Pub Date : 2019-07-01DOI: 10.1109/SAFEPROCESS45799.2019.9213312
Xiaoqiang Zhu, Jingzhong Fang, M. Zhong, Yang Liu
In this work, we investigate the fault detection (FD) problem based on parity space for linear discrete time systems with integral measurements. The traditional parity space-based FD method is no longer applicable to the systems with integral measurements. The transfer matrices need to be redesigned to make the traditional parity relation still hold. Moreover, an algorithm is also provided to compute the transfer matrices and the singular value decomposition (SVD) is used to design the parity space matrices. Finally, an illustrative example about a three-tank system is demonstrated the availability of our proposed approach.
{"title":"The Parity Space-based Fault Detection for Linear Discrete Time Systems with Integral Measurements","authors":"Xiaoqiang Zhu, Jingzhong Fang, M. Zhong, Yang Liu","doi":"10.1109/SAFEPROCESS45799.2019.9213312","DOIUrl":"https://doi.org/10.1109/SAFEPROCESS45799.2019.9213312","url":null,"abstract":"In this work, we investigate the fault detection (FD) problem based on parity space for linear discrete time systems with integral measurements. The traditional parity space-based FD method is no longer applicable to the systems with integral measurements. The transfer matrices need to be redesigned to make the traditional parity relation still hold. Moreover, an algorithm is also provided to compute the transfer matrices and the singular value decomposition (SVD) is used to design the parity space matrices. Finally, an illustrative example about a three-tank system is demonstrated the availability of our proposed approach.","PeriodicalId":353946,"journal":{"name":"2019 CAA Symposium on Fault Detection, Supervision and Safety for Technical Processes (SAFEPROCESS)","volume":"17 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2019-07-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"115494787","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":0,"RegionCategory":"","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}
Pub Date : 2019-07-01DOI: 10.1109/SAFEPROCESS45799.2019.9213342
Saite Fan, Feifan Shen, Zhihuan Song
In this paper, a data-driven framework base on density peak clustering (DPC) and just-in-time learning (JITL) is developed to handle with multiphase and multimode monitoring problem of batch processes. To deal with batch-to-batch variations and non-Gaussian distributions of batch data, DPC is firstly used for phase and mode classification and identification. Due to the variety of output trajectories in the same phase and mode, JITL is used to extract similar trajectories as an advanced subdivision strategy to obtain sub-datasets with similar output trajectories. Thus, for each sub-phase in a certain sub-mode, local quality-relevant models are established to achieve an accurate modeling and monitoring scheme. Finally, Bayesian fusion is introduced as the ensemble strategy to determine the final probability of faulty conditions. For performance evaluation, a numerical example and a simulated fed-batch penicillin fermentation process are provided. The monitoring results show the effectiveness of the proposed method.
{"title":"Multiphase and Multimode Monitoring of Batch Processes Based on Density Peak Clustering and Just-in-time Learning","authors":"Saite Fan, Feifan Shen, Zhihuan Song","doi":"10.1109/SAFEPROCESS45799.2019.9213342","DOIUrl":"https://doi.org/10.1109/SAFEPROCESS45799.2019.9213342","url":null,"abstract":"In this paper, a data-driven framework base on density peak clustering (DPC) and just-in-time learning (JITL) is developed to handle with multiphase and multimode monitoring problem of batch processes. To deal with batch-to-batch variations and non-Gaussian distributions of batch data, DPC is firstly used for phase and mode classification and identification. Due to the variety of output trajectories in the same phase and mode, JITL is used to extract similar trajectories as an advanced subdivision strategy to obtain sub-datasets with similar output trajectories. Thus, for each sub-phase in a certain sub-mode, local quality-relevant models are established to achieve an accurate modeling and monitoring scheme. Finally, Bayesian fusion is introduced as the ensemble strategy to determine the final probability of faulty conditions. For performance evaluation, a numerical example and a simulated fed-batch penicillin fermentation process are provided. The monitoring results show the effectiveness of the proposed method.","PeriodicalId":353946,"journal":{"name":"2019 CAA Symposium on Fault Detection, Supervision and Safety for Technical Processes (SAFEPROCESS)","volume":"52 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2019-07-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"115602309","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":0,"RegionCategory":"","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}
Pub Date : 2019-07-01DOI: 10.1109/SAFEPROCESS45799.2019.9213414
Zicheng Wang, Lifu Yi, Kai Yu, G. Gu, Jianqiang Wang
Track circuit (TC) is an important equipment in China Train Control System (CTCS). But its failure rate has been high. The predictive maintenance mechanism of TC can further ensure the safe operation of train. While the fault diagnosis and realization of TC status is the premise to achieve prediction maintenance. With regards to this, a fault diagnosis method for TC based on Grey Wolf Optimizer (GWO) algorithm is put forward in this paper. A Uniform Transmission Line (UTL) Model of TC is established and the impact on the Locomotive Signal Amplitude Envelope (LSAE) by ballast resistance, compensation capacitor is analyzed. The above parameters are chosen as the decision variables. To minimum the difference between the real LSAE and the one calculated using the UTL model as the objective to form the fitness function. GWO algorithm has the characteristic of insensitivity to initial solution values, higher optimization efficiency and global optimization ability and it is employed to iteratively search for the optimum solution of TC parameters. Experiment results show that the method proposed in this paper can realize the diagnosis of important parameters of TC and it has high adaptability and excellent accuracy.
{"title":"Fault Diagnosis of Track Circuit Compensation Capacitor Based on GWO Algorithm","authors":"Zicheng Wang, Lifu Yi, Kai Yu, G. Gu, Jianqiang Wang","doi":"10.1109/SAFEPROCESS45799.2019.9213414","DOIUrl":"https://doi.org/10.1109/SAFEPROCESS45799.2019.9213414","url":null,"abstract":"Track circuit (TC) is an important equipment in China Train Control System (CTCS). But its failure rate has been high. The predictive maintenance mechanism of TC can further ensure the safe operation of train. While the fault diagnosis and realization of TC status is the premise to achieve prediction maintenance. With regards to this, a fault diagnosis method for TC based on Grey Wolf Optimizer (GWO) algorithm is put forward in this paper. A Uniform Transmission Line (UTL) Model of TC is established and the impact on the Locomotive Signal Amplitude Envelope (LSAE) by ballast resistance, compensation capacitor is analyzed. The above parameters are chosen as the decision variables. To minimum the difference between the real LSAE and the one calculated using the UTL model as the objective to form the fitness function. GWO algorithm has the characteristic of insensitivity to initial solution values, higher optimization efficiency and global optimization ability and it is employed to iteratively search for the optimum solution of TC parameters. Experiment results show that the method proposed in this paper can realize the diagnosis of important parameters of TC and it has high adaptability and excellent accuracy.","PeriodicalId":353946,"journal":{"name":"2019 CAA Symposium on Fault Detection, Supervision and Safety for Technical Processes (SAFEPROCESS)","volume":"23 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2019-07-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"127132645","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":0,"RegionCategory":"","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}
Pub Date : 2019-07-01DOI: 10.1109/SAFEPROCESS45799.2019.9213446
Ruihua Jiao, Kai-xiang Peng, Kai Zhang, Liang Ma, Yanting Pi
The prediction of remaining useful life (RUL) and safety assessment are the key of prognostics and health management (PHM) that provide decision support for it. A hybrid approach for the prediction of RUL which combines partial least squares (PLS) with support vector regression (SVR) and similarity based prediction (SBP) is proposed firstly. The SVR model, trained in a supervised manner, is employed to learn features extracted by PLS to capture the health indicator (HI) degenerate trajectory. Then the RUL prediction is implemented by calculating the similarity between the HI degenerate trajectories. Furthermore, on the basis of the prediction results, we construct a fuzzy comprehensive evaluation model to evaluate the safety level. To validate the proposed approach, a case study is performed on benchmark simulated aircraft engine datasets. The results show the superiority of the hybrid approach compared with other methods reported in the literature and indicate the effectiveness of the fuzzy comprehensive evaluation method in safety assessment.
{"title":"A Novel Scheme for Remaining Useful Life Prediction and Safety Assessment Based on Hybrid Method","authors":"Ruihua Jiao, Kai-xiang Peng, Kai Zhang, Liang Ma, Yanting Pi","doi":"10.1109/SAFEPROCESS45799.2019.9213446","DOIUrl":"https://doi.org/10.1109/SAFEPROCESS45799.2019.9213446","url":null,"abstract":"The prediction of remaining useful life (RUL) and safety assessment are the key of prognostics and health management (PHM) that provide decision support for it. A hybrid approach for the prediction of RUL which combines partial least squares (PLS) with support vector regression (SVR) and similarity based prediction (SBP) is proposed firstly. The SVR model, trained in a supervised manner, is employed to learn features extracted by PLS to capture the health indicator (HI) degenerate trajectory. Then the RUL prediction is implemented by calculating the similarity between the HI degenerate trajectories. Furthermore, on the basis of the prediction results, we construct a fuzzy comprehensive evaluation model to evaluate the safety level. To validate the proposed approach, a case study is performed on benchmark simulated aircraft engine datasets. The results show the superiority of the hybrid approach compared with other methods reported in the literature and indicate the effectiveness of the fuzzy comprehensive evaluation method in safety assessment.","PeriodicalId":353946,"journal":{"name":"2019 CAA Symposium on Fault Detection, Supervision and Safety for Technical Processes (SAFEPROCESS)","volume":"47 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2019-07-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"127047267","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":0,"RegionCategory":"","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}
Pub Date : 2019-07-01DOI: 10.1109/SAFEPROCESS45799.2019.9213373
Xintong Li, Rui Felizardo, Feng Xue, Rui Felizardo Mauaie, Li-da Qin, Kai Song
Kernel principal component analysis is a technique applied for monitoring nonlinear processes. However, compute control limit based on Gaussian distribution can deteriorate its performance. Kernel density estimation is applied to solve the aforementioned issue. In conventional KPCA, a kernel based model depends on a single Gaussian kernel function selected empirically, which means a single model corresponds to a single Gaussian kernel function. It may be effective for certain kinds of fault but not for others which leads to a poor detection performance. Different Gaussian kernel functions may be needed for each kind of fault. To solve these issue, in this work, a novel ensemble kernel principal component analysis-Bayes (EKPCA-Bayes) is proposed. The ensemble learning with Bayesian inference strategy were applied into conventional KPCA. At last, the fault diagnosis performance is tested for the first time through contribution plot to find out the root cause variables. The proposed method was tested in the Tennessee Eastman (TE) benchmark process for fault detection and fault diagnosis as well.
{"title":"Fault detection and diagnosis based on new ensemble kernel principal component analysis","authors":"Xintong Li, Rui Felizardo, Feng Xue, Rui Felizardo Mauaie, Li-da Qin, Kai Song","doi":"10.1109/SAFEPROCESS45799.2019.9213373","DOIUrl":"https://doi.org/10.1109/SAFEPROCESS45799.2019.9213373","url":null,"abstract":"Kernel principal component analysis is a technique applied for monitoring nonlinear processes. However, compute control limit based on Gaussian distribution can deteriorate its performance. Kernel density estimation is applied to solve the aforementioned issue. In conventional KPCA, a kernel based model depends on a single Gaussian kernel function selected empirically, which means a single model corresponds to a single Gaussian kernel function. It may be effective for certain kinds of fault but not for others which leads to a poor detection performance. Different Gaussian kernel functions may be needed for each kind of fault. To solve these issue, in this work, a novel ensemble kernel principal component analysis-Bayes (EKPCA-Bayes) is proposed. The ensemble learning with Bayesian inference strategy were applied into conventional KPCA. At last, the fault diagnosis performance is tested for the first time through contribution plot to find out the root cause variables. The proposed method was tested in the Tennessee Eastman (TE) benchmark process for fault detection and fault diagnosis as well.","PeriodicalId":353946,"journal":{"name":"2019 CAA Symposium on Fault Detection, Supervision and Safety for Technical Processes (SAFEPROCESS)","volume":"17 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2019-07-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"122343273","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":0,"RegionCategory":"","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}
Pub Date : 2019-07-01DOI: 10.1109/SAFEPROCESS45799.2019.9213313
Hongya Wang, L. Yao
This paper presents a new fault diagnosis (FD) and fault-tolerant control (FTC) method based on the model equivalent transformation for the stochastic distribution time-delayed control systems, in which the random delay between the controller and the actuator and the external disturbance is considered. The linear B-spline is used to approximate the probability density function (PDF) of system output. The original system is transformed into an equivalent system without random delay based on the Laplace transformation method. Then, the equivalent system is converted to the augmentation system with a new state variable is introduced. The observer is designed to estimate the fault information based on the augmentation system. The adaptive control algorithm and a virtual sensor compensator are designed to realise the FTC. Finally, simulations is given to show the efficiency of the proposed approach.
{"title":"Sensor Fault Diagnosis and Fault Tolerant Control for Stochastic Distribution Time-delayed Control Systems","authors":"Hongya Wang, L. Yao","doi":"10.1109/SAFEPROCESS45799.2019.9213313","DOIUrl":"https://doi.org/10.1109/SAFEPROCESS45799.2019.9213313","url":null,"abstract":"This paper presents a new fault diagnosis (FD) and fault-tolerant control (FTC) method based on the model equivalent transformation for the stochastic distribution time-delayed control systems, in which the random delay between the controller and the actuator and the external disturbance is considered. The linear B-spline is used to approximate the probability density function (PDF) of system output. The original system is transformed into an equivalent system without random delay based on the Laplace transformation method. Then, the equivalent system is converted to the augmentation system with a new state variable is introduced. The observer is designed to estimate the fault information based on the augmentation system. The adaptive control algorithm and a virtual sensor compensator are designed to realise the FTC. Finally, simulations is given to show the efficiency of the proposed approach.","PeriodicalId":353946,"journal":{"name":"2019 CAA Symposium on Fault Detection, Supervision and Safety for Technical Processes (SAFEPROCESS)","volume":"22 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2019-07-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"122472917","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":0,"RegionCategory":"","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}
Pub Date : 2019-07-01DOI: 10.1109/SAFEPROCESS45799.2019.9213418
Yang Yue, Wei Dong, Xinya Sun, Xingquan Ji
The traction system of high-speed train has many faults, among which compound faults account for a certain proportion. Compared with single faults, compound faults will lead to more serious consequences. This paper takes the fault chain of compound fault of “CRH380D high-speed train traction inverter IGBT open circuit and motor speed sensor gain coefficient is too small” as an example, establishes a mathematical model of the fault chain based on the fault mechanism, and obtains the relationship between fault characteristic variables and traction motor failure rate by using relevant experimental data and national standards, thus obtains the probability of compound risk chain occurrence. Event tree and grey clustering method were used to evaluate the consequences of the compound risk chain. Finally, taking the actual Chengdu-Chongqing passenger dedicated line as an example, the risk analysis and evaluation of the compound fault were carried out.
{"title":"A Dynamic Risk Analysis Method for Compound Faults of Traction System of High Speed Train Based on Characteristic Variables","authors":"Yang Yue, Wei Dong, Xinya Sun, Xingquan Ji","doi":"10.1109/SAFEPROCESS45799.2019.9213418","DOIUrl":"https://doi.org/10.1109/SAFEPROCESS45799.2019.9213418","url":null,"abstract":"The traction system of high-speed train has many faults, among which compound faults account for a certain proportion. Compared with single faults, compound faults will lead to more serious consequences. This paper takes the fault chain of compound fault of “CRH380D high-speed train traction inverter IGBT open circuit and motor speed sensor gain coefficient is too small” as an example, establishes a mathematical model of the fault chain based on the fault mechanism, and obtains the relationship between fault characteristic variables and traction motor failure rate by using relevant experimental data and national standards, thus obtains the probability of compound risk chain occurrence. Event tree and grey clustering method were used to evaluate the consequences of the compound risk chain. Finally, taking the actual Chengdu-Chongqing passenger dedicated line as an example, the risk analysis and evaluation of the compound fault were carried out.","PeriodicalId":353946,"journal":{"name":"2019 CAA Symposium on Fault Detection, Supervision and Safety for Technical Processes (SAFEPROCESS)","volume":"26 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2019-07-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"122611089","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":0,"RegionCategory":"","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}
Pub Date : 2019-07-01DOI: 10.1109/SAFEPROCESS45799.2019.9213329
Haoqiang Shi, Shaolin Hu, Jiaxu Zhang
As the core component of the navigation system, the gyroscope directly affects the navigation performance of the system. In this paper, the three-degree-of-freedom gyroscope is used as the object, firstly, the three gyroscope redundant configuration forms are studied, and the combined gyroscope data simulation platform is built by using the UAV and the gyroscope sensor, and simulate possible failures by interfering with a gyroscope during flight tests. Secondly, the faulty gyro detection and identification are carried out by using the measured redundant information. At the same time, the gyroscope fault detection algorithm with redundant configuration is proposed, the accuracy and feasibility of the method are verified by the measured data of the gyroscope. The simulation shows that the method can accurately detect the gyroscope failure, improve the data utilization of the gyroscope, and increase the reliability of the navigation system.
{"title":"Research on Fault Diagnosis of Three Degrees of Freedom Gyroscope Redundant System","authors":"Haoqiang Shi, Shaolin Hu, Jiaxu Zhang","doi":"10.1109/SAFEPROCESS45799.2019.9213329","DOIUrl":"https://doi.org/10.1109/SAFEPROCESS45799.2019.9213329","url":null,"abstract":"As the core component of the navigation system, the gyroscope directly affects the navigation performance of the system. In this paper, the three-degree-of-freedom gyroscope is used as the object, firstly, the three gyroscope redundant configuration forms are studied, and the combined gyroscope data simulation platform is built by using the UAV and the gyroscope sensor, and simulate possible failures by interfering with a gyroscope during flight tests. Secondly, the faulty gyro detection and identification are carried out by using the measured redundant information. At the same time, the gyroscope fault detection algorithm with redundant configuration is proposed, the accuracy and feasibility of the method are verified by the measured data of the gyroscope. The simulation shows that the method can accurately detect the gyroscope failure, improve the data utilization of the gyroscope, and increase the reliability of the navigation system.","PeriodicalId":353946,"journal":{"name":"2019 CAA Symposium on Fault Detection, Supervision and Safety for Technical Processes (SAFEPROCESS)","volume":"12 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2019-07-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"122188667","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":0,"RegionCategory":"","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}
Pub Date : 2019-07-01DOI: 10.1109/SAFEPROCESS45799.2019.9213408
Rui Wu, Jie Ma
Data-driven Prognostic(DDP) has become one of the major method of component of prognostic and healthy management(PHM) systems in the industrial area. The fault prediction methods mainly include fault failure probability assessment and remaining useful life(RUL) prediction. As the basis for the development of equipment maintenance strategy, the remaining service life prediction is one of the important links of PHM. Accurately predicting the RUL can provide comprehensive, accurate and effective information for the development of equipment maintenance strategies, which helps to avoid equipment failure and reduce the loss caused by failure, thus ensuring the safe and reliable operation of the equipment. In recent years, the RUL prediction has received extensive attention in research and engineering fields and achieved certain results. Among them, the method based on degraded data modeling has become one of the mainstream methods in the field of life prediction because it does not require failure data and the convenience of characterizing the uncertainty of degradation. DDP about RUL method based on degradation data can be classified into the machine learning method and the mathematical statistics method. Prognostic techniques are designed to accurately estimate the RUL of subsystems or components using sensor data. However, mathematical statistics methods of estimating RUL use sensor data to make assumptions as to how the system degrades or fades (eg, exponential decay); As well as the current some machine learning methods ignore the uncertainty. Based on current problems, we propose a novel Long-Short Term Memory(LSTM) Neural Network complement with Uncertainty: automatically learn higher-level abstract representations from the underlying raw sensor data, and use these representations to estimate RUL from the sensor data; it does not rely on any degradation trend assumption, is robust to noise, and can handle missing values and uncertainty in sensor data. We compared several publicly available algorithms on a publicly available Turbofan engine dataset and found that several of the proposed metrics (Score, etc.) outperformed the previously proposed state-of-art techniques.
{"title":"An Improved LSTM Neural Network with Uncertainty to Predict Remaining Useful Life","authors":"Rui Wu, Jie Ma","doi":"10.1109/SAFEPROCESS45799.2019.9213408","DOIUrl":"https://doi.org/10.1109/SAFEPROCESS45799.2019.9213408","url":null,"abstract":"Data-driven Prognostic(DDP) has become one of the major method of component of prognostic and healthy management(PHM) systems in the industrial area. The fault prediction methods mainly include fault failure probability assessment and remaining useful life(RUL) prediction. As the basis for the development of equipment maintenance strategy, the remaining service life prediction is one of the important links of PHM. Accurately predicting the RUL can provide comprehensive, accurate and effective information for the development of equipment maintenance strategies, which helps to avoid equipment failure and reduce the loss caused by failure, thus ensuring the safe and reliable operation of the equipment. In recent years, the RUL prediction has received extensive attention in research and engineering fields and achieved certain results. Among them, the method based on degraded data modeling has become one of the mainstream methods in the field of life prediction because it does not require failure data and the convenience of characterizing the uncertainty of degradation. DDP about RUL method based on degradation data can be classified into the machine learning method and the mathematical statistics method. Prognostic techniques are designed to accurately estimate the RUL of subsystems or components using sensor data. However, mathematical statistics methods of estimating RUL use sensor data to make assumptions as to how the system degrades or fades (eg, exponential decay); As well as the current some machine learning methods ignore the uncertainty. Based on current problems, we propose a novel Long-Short Term Memory(LSTM) Neural Network complement with Uncertainty: automatically learn higher-level abstract representations from the underlying raw sensor data, and use these representations to estimate RUL from the sensor data; it does not rely on any degradation trend assumption, is robust to noise, and can handle missing values and uncertainty in sensor data. We compared several publicly available algorithms on a publicly available Turbofan engine dataset and found that several of the proposed metrics (Score, etc.) outperformed the previously proposed state-of-art techniques.","PeriodicalId":353946,"journal":{"name":"2019 CAA Symposium on Fault Detection, Supervision and Safety for Technical Processes (SAFEPROCESS)","volume":"1 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2019-07-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"129212115","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":0,"RegionCategory":"","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}
Pub Date : 2019-07-01DOI: 10.1109/SAFEPROCESS45799.2019.9213402
Wu-Dong Yang, Ji-Lie Zhang, G. Gu
We propose a parameter estimation approach to fault diagnosis for jointless track circuits in railway transportation, focusing on the compensation capacitors. How to estimate various parameters of the jointless track circuits poses a tremendous challenge, because the existing track circuits do not have sensor networks embedded to the railway network. Assuming the available special inspection train and the measurement data, we analyze how various parameters of the jointless track circuits can be estimated, and how faults in the compensation capacitors can be detected. Our analysis results are illustrated by a numerical example.
{"title":"Parameter Estimation and Fault Diagnosis for Compensation Capacitators in ZPW-2000 Jointless Track Circuit","authors":"Wu-Dong Yang, Ji-Lie Zhang, G. Gu","doi":"10.1109/SAFEPROCESS45799.2019.9213402","DOIUrl":"https://doi.org/10.1109/SAFEPROCESS45799.2019.9213402","url":null,"abstract":"We propose a parameter estimation approach to fault diagnosis for jointless track circuits in railway transportation, focusing on the compensation capacitors. How to estimate various parameters of the jointless track circuits poses a tremendous challenge, because the existing track circuits do not have sensor networks embedded to the railway network. Assuming the available special inspection train and the measurement data, we analyze how various parameters of the jointless track circuits can be estimated, and how faults in the compensation capacitors can be detected. Our analysis results are illustrated by a numerical example.","PeriodicalId":353946,"journal":{"name":"2019 CAA Symposium on Fault Detection, Supervision and Safety for Technical Processes (SAFEPROCESS)","volume":"24 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2019-07-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"123838259","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":0,"RegionCategory":"","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}
京公网安备 11010802042870号
京ICP备2023020795号-1
扫码关注我们
求助内容：
应助结果提醒方式：