temperature, the cant/tilt... The research aims to study the signals intransient and non-transient regimes, with and without position sensors in some cases, with features engineering based on the time domain, the frequency domain, and time-frequency. Furthermore, the research tackles Machine Learning techniques for data/failure classification. The main objective is to work on signal-based techniques, and if possible, additional investigation will be done using model-based techniques
Book chapters on the topic "Conditional-based monitoring"
1
Liu, Li-ping, Jian-lan Zhong, and Yi-zhong Ma. "A Multivariate Synthetic Control Chart for Monitoring Covariance Matrix Based on Conditional Entropy." In The 19th International Conference on Industrial Engineering and Engineering Management, 99–107. Berlin, Heidelberg: Springer Berlin Heidelberg, 2013. http://dx.doi.org/10.1007/978-3-642-37270-4_10.
Full text
2
Mahanta, Prabal, and Saurabh Jain. "Determination of Manufacturing Unit Root-Cause Analysis Based on Conditional Monitoring Parameters Using In-Memory Paradigm and Data-Hub Rule Based Optimization Platform." In On the Move to Meaningful Internet Systems: OTM 2015 Workshops, 41–48. Cham: Springer International Publishing, 2015. http://dx.doi.org/10.1007/978-3-319-26138-6_6.
Full text
3
Junges, Sebastian, Hazem Torfah, and Sanjit A. Seshia. "Runtime Monitors for Markov Decision Processes." In Computer Aided Verification, 553–76. Cham: Springer International Publishing, 2021. http://dx.doi.org/10.1007/978-3-030-81688-9_26.
Full textAbstract:
AbstractWe investigate the problem of monitoring partially observable systems with nondeterministic and probabilistic dynamics. In such systems, every state may be associated with a risk, e.g., the probability of an imminent crash. During runtime, we obtain partial information about the system state in form of observations. The monitor uses this information to estimate the risk of the (unobservable) current system state. Our results are threefold. First, we show that extensions of state estimation approaches do not scale due the combination of nondeterminism and probabilities. While exploiting a geometric interpretation of the state estimates improves the practical runtime, this cannot prevent an exponential memory blowup. Second, we present a tractable algorithm based on model checking conditional reachability probabilities. Third, we provide prototypical implementations and manifest the applicability of our algorithms to a range of benchmarks. The results highlight the possibilities and boundaries of our novel algorithms.
4
Chiachío, J., M. Chiachío, S. Sankararaman, A. Saxena, and K. Goebel. "Prognostics Design for Structural Health Management." In Emerging Design Solutions in Structural Health Monitoring Systems, 234–73. IGI Global, 2015. http://dx.doi.org/10.4018/978-1-4666-8490-4.ch011.
Full textAbstract:
The chapter describes the application of prognostic techniques to the domain of structural health and demonstrates the efficacy of the methods using fatigue data from a graphite-epoxy composite coupon. Prognostics denotes the in-situ assessment of the health of a component and the repeated estimation of remaining life, conditional on anticipated future usage. The methods shown here use a physics-based modeling approach whereby the behavior of the damaged components is encapsulated via mathematical equations that describe the characteristics of the components as it experiences increasing degrees of degradation. Mathematical rigorous techniques are used to extrapolate the remaining life to a failure threshold. Additionally, mathematical tools are used to calculate the uncertainty associated with making predictions. The information stemming from the predictions can be used in an operational context for go/no go decisions, quantify risk of ability to complete a (set of) mission or operation, and when to schedule maintenance.
5
Agarwal, Ruchi, and Lev Virine. "Monte Carlo Project Risk Analysis." In Advances in IT Personnel and Project Management, 109–29. IGI Global, 2017. http://dx.doi.org/10.4018/978-1-5225-1790-0.ch005.
Full textAbstract:
Monte Carlo simulations of project schedules have become one of the foundations of quantitative project risk analysis. Monte Carlo method helps to determine the chance that project will be completed on time and on budget, expected project cost and finish time given risks and uncertainties, as well as identify critical risks and crucial tasks. There are a number of ways how Monte Carlo schedule risk analysis can be conducted. “Traditional” Monte Carlo schedule analysis is performed based on statistical distributions of task duration, cost and other input parameters. Event-based quantitative risk analysis incorporates risk events, which can affect project schedules. The chapter discusses a number of important concepts related to Monte Carlo simulations: statistical distribution, sampling process, convergence monitoring, sensitivity analysis, probabilistic and conditional branching and others.
6
Lai, Yuehua, Ran Li, Mingliang Liu, Zaoyang Wu, and Rongming Chen. "An End-To-End Fault Diagnosis Method for Emulsion Pump with Class-Imbalance." In Frontiers in Artificial Intelligence and Applications. IOS Press, 2023. http://dx.doi.org/10.3233/faia230883.
Full textAbstract:
The condition monitoring data of emulsion pump follow the long-tail distribution. The amount of monitoring data for the normal condition is very large, while the amount of monitoring data for different fault conditions is very small, the problem of class-imbalance is prominent. The traditional intelligent fault diagnosis methods are proposed under the assumption of class balance, which the fault diagnosis model has the shortcoming of insufficient generalization ability when dealing with the class-imbalance problem. Thus, an end-to-end fault diagnosis method for emulsion pump with class-imbalance is proposed. conditional variational autoencoder is used to extract features and learn the state data distribution of emulsion pump, and the loss value of training samples is adjusted based on focal loss to balance the influence of different types of data on the model. Moreover, the end-to-end fault diagnosis model can be obtained based on the decoder model. Finally, the effectiveness of the proposed method is verified by simulation experiment data of emulsion pump faults. Compared with other methods under different types of imbalanced rates, the results show that the fault of emulsion pump can be accurately identified under the condition of only a small amount of fault data by the proposed method and the corresponding recognition accuracy is better than other methods.
Conference papers on the topic "Conditional-based monitoring"
1
KAMARIOTIS, ANTONIOS, ELENI CHATZI, and DANIEL STRAUB. "QUANTIFYING THE VALUE OF VIBRATION-BASED STRUCTURAL HEALTH MONITORING CONSIDERING ENVIRONMENTAL VARIABILITY." In Structural Health Monitoring 2021. Destech Publications, Inc., 2022. http://dx.doi.org/10.12783/shm2021/36356.
Full textAbstract:
The value of structural health monitoring (SHM) can be quantified as the difference in expected total life-cycle costs between two different maintenance planning strategies, one representing the standard means to assessment, namely intermittent visual inspections, and the other based on availability of continuous SHM data. We show how to quantify the value of vibration-based SHM conditional on a damage history over the structural lifetime. We showcase the analysis through application on a numerical benchmark model of a two-span bridge system subjected to gradual deterioration and sudden damages in the middle elastic support over its life-cycle, simulating the case of scour. The effect of environmental variability is included in the analysis by means of a stochastic model for the dependence of the Young’s modulus on temperature (E-T). The numerical investigations provide insights related to the effect of the temperature variability, as well as the visual inspections’ quality, on the value of SHM.
2
Burger, Mernout, Alexey Pavlov, and Kristin Y. Pettersen. "Maritime surveillance and monitoring using autonomous vehicles with conditional integrator-based control." In OCEANS 2009-EUROPE (OCEANS). IEEE, 2009. http://dx.doi.org/10.1109/oceanse.2009.5278240.
Full text
3
POOLE, J., P. GARDNER, A. J. HUGHES, R. S. MILLS, T. A. DARDENO, N. DERVILIS, and K. WORDEN. "PHYSICS-INFORMED TRANSFER LEARNING IN PBSHM: A CASE STUDY ON EXPERIMENTAL HELICOPTER BLADES." In Structural Health Monitoring 2023. Destech Publications, Inc., 2023. http://dx.doi.org/10.12783/shm2023/36990.
Full textAbstract:
Data for training Structural Health Monitoring (SHM) systems are often expensive or infeasible to obtain. Population-based SHM, which considers data across a population of structures, presents a potential solution to this issue. However, as differences between structures can lead to differing training and testing distributions, conventional machine learning methods may not generalise between structures. To address this issue, transfer learning (TL) can be used to leverage information across related domains. An important consideration when applying TL is how to asses similarity to identify and extract shared information. In unsupervised TL, a major challenge is that previous data-based metrics are limited to quantifying marginal distribution similarity in the unsupervised setting. This paper proposes utilising the Modal Assurance Criterion (MAC) between modes of healthy structures as a measure of data similarity to identify features that minimise conditional distribution shift. The MAC is incorporated into a feature selection criterion and a TL methodology is proposed. Moreover, the proposed methodology is shown to facilitate label sharing within a heterogeneous population of helicopter blades
4
Colchado, Luis. "Interpolation and Prediction of PM2.5 based on Conditional Generative Adversarial Network and a forecasting model." In LatinX in AI at Neural Information Processing Systems Conference 2019. Journal of LatinX in AI Research, 2019. http://dx.doi.org/10.52591/lxai2019120828.
Full textAbstract:
Currently, air pollution is a severe problem, because pollutants such as Particulate matter of 2.5 micrometers affect human health. Therefore, several works address the prediction of this pollutant, using statistical methods and machine learning. However, these predictions are performed in places of a city, where air quality monitoring stations are available, which is not always possible due to their high implementation and maintenance costs. Thus, in this work, we propose an architecture based on a Conditional Generative Adversary Network to create new synthetic data and interpolate this pollutant in places where monitoring stations are missing.
5
ZENG, JICE, MICHAEL D. TODD, and HU ZHEN. "DEGRADATION MODEL UPDATING FOR FAILURE PROGNOSTICS USING A SEQUENTIAL LIKELIHOOD- FREE BAYESIAN INFERENCE METHOD AND VIDEO MONITORING DATA." In Structural Health Monitoring 2023. Destech Publications, Inc., 2023. http://dx.doi.org/10.12783/shm2023/36804.
Full textAbstract:
Structural systems are inevitably subject to degradation that evolves progressively over time. Developing a degradation model to capture the physics of damage evolution is essential for failure prognostics, i.e., remaining useful life (RUL) prediction, to enable individualized predictive maintenance. Due to the lack of runto- failure data for large structural systems and natural variability across physical systems, uncertainty is inherent in the degradation model even if a degradation model can be constructed based on the physics of a certain damage mechanism. It is therefore necessary to update the degradation model over time based on measurements of quantities that are directly measurable. With the development of sensing and image processing techniques, it is possible to derive structural strain response from videos, which overcomes the limitations of the cumbersome and costly deployment of conventional contact sensors. While the strain video monitoring data provide rich information for structural health monitoring, the usage of this information for degradation model updating is challenging due to the implicit connection between the degradation model parameters and strain video monitoring data and the highly complicated model architectures. This research proposes a novel sequential Bayesian model updating framework for a degradation model using a likelihood-free Bayesian inference method and strain video monitoring data. In the proposed framework, strain video monitoring data are first compressed into lowdimensional latent time-series features using a convolutional autoencoder. Subsequently, a likelihood-free Bayesian inference method is employed to update the degradation model using a given time duration of the monitoring data. To enable continuous monitoring and model updating over a long time period, a sequential Bayesian model updating scheme is developed. Based on the updated degradation model, failure prognostics are performed sequentially and the associated uncertainty on RUL estimation is also quantified. The application of the developed framework to a miter gate structure demonstrates the efficacy of the proposed framework. Keywords: Remaining useful life; Degradation model; Likelihood-free Bayesian inference; Conditional invertible neural network
6
Zachar, Matej, Vladimi´r Danisˇka, and Vladimi´r Necˇas. "Implementation of Decommissioning Materials Conditional Clearance Process to the OMEGA Calculation Code." In ASME 2010 13th International Conference on Environmental Remediation and Radioactive Waste Management. ASMEDC, 2010. http://dx.doi.org/10.1115/icem2010-40120.
Full textAbstract:
The activities performed during nuclear installation decommissioning process inevitably lead to the production of large amount of radioactive material to be managed. Significant part of materials has such low radioactivity level that allows them to be released to the environment without any restriction for further use. On the other hand, for materials with radioactivity slightly above the defined unconditional clearance level, there is a possibility to release them conditionally for a specific purpose in accordance with developed scenario assuring that radiation exposure limits for population not to be exceeded. The procedure of managing such decommissioning materials, mentioned above, could lead to recycling and reuse of more solid materials and to save the radioactive waste repository volume. In the paper an implementation of the process of conditional release to the OMEGA Code is analyzed in details; the Code is used for calculation of decommissioning parameters. The analytical approach in the material parameters assessment, firstly, assumes a definition of radiological limit conditions, based on the evaluation of possible scenarios for conditionally released materials, and their application to appropriate sorter type in existing material and radioactivity flow system. Other calculation procedures with relevant technological or economical parameters, mathematically describing e.g. final radiation monitoring or transport outside the locality, are applied to the OMEGA Code in the next step. Together with limits, new procedures creating independent material stream allow evaluation of conditional material release process during decommissioning. Model calculations evaluating various scenarios with different input parameters and considering conditional release of materials to the environment are performed to verify the implemented methodology. Output parameters and results of the model assessment are presented, discussed and concluded in the final part of the paper.
7
Timashev, Sviatoslav A. "Optimal Control of Performance Risk for Large Potentially Dangerous Systems (LPDS)." In ASME 2002 Pressure Vessels and Piping Conference. ASMEDC, 2002. http://dx.doi.org/10.1115/pvp2002-1389.
Full textAbstract:
The paper considers the safety problem for large potentially dangerous systems (LPDS). Disruption of their normal operations may lead to casualties, ecological and property damage. Solution to the above problem is sought in the framework of risk control of LPDS during their normal operation, based on the principle of preventive actions. Risk is described as the product of conditional probability of failure and the overall consequences of such failure. Methods of brining down risk analysis problems to reliability problems are presented. They are based on the following: assessments of “cost of life” (as economic equivalent of casualty); simultaneous optimization of the LPDS and its safety subsystem (expansion of the object of optimization). Such an approach allows unification and merging of structural reliability theory and probabilistic risk analysis. A quantitative method of damage size (the first component of risk) assessment is described, based on computer modeling of a full group of scenarios of a structural failure developing into a full blown LPDS catastrophe. As a result of modeling, the destruction zones and the character, size and probabilities of all kinds of damage (casualties, ecological damage, loss of property) are assessed. It is proposed, as the main method of securing LPDS integrity and safety, to equip each LPDS with suitable monitoring/inspection/maintenance systems, designed as an instrument for controlling the second component of risk (conditional probability of failure), on the basis of a three-level (warning-alarm-failure) control policy. In the outlined format maintenance/repair is considered as optimal control of random degradation and renewal functions, interaction of which forms a certain regeneration process. Analysis of this process allows defining the optimal triggering levels of deterioration parameters or risk that minimize total expenditures of LPDS performance while ensuring its safety. The problem formulated above naturally embodies all existing maintenance methods (based on admissible performance time, rate of failure and on actual and prognosed system condition). Further, the problem of optimal cessation of performance is solved. It allows convoluting a multi-parameter problem into a one-parameter problem and defining the ultimate permissible level of conditional probability of failure. The described methods of risk analysis and control were used in residual lifetime monitoring systems for oil pumping aggregates and for main oil pipe line segments repair prioritization.
8
Qi, Junyu, Alexandre Mauricio, and Konstantinos Gryllias. "Comparison of Blind Diagnostic Indicators for Condition Monitoring of Wind Turbine Gearbox Bearings." In ASME Turbo Expo 2020: Turbomachinery Technical Conference and Exposition. American Society of Mechanical Engineers, 2020. http://dx.doi.org/10.1115/gt2020-15278.
Full textAbstract:
Abstract Under the pressure of climate change, renewable energy gradually replaces fossil fuels and plays nowadays a significant role in energy production. Among different types of energy sources, wind power covered 14% of the EU’s electricity demand in 2018. The Operations and Maintenance (O&M) costs of wind turbines may easily reach up to 20–25% of the total leverised cost per kWh produced over the lifetime of the turbine for a new unit. According to Wood Mackenzie Power & Renewables (WMPR) onshore wind farm operators are expected to spend nearly $15 billion on O&M services in 2019. Manufacturers and operators try to reduce O&M on one hand by developing new turbine designs and on the other hand by adopting condition monitoring approaches. One of the most critical and rather complex assembly of wind turbines is the gearbox. Gearboxes are designed to last till the end of asset’s lifetime, according to the IEC 61400-4 standards. On the other hand, a recent study over approximately 350 offshore wind turbines indicated that gearboxes might have to be replaced as early as 6.5 years. Therefore a plethora of sensor types and signal processing methodologies have been proposed in order to accurately detect and diagnose the presence of a fault. Among others, Envelope Analysis is one of the most important methodologies, where an envelope of the vibration signal is estimated, usually after filtering around a selected frequency band excited by impacts due to the fault. Sometimes the gearbox is equipped with many acceleration sensors and its kinematics is clearly known. In these cases Cyclostationary Analysis and the corresponding methodologies, i.e. the Cyclic Spectral Correlation and the Cyclic Spectral Coherence, have been proposed as powerful tools. On the other hand often the gearbox is equipped with a limited number of sensors and a simple global diagnostic indicator is demanded, being capable to detect globally various faults of different components. The scope of this paper is the application and comparison of a number of blind global diagnostic indicators which are based on Entropy (Permutation entropy, Approximate entropy, Samples entropy, Fuzzy entropy, Conditional entropy and Wiener entropy), on Negentropy (Infogram), on Sparsity (Sparse-L2/L1, Sparse-L1/L0, Sparse-Gini index) and on Statistics (Mean, Standard deviation, Kurtosis, etc.). The performance of the indicators is evaluated and compared on a wind turbine data set, consisted of vibration data captured by one accelerometer mounted on six 2.5 MW wind turbines, located in a wind park in northern Sweden, where two different bearing faults have been filed, for one wind turbine, during a period of 46 months. Among the different diagnostic indicators Permutation entropy, Approximate entropy, Samples entropy, Fuzzy entropy, Conditional entropy and Wiener entropy achieve the best results detecting blindly the two failure events.
9
Liu, Xiaoguang, Yongjie Pan, and Xinxin Zhao. "Research on Key Technology of Operation and Maintenance Management of Long Span Railway Steel Bridge Based on BIM." In IABSE Conference, Seoul 2020: Risk Intelligence of Infrastructures. Zurich, Switzerland: International Association for Bridge and Structural Engineering (IABSE), 2020. http://dx.doi.org/10.2749/seoul.2020.222.
Full textAbstract:
<p>In order to adapt to the development trend of informatization and intelligence of railway bridge operation and maintenance management, the integration of BIM Technology and large-span railway steel bridge operation and maintenance business becomes more and more urgent. Taking one special railway steel bridge as an example, the division levels of bridge structural parts, structural elements and specific components were defined, and the refined BIM model of bridge was established based on the demand of operation and maintenance. The knowledge base systems of component, defect, inspection and maintenance in bridge was formed. The three terminal BIM management system was developed, and the closed-loop management process of bridge inspection, maintenance and repair based on the BIM model was established. At the same time, the monitoring information could be integrated, which can provide the basis for the formation of bridge digital twins. The research results provide a firmly support for data-driven comprehensive evaluation and conditional maintenance of railway steel bridges.</p>
10
Li, Lin, Zeyi Sun, Xinwei Xu, and Kaifu Zhang. "Multi-Zone Proportional Hazard Model for a Multi-Stage Degradation Process." In ASME 2013 International Manufacturing Science and Engineering Conference collocated with the 41st North American Manufacturing Research Conference. American Society of Mechanical Engineers, 2013. http://dx.doi.org/10.1115/msec2013-1113.
Full textAbstract:
Conditional-based maintenance (CBM) decision-making is of high interests in recent years due to its better performance on cost efficiency compared to other traditional policies. One of the most respected methods based on condition-monitoring data for maintenance decision-making is Proportional Hazards Model (PHM). It utilizes condition-monitoring data as covariates and identifies their effects on the lifetime of a component. Conventional modeling process of PHM only treats the degradation process as a whole lifecycle. In this paper, the PHM is advanced to describe a multi-zone degradation system considering the fact that the lifecycle of a machine can be divided into several different degradation stages. The methods to estimate reliability and performance prognostics are developed based on the proposed multi-zone PHM to predict the remaining time that the machine stays at the current stage before transferring into the next stage and the remaining useful life (RUL). The results illustrate that the multi-zone PHM effectively monitors the equipment status change and leads to a more accurate RUL prediction compared with traditional PHM.