Pub Date : 2019-07-01DOI: 10.1109/SAFEPROCESS45799.2019.9213386
Zhi-wen Chen, Zhuo Chen, Tao Peng, Ketian Liang, Chunhua Yang, Xu Yang
Fault detection is critical to ensure the safe operation of high speed trains. One class support vector machine (OCSVM) and one class minimax probability machine (OCMPM) are two domain-based single class classification methods and commonly used for fault detection. This paper systematically analyzes their training and detecting complexity, principle of optimization and hyperparameter influence of both methods, and compares their performance on motor and sensor fault data from the simulated traction control system of the high speed train. It shows that OCMPM achieves higher fault detection rate than OCSVM given the same false alarm rate. But OCMPM is unfeasible used for real-time fault detection when the training dataset is large.
{"title":"A comparison of OCMPM and OCSVM in motor and sensor fault detection for traction control system","authors":"Zhi-wen Chen, Zhuo Chen, Tao Peng, Ketian Liang, Chunhua Yang, Xu Yang","doi":"10.1109/SAFEPROCESS45799.2019.9213386","DOIUrl":"https://doi.org/10.1109/SAFEPROCESS45799.2019.9213386","url":null,"abstract":"Fault detection is critical to ensure the safe operation of high speed trains. One class support vector machine (OCSVM) and one class minimax probability machine (OCMPM) are two domain-based single class classification methods and commonly used for fault detection. This paper systematically analyzes their training and detecting complexity, principle of optimization and hyperparameter influence of both methods, and compares their performance on motor and sensor fault data from the simulated traction control system of the high speed train. It shows that OCMPM achieves higher fault detection rate than OCSVM given the same false alarm rate. But OCMPM is unfeasible used for real-time fault detection when the training dataset is large.","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":"126376102","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/SAFEPROCESS45799.2019.9213417
Zhichao Li, Tianzhen Wang, Milu Zhang, Yide Wang, D. Diallo
In recent years, more and more attention has been paid to marine current turbines (MCTs). Attachments on blades will influence the system operation by causing imbalance and it is essential to monitor its working state, repair or replace the faulty blade (s) to reduce its damages. Imbalance fault detection of MCTs using electric signals has many superiorities compared with traditional vibration-based method. However, there are some shortcomings in using decomposition method to weaken the influence of waves and turbulence. This paper proposes a method to detect the imbalance fault of MCTs using voltage signal. In this proposed method, the instantaneous voltage frequency and average voltage frequency is calculated through Hilbert transform (HT). Meanwhile, the imbalance fault frequency is extracted by using the cubic spline interpolation. Finally, the wavelet transform (WT) method is used to detect whether there is a blade imbalance fault. The effectiveness of this method is verified by theoretical analysis, simulation results and experimental results.
{"title":"An Imbalance Fault Detection Method for MCTs Using Voltage Signal","authors":"Zhichao Li, Tianzhen Wang, Milu Zhang, Yide Wang, D. Diallo","doi":"10.1109/SAFEPROCESS45799.2019.9213417","DOIUrl":"https://doi.org/10.1109/SAFEPROCESS45799.2019.9213417","url":null,"abstract":"In recent years, more and more attention has been paid to marine current turbines (MCTs). Attachments on blades will influence the system operation by causing imbalance and it is essential to monitor its working state, repair or replace the faulty blade (s) to reduce its damages. Imbalance fault detection of MCTs using electric signals has many superiorities compared with traditional vibration-based method. However, there are some shortcomings in using decomposition method to weaken the influence of waves and turbulence. This paper proposes a method to detect the imbalance fault of MCTs using voltage signal. In this proposed method, the instantaneous voltage frequency and average voltage frequency is calculated through Hilbert transform (HT). Meanwhile, the imbalance fault frequency is extracted by using the cubic spline interpolation. Finally, the wavelet transform (WT) method is used to detect whether there is a blade imbalance fault. The effectiveness of this method is verified by theoretical analysis, simulation results and experimental results.","PeriodicalId":353946,"journal":{"name":"2019 CAA Symposium on Fault Detection, Supervision and Safety for Technical Processes (SAFEPROCESS)","volume":"21 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":"126746747","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/SAFEPROCESS45799.2019.9213359
Yanwen Wang, Maoyin Chen, Donghua Zhou
In this paper, a novel part mutual information based quality-related component analysis (PMIQCA) method is presented to detect quality-related faults and reduce the interference alarms. The low-dimensional subspace of process variables can be found, which reflects real-time changes in quality. The detection rates of quality-unrelated faults can be reduced while the detection rates of faults that are related to quality are increased. The basic idea is to select the most relevant process variables and principal components (PCs) with the maximal part mutual information (PMI) for each iteration, so as to build a more accurate supervisory relations between process variables and quality. Afterwards, two appropriate statistics are established for quality-related fault detection. Finally, the Tennessee Eastman Process (TEP) is carried out to demonstrate the effectiveness of PMIQCA.
{"title":"Part Mutual Information Based Quality-related Component Analysis for Fault Detection","authors":"Yanwen Wang, Maoyin Chen, Donghua Zhou","doi":"10.1109/SAFEPROCESS45799.2019.9213359","DOIUrl":"https://doi.org/10.1109/SAFEPROCESS45799.2019.9213359","url":null,"abstract":"In this paper, a novel part mutual information based quality-related component analysis (PMIQCA) method is presented to detect quality-related faults and reduce the interference alarms. The low-dimensional subspace of process variables can be found, which reflects real-time changes in quality. The detection rates of quality-unrelated faults can be reduced while the detection rates of faults that are related to quality are increased. The basic idea is to select the most relevant process variables and principal components (PCs) with the maximal part mutual information (PMI) for each iteration, so as to build a more accurate supervisory relations between process variables and quality. Afterwards, two appropriate statistics are established for quality-related fault detection. Finally, the Tennessee Eastman Process (TEP) is carried out to demonstrate the effectiveness of PMIQCA.","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":"128112333","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/SAFEPROCESS45799.2019.9213345
Ran Li, Yang Liu
A hybrid dimension reduction algorithm based on feature selection and kernel principal component analysis (KPCA) is proposed in this paper to better realize the classification of the planetary gearbox faults. Firstly, in order to reduce the redundancy of some unnecessary features in the sample to a greater extent and the complexity of the kernel matrix calculation, a multi-criterion feature selection method is used to eliminate the irrelevant features. Secondly, through KPCA, the nonlinear principal component of the selected features is built. Then, fault is recognized by put the feature subset into the SVM classification. The proposed algorithm is applied to a planetary gearbox fault diagnosis experiment, and the experimental results show that the proposed algorithm outperforms the ones which employ feature selection or KPCA separately.
{"title":"Fault Diagnosis for the Planetary Gearbox Based on a Hybrid Dimension Reduction Algorithm","authors":"Ran Li, Yang Liu","doi":"10.1109/SAFEPROCESS45799.2019.9213345","DOIUrl":"https://doi.org/10.1109/SAFEPROCESS45799.2019.9213345","url":null,"abstract":"A hybrid dimension reduction algorithm based on feature selection and kernel principal component analysis (KPCA) is proposed in this paper to better realize the classification of the planetary gearbox faults. Firstly, in order to reduce the redundancy of some unnecessary features in the sample to a greater extent and the complexity of the kernel matrix calculation, a multi-criterion feature selection method is used to eliminate the irrelevant features. Secondly, through KPCA, the nonlinear principal component of the selected features is built. Then, fault is recognized by put the feature subset into the SVM classification. The proposed algorithm is applied to a planetary gearbox fault diagnosis experiment, and the experimental results show that the proposed algorithm outperforms the ones which employ feature selection or KPCA separately.","PeriodicalId":353946,"journal":{"name":"2019 CAA Symposium on Fault Detection, Supervision and Safety for Technical Processes (SAFEPROCESS)","volume":"28 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":"134293234","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/SAFEPROCESS45799.2019.9213390
Zixin An, Hao Yang, B. Jiang
In this paper, based on the small-gain theorem of large-scale interconnected systems, we study the convergence performance of nonlinear interconnected systems with cycles, and establish a safely reconfigurable condition for the control law of each subsystem, which is applied to design fault-tolerant control (FTC) schemes. Both individual and cooperative FTC methods are presented in this paper by redesigning the controller of each subsystem and adjusting the interconnected gain between subsystems to ensure that the trajectories of states do not exceed the given safety bound.
{"title":"Safe Reconfigurability of a Class of Nonlinear Interconnected Systems","authors":"Zixin An, Hao Yang, B. Jiang","doi":"10.1109/SAFEPROCESS45799.2019.9213390","DOIUrl":"https://doi.org/10.1109/SAFEPROCESS45799.2019.9213390","url":null,"abstract":"In this paper, based on the small-gain theorem of large-scale interconnected systems, we study the convergence performance of nonlinear interconnected systems with cycles, and establish a safely reconfigurable condition for the control law of each subsystem, which is applied to design fault-tolerant control (FTC) schemes. Both individual and cooperative FTC methods are presented in this paper by redesigning the controller of each subsystem and adjusting the interconnected gain between subsystems to ensure that the trajectories of states do not exceed the given safety bound.","PeriodicalId":353946,"journal":{"name":"2019 CAA Symposium on Fault Detection, Supervision and Safety for Technical Processes (SAFEPROCESS)","volume":"311 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":"133345268","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/SAFEPROCESS45799.2019.9213410
Qing Wang, X. Liang, Maopeng Ran, Chaoyang Dong
The paper investigate the fault-tolerant attitude control for the rigid spacecraft attitude system with external disturbances and actuator faults simultaneously. Firstly, an iterative learning-based observer is proposed, which can estimate the actuator faults with high precise even in presence of the disturbance. Then, employing the estimate informations of the designed observer, a sliding-mode fault-tolerant control scheme is designed to guarantee stability of the closed-loop system and reject to the external disturbance. Finally, the simulation results are given to validate the effectiveness of the proposed approaches.
{"title":"Observer-based Sliding Mode Fault-Tolerant Control for Spacecraft Attitude System with Actuator Faults","authors":"Qing Wang, X. Liang, Maopeng Ran, Chaoyang Dong","doi":"10.1109/SAFEPROCESS45799.2019.9213410","DOIUrl":"https://doi.org/10.1109/SAFEPROCESS45799.2019.9213410","url":null,"abstract":"The paper investigate the fault-tolerant attitude control for the rigid spacecraft attitude system with external disturbances and actuator faults simultaneously. Firstly, an iterative learning-based observer is proposed, which can estimate the actuator faults with high precise even in presence of the disturbance. Then, employing the estimate informations of the designed observer, a sliding-mode fault-tolerant control scheme is designed to guarantee stability of the closed-loop system and reject to the external disturbance. Finally, the simulation results are given to validate the effectiveness of the proposed approaches.","PeriodicalId":353946,"journal":{"name":"2019 CAA Symposium on Fault Detection, Supervision and Safety for Technical Processes (SAFEPROCESS)","volume":"11 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":"130795578","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/SAFEPROCESS45799.2019.9213407
Fan Liu, Peiliang Wang, Zhiduan Cai, Zhe Zhou, Yanfeng Wang, Zeyu Yang
With the rapid development of deep learning in recent years, more and more deep architecture models have been used for batch process fault diagnosis. Deep Belief Network (DBN) has advantages in extracting features and processing high-dimensional, non-linear data, but the relevance of time series is not fully considered in training with time-dependent signals. The batch process has the characteristics of non-linearity, multiple working conditions and multiple time periods. Hence, DBN does not perform well in batch process. For this purpose, a method based on the combination of Long Short-Term Memory (LSTM) network and Deep Belief Network (DBN) is proposed. The method first adopts the preprocessing method of variable expansion and continuous sampling, and then uses DBN-LSTM network for feature extraction, time correlation analysis, and fault diagnosis. This method is applied to a class of semiconductor etching process. The experimental results show that the proposed method can effectively extract time-ordered nonlinear fault features from the original batch process data and has high fault diagnosis accuracy.
{"title":"Batch Process Fault Diagnosis Based on The Combination of Deep Belief Network and Long Short-Term Memory Network","authors":"Fan Liu, Peiliang Wang, Zhiduan Cai, Zhe Zhou, Yanfeng Wang, Zeyu Yang","doi":"10.1109/SAFEPROCESS45799.2019.9213407","DOIUrl":"https://doi.org/10.1109/SAFEPROCESS45799.2019.9213407","url":null,"abstract":"With the rapid development of deep learning in recent years, more and more deep architecture models have been used for batch process fault diagnosis. Deep Belief Network (DBN) has advantages in extracting features and processing high-dimensional, non-linear data, but the relevance of time series is not fully considered in training with time-dependent signals. The batch process has the characteristics of non-linearity, multiple working conditions and multiple time periods. Hence, DBN does not perform well in batch process. For this purpose, a method based on the combination of Long Short-Term Memory (LSTM) network and Deep Belief Network (DBN) is proposed. The method first adopts the preprocessing method of variable expansion and continuous sampling, and then uses DBN-LSTM network for feature extraction, time correlation analysis, and fault diagnosis. This method is applied to a class of semiconductor etching process. The experimental results show that the proposed method can effectively extract time-ordered nonlinear fault features from the original batch process data and has high fault diagnosis accuracy.","PeriodicalId":353946,"journal":{"name":"2019 CAA Symposium on Fault Detection, Supervision and Safety for Technical Processes (SAFEPROCESS)","volume":"14 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":"121191238","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/SAFEPROCESS45799.2019.9213332
Li Zhao, Wei Li, Yajie Li, Yahong Shi
The co-design problem is studied for a class of nonlinear CPS under cyber attack, physical component failure and limited communication resources by introducing DETCS. Firstly, in the circumstances of cyber attack and physical component failure, the defense idea of active fault-tolerant combine with passive attack-tolerant is developed, and on the basis, a nonlinear CPS security control model is established that integrates trigger condition, actuator fault and cyber attack. Secondly, based on time delay system theory, the design of robust attack-tolerant observer which can estimate the being attack state and fault in real time, as well as a method of co-compute between fault-tolerant, attack-tolerant controller, the event trigger matrix are obtained respectively. Thus, the goals of active fault-tolerant, passive attack-tolerant control and the method of saving cyber communication resource are given. Finally, a simulation example is given to verify the effectiveness and feasibility of the theoretical research.
{"title":"Research on Co-Design between Security Control and Communication for a Class of Nonlinear CPS under Cyber Attack","authors":"Li Zhao, Wei Li, Yajie Li, Yahong Shi","doi":"10.1109/SAFEPROCESS45799.2019.9213332","DOIUrl":"https://doi.org/10.1109/SAFEPROCESS45799.2019.9213332","url":null,"abstract":"The co-design problem is studied for a class of nonlinear CPS under cyber attack, physical component failure and limited communication resources by introducing DETCS. Firstly, in the circumstances of cyber attack and physical component failure, the defense idea of active fault-tolerant combine with passive attack-tolerant is developed, and on the basis, a nonlinear CPS security control model is established that integrates trigger condition, actuator fault and cyber attack. Secondly, based on time delay system theory, the design of robust attack-tolerant observer which can estimate the being attack state and fault in real time, as well as a method of co-compute between fault-tolerant, attack-tolerant controller, the event trigger matrix are obtained respectively. Thus, the goals of active fault-tolerant, passive attack-tolerant control and the method of saving cyber communication resource are given. Finally, a simulation example is given to verify the effectiveness and feasibility of the theoretical research.","PeriodicalId":353946,"journal":{"name":"2019 CAA Symposium on Fault Detection, Supervision and Safety for Technical Processes (SAFEPROCESS)","volume":"48 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":"116098777","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/SAFEPROCESS45799.2019.9213445
Zhouxiao Xiao, H. Fang, Yang Chang
With the widespread application of lithium-ion batteries in industries around the world, lithium-ion battery performance degradation prediction and remaining useful life (RUL) estimation methods are receiving much more attention. This paper summarizes the nonlinear filtering algorithms used in RUL estimation of lithium-ion batteries, which compares and analyzes the applicable conditions and performance of the commonly used nonlinear filtering algorithms, including extended Kalman filtering (EKF), unscented Kalman filtering (UKF), particle filtering (PF), extended particle filtering (EPF) and unscented particle filtering(UPF). Simulations are obtained by lithium-ion battery performance degradation model and the performance of these algorithms are verified.
{"title":"Research on Remaining Useful Life Prediction Based on Nonlinear Filtering for Lithium-ion Battery","authors":"Zhouxiao Xiao, H. Fang, Yang Chang","doi":"10.1109/SAFEPROCESS45799.2019.9213445","DOIUrl":"https://doi.org/10.1109/SAFEPROCESS45799.2019.9213445","url":null,"abstract":"With the widespread application of lithium-ion batteries in industries around the world, lithium-ion battery performance degradation prediction and remaining useful life (RUL) estimation methods are receiving much more attention. This paper summarizes the nonlinear filtering algorithms used in RUL estimation of lithium-ion batteries, which compares and analyzes the applicable conditions and performance of the commonly used nonlinear filtering algorithms, including extended Kalman filtering (EKF), unscented Kalman filtering (UKF), particle filtering (PF), extended particle filtering (EPF) and unscented particle filtering(UPF). Simulations are obtained by lithium-ion battery performance degradation model and the performance of these algorithms are verified.","PeriodicalId":353946,"journal":{"name":"2019 CAA Symposium on Fault Detection, Supervision and Safety for Technical Processes (SAFEPROCESS)","volume":"87 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":"116562914","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/SAFEPROCESS45799.2019.9213264
K. Zhu, Chuanyu Zhang, N. Lu, B. Jiang
The remaining useful life (RUL) prediction of high-speed railway traction system is of great significance for ensuring the safe and efficient driving of high-speed railway trains. Due to the complex structure of high-speed railway traction system, it is difficult to reveal system-level degradation mechanism; thus, a data-driven RUL prediction method based on similarity of degradation features is proposed in this paper. The seq2seq structure of the Long Short Term Memory (LSTM) is adopted to extract the multivariate features of the degradation trajectory. Based on these features, a similarity-based RUL prediction method is utilized to compute the RUL of the system. Experiments are conducted on the semi-physical platform of the CRH2 traction system. Results can show that the proposed method can extract reasonable degradation features; and the prediction accuracy is greatly improved compared with several existing methods.
{"title":"Data-driven RUL Prediction of High-speed Railway Traction System Based on Similarity of Degradation Feature","authors":"K. Zhu, Chuanyu Zhang, N. Lu, B. Jiang","doi":"10.1109/SAFEPROCESS45799.2019.9213264","DOIUrl":"https://doi.org/10.1109/SAFEPROCESS45799.2019.9213264","url":null,"abstract":"The remaining useful life (RUL) prediction of high-speed railway traction system is of great significance for ensuring the safe and efficient driving of high-speed railway trains. Due to the complex structure of high-speed railway traction system, it is difficult to reveal system-level degradation mechanism; thus, a data-driven RUL prediction method based on similarity of degradation features is proposed in this paper. The seq2seq structure of the Long Short Term Memory (LSTM) is adopted to extract the multivariate features of the degradation trajectory. Based on these features, a similarity-based RUL prediction method is utilized to compute the RUL of the system. Experiments are conducted on the semi-physical platform of the CRH2 traction system. Results can show that the proposed method can extract reasonable degradation features; and the prediction accuracy is greatly improved compared with several existing methods.","PeriodicalId":353946,"journal":{"name":"2019 CAA Symposium on Fault Detection, Supervision and Safety for Technical Processes (SAFEPROCESS)","volume":"20 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":"123179482","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：