Pub Date : 2019-10-01DOI: 10.1109/phm-qingdao46334.2019.8942989
Long Zhang, Jiamin Wu, Rongzhen Wu, Canzhuang Zhen, Bing Lei
Fault recognition of rolling bearings is the basis of condition-based maintenance. Aiming at the non-stationarity and non-linearity of vibration signals emitted from defective bearings, a fault recognition method is proposed based on Empirical Mode Decomposition (EMD) and Self-Organizing Feature Maps (SOM) neural networks. Vibration signals are decomposed into a collection of IMFs (Intrinsic Mode Functions) by EMD, and then the energy features extracted from IMFs containing fault information are treated as input of SOM neural network. Various bearing health conditions involving different fault types and severity levels are identified by the SOM. Experimental results verified the effectiveness of the proposed method.
{"title":"Recognition of Rolling Bearing Based on EMD and SOM Neural Network","authors":"Long Zhang, Jiamin Wu, Rongzhen Wu, Canzhuang Zhen, Bing Lei","doi":"10.1109/phm-qingdao46334.2019.8942989","DOIUrl":"https://doi.org/10.1109/phm-qingdao46334.2019.8942989","url":null,"abstract":"Fault recognition of rolling bearings is the basis of condition-based maintenance. Aiming at the non-stationarity and non-linearity of vibration signals emitted from defective bearings, a fault recognition method is proposed based on Empirical Mode Decomposition (EMD) and Self-Organizing Feature Maps (SOM) neural networks. Vibration signals are decomposed into a collection of IMFs (Intrinsic Mode Functions) by EMD, and then the energy features extracted from IMFs containing fault information are treated as input of SOM neural network. Various bearing health conditions involving different fault types and severity levels are identified by the SOM. Experimental results verified the effectiveness of the proposed method.","PeriodicalId":259179,"journal":{"name":"2019 Prognostics and System Health Management Conference (PHM-Qingdao)","volume":"125 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2019-10-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"123725663","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 : 2019-10-01DOI: 10.1109/phm-qingdao46334.2019.8943052
M. Hailong, Li Zhen
A new prediction method is proposed based on relative features and support vector machine to estimate the bearing remaining life under limited data conditions. To eliminate the redundancy and relevance within features, principal component analysis (PCA) was applied to obtain the relative features, which could reflect the running states and degradation trends of bearings. Then, the relative features are input into the support vector machine. The bearing residual life prediction model is constructed based on the relative features and support vector machine. The field measured signals are used to verify the effective of the proposed method. The results show that the proposed prediction method can obtain accurate prediction results under small sample conditions.
{"title":"Remaining Life Predictions of Bearing Based on Relative Features and Support Vector Machine","authors":"M. Hailong, Li Zhen","doi":"10.1109/phm-qingdao46334.2019.8943052","DOIUrl":"https://doi.org/10.1109/phm-qingdao46334.2019.8943052","url":null,"abstract":"A new prediction method is proposed based on relative features and support vector machine to estimate the bearing remaining life under limited data conditions. To eliminate the redundancy and relevance within features, principal component analysis (PCA) was applied to obtain the relative features, which could reflect the running states and degradation trends of bearings. Then, the relative features are input into the support vector machine. The bearing residual life prediction model is constructed based on the relative features and support vector machine. The field measured signals are used to verify the effective of the proposed method. The results show that the proposed prediction method can obtain accurate prediction results under small sample conditions.","PeriodicalId":259179,"journal":{"name":"2019 Prognostics and System Health Management Conference (PHM-Qingdao)","volume":"34 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2019-10-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"121598375","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 : 2019-10-01DOI: 10.1109/phm-qingdao46334.2019.8943022
Yujie Zhang, Liansheng Liu, Datong Liu, Yu Peng
Electro-Mechanical Actuator (EMA) utilized in the flight control actuation is becoming more and more important in aerospace applications, especially for more electric aircraft. EMA Health Indicator (HI) extraction is challenging as the sensor installation is limited, which is a critical part of EMA Prognostics and Health Management (PHM). Model Reference Adaptive System (MRAS) is an effective parameter estimation method to extract HIs of Permanent Magnet Synchronous Motor (PMSM) of EMA, which can achieve high precision estimation with a small amount of calculation. However, the MRAS based HI extraction method is not suitable for stator resistance estimation of PMSM with Field-Oriented Control (FOC) strategy in which the expected d-axis current is zero. Hence, to deal with this problem, an improved MRAS is proposed for the HI extraction of stator resistance of EMA PMSM. In the proposed HI extraction method, the expected d-axis current of PMSM is set to a constant nearly zero, and the inputs of d-axis current of MRAS is substituted by the sum of a constant and d-axis current. Besides, the structure of adjustable model of MRAS is improved to cope with this sum. Furthermore, the estimated stator resistance based on improved MRAS, which is a useful HI for EMA PMSM, can be obtained. To evaluate the effectiveness of HI extraction method based on improved MRAS for EMA PMSM, two experiments are carried out using simulation data. The experimental results demonstrate that the improved MRAS based method is more suitable for HI extraction of EMA PMSM.
{"title":"Improved MRAS based HI extraction method for PMSM of Electro-Mechanical Actuator","authors":"Yujie Zhang, Liansheng Liu, Datong Liu, Yu Peng","doi":"10.1109/phm-qingdao46334.2019.8943022","DOIUrl":"https://doi.org/10.1109/phm-qingdao46334.2019.8943022","url":null,"abstract":"Electro-Mechanical Actuator (EMA) utilized in the flight control actuation is becoming more and more important in aerospace applications, especially for more electric aircraft. EMA Health Indicator (HI) extraction is challenging as the sensor installation is limited, which is a critical part of EMA Prognostics and Health Management (PHM). Model Reference Adaptive System (MRAS) is an effective parameter estimation method to extract HIs of Permanent Magnet Synchronous Motor (PMSM) of EMA, which can achieve high precision estimation with a small amount of calculation. However, the MRAS based HI extraction method is not suitable for stator resistance estimation of PMSM with Field-Oriented Control (FOC) strategy in which the expected d-axis current is zero. Hence, to deal with this problem, an improved MRAS is proposed for the HI extraction of stator resistance of EMA PMSM. In the proposed HI extraction method, the expected d-axis current of PMSM is set to a constant nearly zero, and the inputs of d-axis current of MRAS is substituted by the sum of a constant and d-axis current. Besides, the structure of adjustable model of MRAS is improved to cope with this sum. Furthermore, the estimated stator resistance based on improved MRAS, which is a useful HI for EMA PMSM, can be obtained. To evaluate the effectiveness of HI extraction method based on improved MRAS for EMA PMSM, two experiments are carried out using simulation data. The experimental results demonstrate that the improved MRAS based method is more suitable for HI extraction of EMA PMSM.","PeriodicalId":259179,"journal":{"name":"2019 Prognostics and System Health Management Conference (PHM-Qingdao)","volume":"13 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2019-10-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"127792379","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 : 2019-10-01DOI: 10.1109/phm-qingdao46334.2019.8942810
Mingyao Liu, Yubin Wu, Zechao Wang, Changrao Du, Zude Zhou
This paper proposes a novel method to detect the liquid level. Specifically, a novel structure based on the diagram and the flexible hinge is presented, in which the Fiber Bragg Grating (FBG) is employed as the sensing element and temperature compensation is considered. The corresponding analytical model of the structure is developed, which shows that the strain of the FBG is a linear correlation with the liquid level. The presented sensor show superior range (±200mm) and superior sensitivity (23.80pm/mm) when compared with some of the similar structures shown in the literature. To validate the analytical model, a Finite Element Model (FEM) is employed and the results showed that the analytical model is accurate. This paper aims to give the structure design and performance analysis for the sensor and the corresponding experiments will be given in our subsequent paper series Part II.
{"title":"A novel method to detect the liquid level based on the FBG sensor Part I: The structure design and performance analysis","authors":"Mingyao Liu, Yubin Wu, Zechao Wang, Changrao Du, Zude Zhou","doi":"10.1109/phm-qingdao46334.2019.8942810","DOIUrl":"https://doi.org/10.1109/phm-qingdao46334.2019.8942810","url":null,"abstract":"This paper proposes a novel method to detect the liquid level. Specifically, a novel structure based on the diagram and the flexible hinge is presented, in which the Fiber Bragg Grating (FBG) is employed as the sensing element and temperature compensation is considered. The corresponding analytical model of the structure is developed, which shows that the strain of the FBG is a linear correlation with the liquid level. The presented sensor show superior range (±200mm) and superior sensitivity (23.80pm/mm) when compared with some of the similar structures shown in the literature. To validate the analytical model, a Finite Element Model (FEM) is employed and the results showed that the analytical model is accurate. This paper aims to give the structure design and performance analysis for the sensor and the corresponding experiments will be given in our subsequent paper series Part II.","PeriodicalId":259179,"journal":{"name":"2019 Prognostics and System Health Management Conference (PHM-Qingdao)","volume":"7 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2019-10-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"126543480","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 : 2019-10-01DOI: 10.1109/phm-qingdao46334.2019.8942998
Xunjia Li, Zhang Tao, Kaiwen Li, Yajie Liu
Spacecraft telemetry data anomaly detection is crucial for the timely detection of potential malfunction in spacecraft systems. Because of the uncertainty of prediction, interval prediction models are more suitable for anomaly detection than point prediction and probability prediction. This paper first puts forward an anomaly detection framework based on the traditional LUBE model, and introduces a method to eliminate the error of the model itself in the framework of anomaly detection. Considering that the LUBE method judges the quality of the prediction interval, there are two indicators, interval width and interval coverage, which is essentially a multiobjective optimization problem. Therefore, this paper proposes a LUBE interval prediction model based on multi-objective optimization. Compared with the traditional model, the combination of the two indicators is obviously superior to the original method. Finally, the effectiveness is proved by anomaly detection experiments of public datasets and spacecraft telemetry data.
{"title":"Spacecraft Telemetry Data Anomaly Detection Based On Multi-objective Optimization Interval Prediction","authors":"Xunjia Li, Zhang Tao, Kaiwen Li, Yajie Liu","doi":"10.1109/phm-qingdao46334.2019.8942998","DOIUrl":"https://doi.org/10.1109/phm-qingdao46334.2019.8942998","url":null,"abstract":"Spacecraft telemetry data anomaly detection is crucial for the timely detection of potential malfunction in spacecraft systems. Because of the uncertainty of prediction, interval prediction models are more suitable for anomaly detection than point prediction and probability prediction. This paper first puts forward an anomaly detection framework based on the traditional LUBE model, and introduces a method to eliminate the error of the model itself in the framework of anomaly detection. Considering that the LUBE method judges the quality of the prediction interval, there are two indicators, interval width and interval coverage, which is essentially a multiobjective optimization problem. Therefore, this paper proposes a LUBE interval prediction model based on multi-objective optimization. Compared with the traditional model, the combination of the two indicators is obviously superior to the original method. Finally, the effectiveness is proved by anomaly detection experiments of public datasets and spacecraft telemetry data.","PeriodicalId":259179,"journal":{"name":"2019 Prognostics and System Health Management Conference (PHM-Qingdao)","volume":"29 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2019-10-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"126567806","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 : 2019-10-01DOI: 10.1109/phm-qingdao46334.2019.8942878
Waleed Bin Yousuf, Tariq Mairaj Rasool Khan, Sumayya Abbas, Muhammad Arslan Hashmi
Cables are the crucial component in the electrical distribution system. Aerial Bundled Cables (ABCs) is a combination of insulated phase conductors bundled tightly together. They have replaced conventional cables due to simplicity in installation and being less prone to pilferage. However insulation degradation is a very common problem with ABCs especially when subjected to coastal environments. Due to bundled structure, the moisture penetrates within the cables. During electrical loading of the cable, this moisture starts deteriorating the cable insulation which eventually results in the cable failure. Actual Non-Destructive Testing (NDT) data from the installed in-service cable is acquired at different time instants to study the phenomena of insulation degradation w.r.t. time. A Particle Filter (PF) based prognostic approach is proposed in this paper to predict the insulation degradation for future time instants so that the cable can be replaced before the failure occurs. The proposed method will help the electrical maintenance managers to plan the replacement activity well in time to ensure uninterruptible/smooth electrical supply.
{"title":"Prognostic Algorithm for Degradation Prediction of Aerial Bundled Cables in Coastal Areas","authors":"Waleed Bin Yousuf, Tariq Mairaj Rasool Khan, Sumayya Abbas, Muhammad Arslan Hashmi","doi":"10.1109/phm-qingdao46334.2019.8942878","DOIUrl":"https://doi.org/10.1109/phm-qingdao46334.2019.8942878","url":null,"abstract":"Cables are the crucial component in the electrical distribution system. Aerial Bundled Cables (ABCs) is a combination of insulated phase conductors bundled tightly together. They have replaced conventional cables due to simplicity in installation and being less prone to pilferage. However insulation degradation is a very common problem with ABCs especially when subjected to coastal environments. Due to bundled structure, the moisture penetrates within the cables. During electrical loading of the cable, this moisture starts deteriorating the cable insulation which eventually results in the cable failure. Actual Non-Destructive Testing (NDT) data from the installed in-service cable is acquired at different time instants to study the phenomena of insulation degradation w.r.t. time. A Particle Filter (PF) based prognostic approach is proposed in this paper to predict the insulation degradation for future time instants so that the cable can be replaced before the failure occurs. The proposed method will help the electrical maintenance managers to plan the replacement activity well in time to ensure uninterruptible/smooth electrical supply.","PeriodicalId":259179,"journal":{"name":"2019 Prognostics and System Health Management Conference (PHM-Qingdao)","volume":"33 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2019-10-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"121731909","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}
Gas turbine engines have been the key power machine for energy conversion & utilization in the 21st century efficiently and cleanly. To improve equipment reliability and availability, prolong service life and reduce O&M costs, gas path component diagnosis is an effective technique for detecting evolving deterioration. Although many diagnostic methods based on steady state or quasi-steady state have been obtained, but no complete scientific system of gas-path diagnosis has been formed yet. Aiming at the above problems, a research route of gas-path component fault diagnosis for gas turbine engine is proposed. The proposed research route provides a new solution for diagnosis for complex nonlinear thermodynamic systems.
{"title":"Gas-path Component Fault Diagnosis for Gas Turbine Engine: A Review","authors":"Jian Chen, Chao Xu, Yulong Ying, Jingchao Li, Yaofei Jin, Hongyu Zhou, Yun Lin, Bin Zhang","doi":"10.1109/phm-qingdao46334.2019.8942819","DOIUrl":"https://doi.org/10.1109/phm-qingdao46334.2019.8942819","url":null,"abstract":"Gas turbine engines have been the key power machine for energy conversion & utilization in the 21st century efficiently and cleanly. To improve equipment reliability and availability, prolong service life and reduce O&M costs, gas path component diagnosis is an effective technique for detecting evolving deterioration. Although many diagnostic methods based on steady state or quasi-steady state have been obtained, but no complete scientific system of gas-path diagnosis has been formed yet. Aiming at the above problems, a research route of gas-path component fault diagnosis for gas turbine engine is proposed. The proposed research route provides a new solution for diagnosis for complex nonlinear thermodynamic systems.","PeriodicalId":259179,"journal":{"name":"2019 Prognostics and System Health Management Conference (PHM-Qingdao)","volume":"17 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2019-10-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"131361940","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 : 2019-10-01DOI: 10.1109/phm-qingdao46334.2019.8943024
Lei Liu, D. Song, Weihua Zhang
Axle box bearing a very vulnerable mechanical component because of its heavy load and unpleasant working environment. Once a fault occurs, it will develop rapidly and seriously threaten the safety of train operation. Therefore, fault pattern recognition of axle box bearing is of great significance. The traditional diagnosis method of axle box bearing is based on vibration signal processing technology and trackside acoustic diagnosis, while the axle box bearing of high-speed EMU in China has not been equipped with acceleration sensors and not every line has been equipped with trackside acoustic diagnosis equipment. Therefore, this paper establishes a fault pattern recognition method based on onboard real-time temperature data of axle box bearing, which can effectively recognize the abnormal condition of a high-speed EMU axle box bearing or an axle box bearing sensor failure.
{"title":"Fault Pattern Recognition of Axle Box Bearings for High-speed EMU Based on Onboard Real-time Temperature Data","authors":"Lei Liu, D. Song, Weihua Zhang","doi":"10.1109/phm-qingdao46334.2019.8943024","DOIUrl":"https://doi.org/10.1109/phm-qingdao46334.2019.8943024","url":null,"abstract":"Axle box bearing a very vulnerable mechanical component because of its heavy load and unpleasant working environment. Once a fault occurs, it will develop rapidly and seriously threaten the safety of train operation. Therefore, fault pattern recognition of axle box bearing is of great significance. The traditional diagnosis method of axle box bearing is based on vibration signal processing technology and trackside acoustic diagnosis, while the axle box bearing of high-speed EMU in China has not been equipped with acceleration sensors and not every line has been equipped with trackside acoustic diagnosis equipment. Therefore, this paper establishes a fault pattern recognition method based on onboard real-time temperature data of axle box bearing, which can effectively recognize the abnormal condition of a high-speed EMU axle box bearing or an axle box bearing sensor failure.","PeriodicalId":259179,"journal":{"name":"2019 Prognostics and System Health Management Conference (PHM-Qingdao)","volume":"27 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2019-10-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"131372195","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 : 2019-10-01DOI: 10.1109/phm-qingdao46334.2019.8943020
Chenyu Xiao, Ming Yu, Xin Liu, Xiaozheng Jin, Canghua Jiang
This paper deals with distributed fault estimation of complex system using bond graph and improved biogeography- based optimization. Firstly, a system decomposition method is used where the complex system is decomposed into several minimal subsystems. Then, distributed analytical redundancy relations and distributed fault signature matrix derived from subsystems diagnostic bond graphs are used for distributed fault detection and isolation respectively. When a set of possible faults are obtained through distributed fault isolation, an improved biogeography-based optimization is proposed for distributed fault estimation. Finally, taking a complex circuit system as an example, numerical simulations are performed to illustrate the effectiveness of the developed method.
{"title":"Distributed Fault Estimation of Complex System Using Improved Biogeography-Based Optimization","authors":"Chenyu Xiao, Ming Yu, Xin Liu, Xiaozheng Jin, Canghua Jiang","doi":"10.1109/phm-qingdao46334.2019.8943020","DOIUrl":"https://doi.org/10.1109/phm-qingdao46334.2019.8943020","url":null,"abstract":"This paper deals with distributed fault estimation of complex system using bond graph and improved biogeography- based optimization. Firstly, a system decomposition method is used where the complex system is decomposed into several minimal subsystems. Then, distributed analytical redundancy relations and distributed fault signature matrix derived from subsystems diagnostic bond graphs are used for distributed fault detection and isolation respectively. When a set of possible faults are obtained through distributed fault isolation, an improved biogeography-based optimization is proposed for distributed fault estimation. Finally, taking a complex circuit system as an example, numerical simulations are performed to illustrate the effectiveness of the developed method.","PeriodicalId":259179,"journal":{"name":"2019 Prognostics and System Health Management Conference (PHM-Qingdao)","volume":"125 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2019-10-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"134428365","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 : 2019-10-01DOI: 10.1109/phm-qingdao46334.2019.8942911
Xuejie Cao, Liujing Xiong, Gang Niu
High-speed train dual-channel speed sensors are often influenced by factors like dusts, vibration, temperature changes, which easily cause false or miss alarm, even wrong isolation. The experimental comparison method commonly used in practical engineering, this method cannot detect faults in time or accurately isolate multiple faults. In this paper, a novel fault detection and isolation (FDI) scheme for dual-channel speed sensors is proposed by using the improved principal component analysis (PCA) and the improved reconstruction-based contribution plots (IRBCP). Take the dual-channel speed sensor of high-speed train as an example, experimental results show that the proposed scheme can satisfy FDI requirements of speed sensors, and is accurate and effective.
{"title":"A Fault Detection and Isolation Scheme for Dual-channel Speed Sensors","authors":"Xuejie Cao, Liujing Xiong, Gang Niu","doi":"10.1109/phm-qingdao46334.2019.8942911","DOIUrl":"https://doi.org/10.1109/phm-qingdao46334.2019.8942911","url":null,"abstract":"High-speed train dual-channel speed sensors are often influenced by factors like dusts, vibration, temperature changes, which easily cause false or miss alarm, even wrong isolation. The experimental comparison method commonly used in practical engineering, this method cannot detect faults in time or accurately isolate multiple faults. In this paper, a novel fault detection and isolation (FDI) scheme for dual-channel speed sensors is proposed by using the improved principal component analysis (PCA) and the improved reconstruction-based contribution plots (IRBCP). Take the dual-channel speed sensor of high-speed train as an example, experimental results show that the proposed scheme can satisfy FDI requirements of speed sensors, and is accurate and effective.","PeriodicalId":259179,"journal":{"name":"2019 Prognostics and System Health Management Conference (PHM-Qingdao)","volume":"25 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2019-10-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"130734500","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：