Pub Date : 2019-10-01DOI: 10.1109/phm-qingdao46334.2019.8942951
Mengling Wu, Gang Liu, Jinjun Lu, Xiaofeng Geng
Speed sensors installed on the axes of high-speed train will lead to faults due to the vibration and electromagnetic interference during train operation. At present the braking system can't detect all faults of speed sensor but misdirect the axle lock fault, which affects the safety of train operation. Therefore, this paper proposes an integral intelligent fault diagnosis method for speed sensor of high-speed train brake system, which realizes real-time detection of speed sensor anomalies and accurate location of the axis of the speed sensor fault. Firstly, the traditional principal component analysis method is improved by proposing a comprehensive monitoring statistic to realize real-time fault detection of speed sensor. Then, the modified reconstruction based contribution plot based on the idea of combination maximization is adopted to achieve accurate fault location of speed sensor. In addition, the fault injection experiments are conducted, the results prove the method can diagnose the fault of speed sensor accurately and effectively, and solve the hidden trouble of high-speed train operation.
{"title":"Research on Fault Diagnosis Method for Speed Sensor of High-Speed Train","authors":"Mengling Wu, Gang Liu, Jinjun Lu, Xiaofeng Geng","doi":"10.1109/phm-qingdao46334.2019.8942951","DOIUrl":"https://doi.org/10.1109/phm-qingdao46334.2019.8942951","url":null,"abstract":"Speed sensors installed on the axes of high-speed train will lead to faults due to the vibration and electromagnetic interference during train operation. At present the braking system can't detect all faults of speed sensor but misdirect the axle lock fault, which affects the safety of train operation. Therefore, this paper proposes an integral intelligent fault diagnosis method for speed sensor of high-speed train brake system, which realizes real-time detection of speed sensor anomalies and accurate location of the axis of the speed sensor fault. Firstly, the traditional principal component analysis method is improved by proposing a comprehensive monitoring statistic to realize real-time fault detection of speed sensor. Then, the modified reconstruction based contribution plot based on the idea of combination maximization is adopted to achieve accurate fault location of speed sensor. In addition, the fault injection experiments are conducted, the results prove the method can diagnose the fault of speed sensor accurately and effectively, and solve the hidden trouble of high-speed train operation.","PeriodicalId":259179,"journal":{"name":"2019 Prognostics and System Health Management Conference (PHM-Qingdao)","volume":"11 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":"121223354","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-qingdao46334.2019.8942896
Wen Jia, Luo Haimin, W. Xiao
a hierarchical PHM (Prognostic and Health Management) architecture divided into subsystem-level and system-level is proposed with its functions and interfaces at various levels to satisfy PHM requirements of the integrated modular mission system. At the subsystem level, integrated condition monitoring method is developed to monitor the operational conditions of various modules, data buses and functional applications according to their characteristics and requirements. At the system level, a MBR (Model-based Reasoning) engine and its diagnostic knowledge model are developed for the integrated PHM data processing, and a graphical PHM display-control interface and a PHM database are designed to display and store PHM data centrally. The overall design method is applied on a project of the scout’s integrated modular mission system and a PHM subsystem is developed, which can provide integrated health condition monitoring and accurate fault diagnosis for the mission system, as well as the real-time and comprehensive health information for pilot and maintenance personnel.
{"title":"Application and Design of PHM in Aircraft’s Integrated Modular Mission System","authors":"Wen Jia, Luo Haimin, W. Xiao","doi":"10.1109/phm-qingdao46334.2019.8942896","DOIUrl":"https://doi.org/10.1109/phm-qingdao46334.2019.8942896","url":null,"abstract":"a hierarchical PHM (Prognostic and Health Management) architecture divided into subsystem-level and system-level is proposed with its functions and interfaces at various levels to satisfy PHM requirements of the integrated modular mission system. At the subsystem level, integrated condition monitoring method is developed to monitor the operational conditions of various modules, data buses and functional applications according to their characteristics and requirements. At the system level, a MBR (Model-based Reasoning) engine and its diagnostic knowledge model are developed for the integrated PHM data processing, and a graphical PHM display-control interface and a PHM database are designed to display and store PHM data centrally. The overall design method is applied on a project of the scout’s integrated modular mission system and a PHM subsystem is developed, which can provide integrated health condition monitoring and accurate fault diagnosis for the mission system, as well as the real-time and comprehensive health information for pilot and maintenance personnel.","PeriodicalId":259179,"journal":{"name":"2019 Prognostics and System Health Management Conference (PHM-Qingdao)","volume":"47 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":"122377392","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-qingdao46334.2019.8942872
M. Zan, Wang Peng, L. Ruihua, Huang Jianbo
The failure detection of the GNSS airborne system can reduce the navigation and positioning failure rate of the GNSS airborne system. While, it takes more longer time to complete the failure detection by traditional failure detection model. Therefore, a novel failure detection model of the GNSS airborne system has been considered and developed by differential equation of gray theory to predict the next arrival time of the heartbeat message when GNSS fails. Furthermore, the reliable message communication can be realized through the prediction result, and failure judgment of the GNSS airborne system, which is defined and utilized as the preliminary judgment basis, can be carried out. Then, the failure detection model of the GNSS airborne system is established in basis on combination logic between rumor heartbeat realization mode and monitoring heartbeat realization mode. Finally the proposed model in this present paper had been simulated and proved the shortest response time, which proves the performance of the model.
{"title":"A Quick-response Failure Detection Model of GNSS Airborne System","authors":"M. Zan, Wang Peng, L. Ruihua, Huang Jianbo","doi":"10.1109/phm-qingdao46334.2019.8942872","DOIUrl":"https://doi.org/10.1109/phm-qingdao46334.2019.8942872","url":null,"abstract":"The failure detection of the GNSS airborne system can reduce the navigation and positioning failure rate of the GNSS airborne system. While, it takes more longer time to complete the failure detection by traditional failure detection model. Therefore, a novel failure detection model of the GNSS airborne system has been considered and developed by differential equation of gray theory to predict the next arrival time of the heartbeat message when GNSS fails. Furthermore, the reliable message communication can be realized through the prediction result, and failure judgment of the GNSS airborne system, which is defined and utilized as the preliminary judgment basis, can be carried out. Then, the failure detection model of the GNSS airborne system is established in basis on combination logic between rumor heartbeat realization mode and monitoring heartbeat realization mode. Finally the proposed model in this present paper had been simulated and proved the shortest response time, which proves the performance of the model.","PeriodicalId":259179,"journal":{"name":"2019 Prognostics and System Health Management Conference (PHM-Qingdao)","volume":"1 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":"116461968","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-qingdao46334.2019.8943040
Bingjun Guo, Lei Song, Taisheng Zheng, Haoran Liang, Hongfei Wang
Anomaly detection for multivariate data is of vital importance in academic research and industry. In real scenes, there is usually a lack of labels of anomalies. Self-Organizing Map (SOM) can map data to the output layer and maintain the original topology, which has been used as a semi-supervised learning method to solve the above problem. In this paper, we first explain the mechanism of classic SOM for anomaly detection, then compare it with two variants of SOM named kernel SOM and K-BMUs SOM. Kernel SOM replaces Euclidean distance with kernel functions, while K-BMUs SOM changes the number of matching neurons. The three types of SOM are applied to multivariate datasets in three different domains. We find that the performance of the three SOM-based methods is related to the characteristics of data.
{"title":"A Comparative Evaluation of SOM-based Anomaly Detection Methods for Multivariate Data","authors":"Bingjun Guo, Lei Song, Taisheng Zheng, Haoran Liang, Hongfei Wang","doi":"10.1109/phm-qingdao46334.2019.8943040","DOIUrl":"https://doi.org/10.1109/phm-qingdao46334.2019.8943040","url":null,"abstract":"Anomaly detection for multivariate data is of vital importance in academic research and industry. In real scenes, there is usually a lack of labels of anomalies. Self-Organizing Map (SOM) can map data to the output layer and maintain the original topology, which has been used as a semi-supervised learning method to solve the above problem. In this paper, we first explain the mechanism of classic SOM for anomaly detection, then compare it with two variants of SOM named kernel SOM and K-BMUs SOM. Kernel SOM replaces Euclidean distance with kernel functions, while K-BMUs SOM changes the number of matching neurons. The three types of SOM are applied to multivariate datasets in three different domains. We find that the performance of the three SOM-based methods is related to the characteristics of data.","PeriodicalId":259179,"journal":{"name":"2019 Prognostics and System Health Management Conference (PHM-Qingdao)","volume":"63 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":"126630853","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-qingdao46334.2019.8942871
Guangqi Qiu, Yingkui Gu
A methodology for developing dynamic diagnosis of multi-state degradation system was proposed in this paper. Wavelet packet energy entropy was employed to characterize the uncertainty and complexity of the signal. Current state evaluation and multi-state recognition had been implemented by hidden Markov model. The recognition performance was verified by a bearing vibration experiment, and the effects of decomposition levels and wavelet mother functions on the recognition performance were taken into account. Compared with classifiers of K-means, BP neural networks (BP-NN) and support vector machine (SVM), hidden Markov model (HMM) achieved a better recognition performance for multi-state degradation system and provided theoretical explanation of the system failure evolution.
{"title":"Dynamic Diagnosis Approach of Multi-state Degradation System Using Hidden Markov Model","authors":"Guangqi Qiu, Yingkui Gu","doi":"10.1109/phm-qingdao46334.2019.8942871","DOIUrl":"https://doi.org/10.1109/phm-qingdao46334.2019.8942871","url":null,"abstract":"A methodology for developing dynamic diagnosis of multi-state degradation system was proposed in this paper. Wavelet packet energy entropy was employed to characterize the uncertainty and complexity of the signal. Current state evaluation and multi-state recognition had been implemented by hidden Markov model. The recognition performance was verified by a bearing vibration experiment, and the effects of decomposition levels and wavelet mother functions on the recognition performance were taken into account. Compared with classifiers of K-means, BP neural networks (BP-NN) and support vector machine (SVM), hidden Markov model (HMM) achieved a better recognition performance for multi-state degradation system and provided theoretical explanation of the system failure evolution.","PeriodicalId":259179,"journal":{"name":"2019 Prognostics and System Health Management Conference (PHM-Qingdao)","volume":"55 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":"126896146","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-qingdao46334.2019.8942949
Xueyi Li, Jialin Li, Chengying Zhao, Yongzhi Qu, D. He
The early gear pitting fault diagnosis has received much attention in the industry. In recent decades, with the popularity growth of artificial neural network, researchers have applied deep learning methods to figure out early gear pitting faults. However, the classical fault diagnosis methods usually use deep neural networks according to the time sequence of the collected signals. In this case, the feature extraction in the direction of the inverse time-domain signals is usually ignored. Aimed at overcoming this shortage, ground on a traditional Long Short Term Memory (LSTM) network, this paper proposes a Bidirectional LSTM (Bi-LSTM) to construct a fault diagnosis model of early gear pitting using raw vibration signals. Using the Bi-LSTM network, feature extraction of the vibrational signals in both directions is simultaneously carried out to evaluate the degree of the early gear pitting faults to better extract the gear pitting characteristics from the raw vibration signals of the gear. Through the analysis of the experimental data, compared with the traditional LSTM model, the Bi-directional LSTM has a classification accuracy of over 96% for early gear pitting fault diagnosis, which is an increase of 4.1%.
{"title":"Early Gear Pitting Fault Diagnosis Based on Bi-directional LSTM","authors":"Xueyi Li, Jialin Li, Chengying Zhao, Yongzhi Qu, D. He","doi":"10.1109/phm-qingdao46334.2019.8942949","DOIUrl":"https://doi.org/10.1109/phm-qingdao46334.2019.8942949","url":null,"abstract":"The early gear pitting fault diagnosis has received much attention in the industry. In recent decades, with the popularity growth of artificial neural network, researchers have applied deep learning methods to figure out early gear pitting faults. However, the classical fault diagnosis methods usually use deep neural networks according to the time sequence of the collected signals. In this case, the feature extraction in the direction of the inverse time-domain signals is usually ignored. Aimed at overcoming this shortage, ground on a traditional Long Short Term Memory (LSTM) network, this paper proposes a Bidirectional LSTM (Bi-LSTM) to construct a fault diagnosis model of early gear pitting using raw vibration signals. Using the Bi-LSTM network, feature extraction of the vibrational signals in both directions is simultaneously carried out to evaluate the degree of the early gear pitting faults to better extract the gear pitting characteristics from the raw vibration signals of the gear. Through the analysis of the experimental data, compared with the traditional LSTM model, the Bi-directional LSTM has a classification accuracy of over 96% for early gear pitting fault diagnosis, which is an increase of 4.1%.","PeriodicalId":259179,"journal":{"name":"2019 Prognostics and System Health Management Conference (PHM-Qingdao)","volume":"22 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":"127758380","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-qingdao46334.2019.8942987
Wang Yang, Dequan Yu, Taisheng Zheng, Wenbo Wu, Zhenxiang Li, Hongyong Fu
As equipment becomes more and more complex, it is increasingly difficult to manually extract and select fault features manually based on expert experience or signal processing techniques. In addition, the shallow model such as BP neural network and SVM have trouble to deal with the complex mapping relationship with respect to the measured signal and the health condition of the equipment, who faces the problem of dimensional disaster. Combined with the advantages of deep confidence network (DBN) in features extraction and deal with high-dimensional and nonlinear samples, a fault feature extraction and diagnosis method based on deep confidence network for gearbox is investigated in this framework. The method uses the original time domain signal to train the deep confidence network and completes the intelligent diagnosis through deep learning. The preponderance is that it can take out the dependence on a great quantity of signal processing techniques and diagnostic experience, and accomplish the extraction of fault features and the intelligent diagnosis of health status with the characteristic of self-adaption. The method has no periodic requirements for time domain signals, and has strong versatility and adaptability. The experimental results of the fault diagnosis for the planetary gearbox demonstrated the feasibility and superiority of the presented method.
{"title":"Fault Diagnosis For Gearbox Based On Deep Belief Network","authors":"Wang Yang, Dequan Yu, Taisheng Zheng, Wenbo Wu, Zhenxiang Li, Hongyong Fu","doi":"10.1109/phm-qingdao46334.2019.8942987","DOIUrl":"https://doi.org/10.1109/phm-qingdao46334.2019.8942987","url":null,"abstract":"As equipment becomes more and more complex, it is increasingly difficult to manually extract and select fault features manually based on expert experience or signal processing techniques. In addition, the shallow model such as BP neural network and SVM have trouble to deal with the complex mapping relationship with respect to the measured signal and the health condition of the equipment, who faces the problem of dimensional disaster. Combined with the advantages of deep confidence network (DBN) in features extraction and deal with high-dimensional and nonlinear samples, a fault feature extraction and diagnosis method based on deep confidence network for gearbox is investigated in this framework. The method uses the original time domain signal to train the deep confidence network and completes the intelligent diagnosis through deep learning. The preponderance is that it can take out the dependence on a great quantity of signal processing techniques and diagnostic experience, and accomplish the extraction of fault features and the intelligent diagnosis of health status with the characteristic of self-adaption. The method has no periodic requirements for time domain signals, and has strong versatility and adaptability. The experimental results of the fault diagnosis for the planetary gearbox demonstrated the feasibility and superiority of the presented method.","PeriodicalId":259179,"journal":{"name":"2019 Prognostics and System Health Management Conference (PHM-Qingdao)","volume":"31 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":"127778312","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-qingdao46334.2019.8942966
H. Chang
There are many ways to evaluate the performance of a five-axis machine tool, but an evaluation can be performed using a recognizable multi-type comparison, and it the most practical is the recognizable performance evaluation (RPE). The RPE is one of the current research methods that can derive accurate reference data in a quantitative and recognizable way and is one of the evaluation methods for multi-type five axis machine tool models. Therefore, based on the RPE and the interface of the IT level distribution in the general mechanical design change, this paper attempts to introduce fuzzy theory to obtain exceptional research results.This study calculates the attribution degree of the tested items. A direct discriminant defuzzification attribution degree drop interval is provided to manage the conflicts in the retested performance evaluation of various types of five-axis machine tools. It is possible to directly evaluate the predicted results. The experimental results show that the interval of the interval is 2σ. This result, for the quantifiable performance evaluation, further distinguishes the landing interval.
{"title":"Performance Evaluation of Multi-type Five-axis Machine Tool With Recognizable Performance Evaluation by Fuzzy Theory","authors":"H. Chang","doi":"10.1109/phm-qingdao46334.2019.8942966","DOIUrl":"https://doi.org/10.1109/phm-qingdao46334.2019.8942966","url":null,"abstract":"There are many ways to evaluate the performance of a five-axis machine tool, but an evaluation can be performed using a recognizable multi-type comparison, and it the most practical is the recognizable performance evaluation (RPE). The RPE is one of the current research methods that can derive accurate reference data in a quantitative and recognizable way and is one of the evaluation methods for multi-type five axis machine tool models. Therefore, based on the RPE and the interface of the IT level distribution in the general mechanical design change, this paper attempts to introduce fuzzy theory to obtain exceptional research results.This study calculates the attribution degree of the tested items. A direct discriminant defuzzification attribution degree drop interval is provided to manage the conflicts in the retested performance evaluation of various types of five-axis machine tools. It is possible to directly evaluate the predicted results. The experimental results show that the interval of the interval is 2σ. This result, for the quantifiable performance evaluation, further distinguishes the landing interval.","PeriodicalId":259179,"journal":{"name":"2019 Prognostics and System Health Management Conference (PHM-Qingdao)","volume":"30 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":"129092908","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-qingdao46334.2019.8942948
Yajing Zhu, Zhinong Li, Jingzhi Tu
The traditional source number estimation method must ensure that the signal sources are independent and noise-free interference. Based on the above deficiency in the traditional BSS method, combining variational Bayesian hidden Markov model (VbHMM) and autocorrelation determination (ARD), a estimation method of mechanical fault sources number based on VbHMM is proposed. In the proposed method, after the Bayesian networks are introduced, the Markov models (HMM) is used to capture the characteristics of a series of time-related time series information in the dynamic and nonlinear signals. The optimal number of hidden sources in the non-stationary signal is deduced by the unique model comparison function of Bayesian inference and autocorrelation determination (ARD). Simulation and experimental results verify the effectiveness of the proposed method.
{"title":"Research on Estimation Method of Mechanical Fault Source Number Based on VbHMM","authors":"Yajing Zhu, Zhinong Li, Jingzhi Tu","doi":"10.1109/phm-qingdao46334.2019.8942948","DOIUrl":"https://doi.org/10.1109/phm-qingdao46334.2019.8942948","url":null,"abstract":"The traditional source number estimation method must ensure that the signal sources are independent and noise-free interference. Based on the above deficiency in the traditional BSS method, combining variational Bayesian hidden Markov model (VbHMM) and autocorrelation determination (ARD), a estimation method of mechanical fault sources number based on VbHMM is proposed. In the proposed method, after the Bayesian networks are introduced, the Markov models (HMM) is used to capture the characteristics of a series of time-related time series information in the dynamic and nonlinear signals. The optimal number of hidden sources in the non-stationary signal is deduced by the unique model comparison function of Bayesian inference and autocorrelation determination (ARD). Simulation and experimental results verify the effectiveness of the proposed method.","PeriodicalId":259179,"journal":{"name":"2019 Prognostics and System Health Management Conference (PHM-Qingdao)","volume":"10 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":"129184613","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-qingdao46334.2019.8942936
F. Chu, Xu Wang, Wei Zhang, Zheng-wei Yang, Yanping Cai
Diesel engine is a kind of power machinery equipment and widely used in industrial and agricultural production. Aiming at the difficulty in fault feature extraction of diesel engine, a visualized method based on the texture enhanced block non-negative matrix factorization (TE-BNMF) is proposed. The method firstly performs time-frequency analysis on the collected cylinder head vibration signals; then the local binary pattern (LBP) method is used to re-encode the vibration spectrum based on the gray distribution. After that, we use block non-negative matrix factorization algorithm (BNMF) to directly extract the feature parameters of the generated local binary feature map. By using a classifier to perform pattern recognition on the above-mentioned coding matrix, the automatic diagnosis of diesel engine faults is achieved. This method was applied to the fault diagnosis of 6 typical operating conditions of diesel engines, which can get high and stable fault recognition accuracy. The experiments show that the TE-BNMF diesel engine visualized fault diagnosis method proposed in this paper can discovery rich information contained in the spectrum image of diesel engine vibration deeply and diagnose the valve clearance fault of the diesel engine adaptively.
{"title":"Visualized Feature Extraction Method of Diesel Engine Based on Texture Enhanced Block NMF (TE-BNMF)","authors":"F. Chu, Xu Wang, Wei Zhang, Zheng-wei Yang, Yanping Cai","doi":"10.1109/phm-qingdao46334.2019.8942936","DOIUrl":"https://doi.org/10.1109/phm-qingdao46334.2019.8942936","url":null,"abstract":"Diesel engine is a kind of power machinery equipment and widely used in industrial and agricultural production. Aiming at the difficulty in fault feature extraction of diesel engine, a visualized method based on the texture enhanced block non-negative matrix factorization (TE-BNMF) is proposed. The method firstly performs time-frequency analysis on the collected cylinder head vibration signals; then the local binary pattern (LBP) method is used to re-encode the vibration spectrum based on the gray distribution. After that, we use block non-negative matrix factorization algorithm (BNMF) to directly extract the feature parameters of the generated local binary feature map. By using a classifier to perform pattern recognition on the above-mentioned coding matrix, the automatic diagnosis of diesel engine faults is achieved. This method was applied to the fault diagnosis of 6 typical operating conditions of diesel engines, which can get high and stable fault recognition accuracy. The experiments show that the TE-BNMF diesel engine visualized fault diagnosis method proposed in this paper can discovery rich information contained in the spectrum image of diesel engine vibration deeply and diagnose the valve clearance fault of the diesel engine adaptively.","PeriodicalId":259179,"journal":{"name":"2019 Prognostics and System Health Management Conference (PHM-Qingdao)","volume":"1 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":"130476090","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：