Pub Date : 2019-10-01DOI: 10.1109/phm-qingdao46334.2019.8942888
Bingxiu Guo, Xiaohui Wang, Yanyan Wang, Haoyun Su, Sijian Chao
Rubber is widely used in aviation, aerospace and other important fields. Monitoring properties of rubber and predicting its remaining life is the key to ensuring timely repair and replacement, and it is related to the safety and reliability of equipment. The traditional methods of life calculation is limited by the study of environment and mechanism. The data-driven is more concise and efficient and it can characterize the coupling effect of many factors for the life of rubber. Support Vector Machine (SVM) is a data-driven method for solving small sample and nonlinear problems with good robustness. In this paper the support vector regression(SVR) algorithm was applied to the prediction of rubber life. We used a certain type Polymerized Styrene Butadiene Rubber cable insulation as an example, the temperature and the concentration of oil mist were set as the features to predict the remaining life. The model was trained by accelerated aging test data, and its remaining life was calculated according to its break elongation retention rate at the end of life. Compared with the actual test results and the pridicted results of linear regression model, the applicability of the method was discussed.
{"title":"Application of Support Vector Regression to predict the Remaining useful life of Polymerized Styrene Butadiene Rubber of cable insulation","authors":"Bingxiu Guo, Xiaohui Wang, Yanyan Wang, Haoyun Su, Sijian Chao","doi":"10.1109/phm-qingdao46334.2019.8942888","DOIUrl":"https://doi.org/10.1109/phm-qingdao46334.2019.8942888","url":null,"abstract":"Rubber is widely used in aviation, aerospace and other important fields. Monitoring properties of rubber and predicting its remaining life is the key to ensuring timely repair and replacement, and it is related to the safety and reliability of equipment. The traditional methods of life calculation is limited by the study of environment and mechanism. The data-driven is more concise and efficient and it can characterize the coupling effect of many factors for the life of rubber. Support Vector Machine (SVM) is a data-driven method for solving small sample and nonlinear problems with good robustness. In this paper the support vector regression(SVR) algorithm was applied to the prediction of rubber life. We used a certain type Polymerized Styrene Butadiene Rubber cable insulation as an example, the temperature and the concentration of oil mist were set as the features to predict the remaining life. The model was trained by accelerated aging test data, and its remaining life was calculated according to its break elongation retention rate at the end of life. Compared with the actual test results and the pridicted results of linear regression model, the applicability of the method was discussed.","PeriodicalId":259179,"journal":{"name":"2019 Prognostics and System Health Management Conference (PHM-Qingdao)","volume":"58 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":"131192542","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-qingdao46334.2019.8942976
Liang Tang, Shunong Zhang, Xuesong Yang, Shuli Hu
Prognostics and health management (PHM) technology has been successfully applied in many complex equipment. However, with the equipment becoming more and more complex, the working conditions changing with time, and the equipment status information increasing, it is difficult by traditional technologies to cope with the new situation and new application scenarios. The application of deep learning method in many fields proves the ability of this method to deal with massive and complex data. In this paper, the special recurrent neural networks (RNN) called long-short term memory (LSTM) network are used to estimate the remaining life of engines with the data of PHM08 Challenge Competition. First, standardize the original data and add life labels in the data preprocessing stage. Then the influences of different data input methods on the prediction results are studied, and the results show that proper method is to input all the time series information at one time. The over-fitting phenomenon can be reduced to some extent by reducing the complexity of the neural network. Thus, a remaining life prediction method based on multi-dimensional data is obtained. The final result was uploaded to the competition’s scoring system and got good results, which confirmed the accuracy of this method. Therefore, the article summarizes a highly accurate LSTM-based multidimensional data failure prediction method.
{"title":"Research on Prognosis for Engines by LSTM Deep Learning Method","authors":"Liang Tang, Shunong Zhang, Xuesong Yang, Shuli Hu","doi":"10.1109/phm-qingdao46334.2019.8942976","DOIUrl":"https://doi.org/10.1109/phm-qingdao46334.2019.8942976","url":null,"abstract":"Prognostics and health management (PHM) technology has been successfully applied in many complex equipment. However, with the equipment becoming more and more complex, the working conditions changing with time, and the equipment status information increasing, it is difficult by traditional technologies to cope with the new situation and new application scenarios. The application of deep learning method in many fields proves the ability of this method to deal with massive and complex data. In this paper, the special recurrent neural networks (RNN) called long-short term memory (LSTM) network are used to estimate the remaining life of engines with the data of PHM08 Challenge Competition. First, standardize the original data and add life labels in the data preprocessing stage. Then the influences of different data input methods on the prediction results are studied, and the results show that proper method is to input all the time series information at one time. The over-fitting phenomenon can be reduced to some extent by reducing the complexity of the neural network. Thus, a remaining life prediction method based on multi-dimensional data is obtained. The final result was uploaded to the competition’s scoring system and got good results, which confirmed the accuracy of this method. Therefore, the article summarizes a highly accurate LSTM-based multidimensional data failure prediction method.","PeriodicalId":259179,"journal":{"name":"2019 Prognostics and System Health Management Conference (PHM-Qingdao)","volume":"35 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":"115161143","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-qingdao46334.2019.8942894
Kun He, Lianghua Zeng, Qin Shui, Jianyu Long, Chuan Li, Diego Cabrera
With the 3D printing rapidly expanding into various fields, 3D printers, as the equipment, should adopt a low-cost and small-sample fault diagnosis methods. A fault diagnosis method based on echo state networks (ESN) for 3D printers is proposed in this paper. A low-cost attitude sensor installed on the 3D printer is employed to collect raw fault data. Subsequently, feature extraction is carried out on the raw fault data. Using these features, ESN, as a shallow learning network, is modeled to diagnose faults of 3D printers. Experimental results show that the fault diagnosis method based on ESN still effective for 3D printers in low-cost and small-sample, which can make the fault recognition accuracy of 3D printer reach to 97.26%. Furthermore, contrast results indicated that the fault diagnosis accuracy of ESN is higher and most stable when compare with support vector machine (SVM), locality preserving projection support vector machine (LPPSVM) and principal component analysis support vector machine (PCASVM).
{"title":"Low-cost and Small-sample Fault Diagnosis for 3D Printers Based on Echo State Networks","authors":"Kun He, Lianghua Zeng, Qin Shui, Jianyu Long, Chuan Li, Diego Cabrera","doi":"10.1109/phm-qingdao46334.2019.8942894","DOIUrl":"https://doi.org/10.1109/phm-qingdao46334.2019.8942894","url":null,"abstract":"With the 3D printing rapidly expanding into various fields, 3D printers, as the equipment, should adopt a low-cost and small-sample fault diagnosis methods. A fault diagnosis method based on echo state networks (ESN) for 3D printers is proposed in this paper. A low-cost attitude sensor installed on the 3D printer is employed to collect raw fault data. Subsequently, feature extraction is carried out on the raw fault data. Using these features, ESN, as a shallow learning network, is modeled to diagnose faults of 3D printers. Experimental results show that the fault diagnosis method based on ESN still effective for 3D printers in low-cost and small-sample, which can make the fault recognition accuracy of 3D printer reach to 97.26%. Furthermore, contrast results indicated that the fault diagnosis accuracy of ESN is higher and most stable when compare with support vector machine (SVM), locality preserving projection support vector machine (LPPSVM) and principal component analysis support vector machine (PCASVM).","PeriodicalId":259179,"journal":{"name":"2019 Prognostics and System Health Management Conference (PHM-Qingdao)","volume":"19 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":"133625225","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-qingdao46334.2019.8943037
Da-peng Ren, Yuwei An, Z. Li
In order to establish a quantitative model to measure mental fatigue of the human body, subjects electroencephalogram (EEG), electrocardiogram (ECG), and galvanic skin response (GSR) are collected through the designed experimental method. Through optimized parameters setting, subjects states of mental fatigue are comprehensively analyzed and evaluated. Moreover, the entropy weight method is used for analyzing and verifying the above three kinds of data including EEG, ECG and GSR as well as comparing the data acquired from the subjects with various mental fatigue states. Thus, a parametric model is constructed to determine the degree of mental fatigue.
{"title":"The Discriminative Model of Mental Fatigue Based on Comprehensive Parameter Analysis","authors":"Da-peng Ren, Yuwei An, Z. Li","doi":"10.1109/phm-qingdao46334.2019.8943037","DOIUrl":"https://doi.org/10.1109/phm-qingdao46334.2019.8943037","url":null,"abstract":"In order to establish a quantitative model to measure mental fatigue of the human body, subjects electroencephalogram (EEG), electrocardiogram (ECG), and galvanic skin response (GSR) are collected through the designed experimental method. Through optimized parameters setting, subjects states of mental fatigue are comprehensively analyzed and evaluated. Moreover, the entropy weight method is used for analyzing and verifying the above three kinds of data including EEG, ECG and GSR as well as comparing the data acquired from the subjects with various mental fatigue states. Thus, a parametric model is constructed to determine the degree of mental fatigue.","PeriodicalId":259179,"journal":{"name":"2019 Prognostics and System Health Management Conference (PHM-Qingdao)","volume":"45 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":"131897119","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-qingdao46334.2019.8943062
Xiaokai Huang, Zemin Yao, Shouqing Huang, Dazhi Liu
Axial piston pumps are key components in hydraulic systems, and their real-time performance degradation analysis has received more and more attention in engineering practice. This paper proposes a degradation trajectory method based on self-organizing map (SOM), which is used to analyze the performance degradation of axial piston pumps. Firstly, a selfadaptive Morlet wavelet filter is applied to process the vibration signals of axial piston pumps, and time-domain metrics of filtered signal is used as eigenvectors which can reflect the performance degradation degree. Then data from typical status are used to train SOM, and trajectory on the output layer of SOM is used to represent the real-time performance of degradation degree. Lastly, the performance degradation experiment of axial piston pumps was carried out and the results showed that the proposed method can describe performance degradation process of axial piston pumps effectively.
{"title":"Performance Degradation Analysis of Axial Piston Pumps Based on Self-Organizing Map","authors":"Xiaokai Huang, Zemin Yao, Shouqing Huang, Dazhi Liu","doi":"10.1109/phm-qingdao46334.2019.8943062","DOIUrl":"https://doi.org/10.1109/phm-qingdao46334.2019.8943062","url":null,"abstract":"Axial piston pumps are key components in hydraulic systems, and their real-time performance degradation analysis has received more and more attention in engineering practice. This paper proposes a degradation trajectory method based on self-organizing map (SOM), which is used to analyze the performance degradation of axial piston pumps. Firstly, a selfadaptive Morlet wavelet filter is applied to process the vibration signals of axial piston pumps, and time-domain metrics of filtered signal is used as eigenvectors which can reflect the performance degradation degree. Then data from typical status are used to train SOM, and trajectory on the output layer of SOM is used to represent the real-time performance of degradation degree. Lastly, the performance degradation experiment of axial piston pumps was carried out and the results showed that the proposed method can describe performance degradation process of axial piston pumps effectively.","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":"134478865","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-qingdao46334.2019.8943051
Kang Wu, S. Zhong, Xu-yun Fu, Changtsing Wei
In the process of aeroengine anomaly detection, there is always an unbalance distribution among the samples of gas path performance parameters, that is, the number of normal samples is much larger than the number of abnormal samples. In addition, this imbalance will worsen with time, which leads to the classifier paying too much attention to normal samples in the process of model training. Thus, the recognition rate of abnormal samples will reduce significantly. To solve the above problems, an adaptive decision threshold support vector machine (ADT-SVM) is proposed and applied to the anomaly detection of aeroengine. Firstly, this paper analyzes the influence of the unbalanced training data on the performance of the traditional classification model. Then the concept of decision threshold is introduced and introduced into support vector machine for anomaly detection. Finally, an adaptive method is proposed to calculate the decision threshold based on the equal expected number of samples, and the performance of the adaptive threshold and the traditional default threshold SVM is compared through experiments, which show that the adaptive threshold is effective in solving the problem of the classification performance degradation of unbalanced gas path performance parameters.
{"title":"An Aeroengine Gas Path Anomaly Detection Method in The Case of Sample Imbalance","authors":"Kang Wu, S. Zhong, Xu-yun Fu, Changtsing Wei","doi":"10.1109/phm-qingdao46334.2019.8943051","DOIUrl":"https://doi.org/10.1109/phm-qingdao46334.2019.8943051","url":null,"abstract":"In the process of aeroengine anomaly detection, there is always an unbalance distribution among the samples of gas path performance parameters, that is, the number of normal samples is much larger than the number of abnormal samples. In addition, this imbalance will worsen with time, which leads to the classifier paying too much attention to normal samples in the process of model training. Thus, the recognition rate of abnormal samples will reduce significantly. To solve the above problems, an adaptive decision threshold support vector machine (ADT-SVM) is proposed and applied to the anomaly detection of aeroengine. Firstly, this paper analyzes the influence of the unbalanced training data on the performance of the traditional classification model. Then the concept of decision threshold is introduced and introduced into support vector machine for anomaly detection. Finally, an adaptive method is proposed to calculate the decision threshold based on the equal expected number of samples, and the performance of the adaptive threshold and the traditional default threshold SVM is compared through experiments, which show that the adaptive threshold is effective in solving the problem of the classification performance degradation of unbalanced gas path performance parameters.","PeriodicalId":259179,"journal":{"name":"2019 Prognostics and System Health Management Conference (PHM-Qingdao)","volume":"96 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":"117293455","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-qingdao46334.2019.8942988
Rui Wang, Zhisheng Zhang, Zhijie Xia, J. Miao, Yiming Guo
The fault diagnosis of CNC machine tools has become an important area of Prognostic and Health Management (PHM). The failure of rolling bearings on spindle is main cause of machine tool faults. Therefore, the significant focus of health management of CNC machine tools and other rotating machines is fault diagnosis of rolling bearings. In terms of the fault diagnosis, it is the most critical task to extracting bearing fault characteristics from vibration signals of rolling bearings. As a result, a new fault diagnosis method for bearing fault classification is proposed in this paper, which is built on the hierarchical entropy and improved Cuckoo Search-Support Vector Machine(CS-SVM). Firstly, ensemble empirical mode decomposition(EEMD) is adopted to decompose time domain vibration signals, aiming at eliminating modal confusion in empirical mode decomposition(EMD) method. Afterwards, the hierarchical entropy is chosen as fault feature parameters compared with sample entropy to construct feature vectors. In addition, the classification algorithm of multiple SVM optimized by the improved CS algorithm is utilized to identify rolling bearing fault modes. Finally, the proposed method is verified through the data taken from the Case Western Reserve University (CWRU) Bearing Data Center. The result demonstrates that the proposed method has promising performance and achieves accurate fault classification accuracy in rolling bearing fault diagnosis in comparison with other methods.
{"title":"A new approach for rolling bearing fault diagnosis based on EEMD hierarchical entropy and improved CS-SVM","authors":"Rui Wang, Zhisheng Zhang, Zhijie Xia, J. Miao, Yiming Guo","doi":"10.1109/phm-qingdao46334.2019.8942988","DOIUrl":"https://doi.org/10.1109/phm-qingdao46334.2019.8942988","url":null,"abstract":"The fault diagnosis of CNC machine tools has become an important area of Prognostic and Health Management (PHM). The failure of rolling bearings on spindle is main cause of machine tool faults. Therefore, the significant focus of health management of CNC machine tools and other rotating machines is fault diagnosis of rolling bearings. In terms of the fault diagnosis, it is the most critical task to extracting bearing fault characteristics from vibration signals of rolling bearings. As a result, a new fault diagnosis method for bearing fault classification is proposed in this paper, which is built on the hierarchical entropy and improved Cuckoo Search-Support Vector Machine(CS-SVM). Firstly, ensemble empirical mode decomposition(EEMD) is adopted to decompose time domain vibration signals, aiming at eliminating modal confusion in empirical mode decomposition(EMD) method. Afterwards, the hierarchical entropy is chosen as fault feature parameters compared with sample entropy to construct feature vectors. In addition, the classification algorithm of multiple SVM optimized by the improved CS algorithm is utilized to identify rolling bearing fault modes. Finally, the proposed method is verified through the data taken from the Case Western Reserve University (CWRU) Bearing Data Center. The result demonstrates that the proposed method has promising performance and achieves accurate fault classification accuracy in rolling bearing fault diagnosis in comparison with other methods.","PeriodicalId":259179,"journal":{"name":"2019 Prognostics and System Health Management Conference (PHM-Qingdao)","volume":"41 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":"116227254","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-qingdao46334.2019.8942929
Sheng Chenxing, Z. Zongxin, Wang Huiyang, Han Yu
On-line detection of metallic wear debris is an effective approach for condition monitoring of mechanical systems. Existing on-line oil conditioning sensors are mainly based on ferrography and inductive techniques. However, ferrography technique needs a clean background and inductive technique requires a high cleanliness of lubricant. To solve these issues, in this paper a metallic wear debris sensor based on eddy current principle is developed. Both numerical simulations and prototype experiments are conducted to evaluate the capacity and feasibility of the new sensor for detecting wear debris. The analysis results demonstrate that: 1) A pulse is generated when the wear debris pass through the sensor, the amplitude and width of the pulse can be used to identify the material and size of the debris; 2) The developed sensor is able to detect copper debris with a diameter greater than 150 μm and iron debris greater than 60 μm. This work provides a new idea for detecting wear debris and a new method for obtaining the characteristics of wear debris.
{"title":"Development of Metallic Wear Debris Sensor Based on Eddy Current Technique","authors":"Sheng Chenxing, Z. Zongxin, Wang Huiyang, Han Yu","doi":"10.1109/phm-qingdao46334.2019.8942929","DOIUrl":"https://doi.org/10.1109/phm-qingdao46334.2019.8942929","url":null,"abstract":"On-line detection of metallic wear debris is an effective approach for condition monitoring of mechanical systems. Existing on-line oil conditioning sensors are mainly based on ferrography and inductive techniques. However, ferrography technique needs a clean background and inductive technique requires a high cleanliness of lubricant. To solve these issues, in this paper a metallic wear debris sensor based on eddy current principle is developed. Both numerical simulations and prototype experiments are conducted to evaluate the capacity and feasibility of the new sensor for detecting wear debris. The analysis results demonstrate that: 1) A pulse is generated when the wear debris pass through the sensor, the amplitude and width of the pulse can be used to identify the material and size of the debris; 2) The developed sensor is able to detect copper debris with a diameter greater than 150 μm and iron debris greater than 60 μm. This work provides a new idea for detecting wear debris and a new method for obtaining the characteristics of wear debris.","PeriodicalId":259179,"journal":{"name":"2019 Prognostics and System Health Management Conference (PHM-Qingdao)","volume":"24 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":"124511023","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-qingdao46334.2019.8942862
Hongwei Luo, L. Song, Mengyang Wang, Huaqing Wang, Lingli Cui
In order to solve the difficulty of features extraction of compound faults in underdetermined state, this research proposes an approach to extract signal features by combining adaptive generalized S transform (GST) and non-negative matrix factorization algorithm (NMF). The adaptive function (AF) is introduced to optimize GST. The optimized GST is used to process monitored signals to get the time-frequency features matrix. The NMF is improved by Itakura-Saito (IS) divergence. And the dimensionality of the signal time-frequency matrix is reduced by it. After iterative updating, several low-dimensional matrices are obtained. The time-domain waveforms of low-dimensional matrices are reconstructed, and the envelope spectrum analysis is performed to realize compound faults diagnosis. The simulation test and the actual bearing compound fault signals experiment prove that this method can effectively extract compound fault features in underdetermined state and realize bearing compound faults diagnosis.
{"title":"Compound Faults Diagnosis Method Based on Adaptive GST-NMF for Rolling Bearing","authors":"Hongwei Luo, L. Song, Mengyang Wang, Huaqing Wang, Lingli Cui","doi":"10.1109/phm-qingdao46334.2019.8942862","DOIUrl":"https://doi.org/10.1109/phm-qingdao46334.2019.8942862","url":null,"abstract":"In order to solve the difficulty of features extraction of compound faults in underdetermined state, this research proposes an approach to extract signal features by combining adaptive generalized S transform (GST) and non-negative matrix factorization algorithm (NMF). The adaptive function (AF) is introduced to optimize GST. The optimized GST is used to process monitored signals to get the time-frequency features matrix. The NMF is improved by Itakura-Saito (IS) divergence. And the dimensionality of the signal time-frequency matrix is reduced by it. After iterative updating, several low-dimensional matrices are obtained. The time-domain waveforms of low-dimensional matrices are reconstructed, and the envelope spectrum analysis is performed to realize compound faults diagnosis. The simulation test and the actual bearing compound fault signals experiment prove that this method can effectively extract compound fault features in underdetermined state and realize bearing compound faults diagnosis.","PeriodicalId":259179,"journal":{"name":"2019 Prognostics and System Health Management Conference (PHM-Qingdao)","volume":"679 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":"122974742","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-qingdao46334.2019.8943015
Shukai Guan, B. Wan, Zhongqing Zhang, J. Zuo
In the development and production stages of components, the reliability enhancement test (RET) has been used as one of the necessary test methods to identify weak links in product design and production. Due to the diversity and the complex environment of components, how to reduce the cost of RET and stimulate the potential defects of the device products quickly has become the primary research goal. In this paper, a design method of component multi-stress RET based on fuzzy theory is presented. First, we use the FMECA to obtain the sensitive stresses of components. The sensitive stresses order is measured by the fuzzy theory. Second, we use the double-crossed stepwise stress method to verify the sensitive stresses sequence. Third, the stress combination of RET is determined by using the fuzzy matrix calculation results and the data distribution characteristics. Fourth, using the failure physics theory and orthogonal experiment methods to optimize the design of RET. Finally, a case study with A/D converter is carried out to verify the above methods. The optimization method of multi-stress RET is helpful to quantify different factors and quickly excite potential defects of components by using failure physical simulations.
{"title":"The Optimization Method of Component Multi-stress Reliability Enhancement Test Based on Fuzzy Theory","authors":"Shukai Guan, B. Wan, Zhongqing Zhang, J. Zuo","doi":"10.1109/phm-qingdao46334.2019.8943015","DOIUrl":"https://doi.org/10.1109/phm-qingdao46334.2019.8943015","url":null,"abstract":"In the development and production stages of components, the reliability enhancement test (RET) has been used as one of the necessary test methods to identify weak links in product design and production. Due to the diversity and the complex environment of components, how to reduce the cost of RET and stimulate the potential defects of the device products quickly has become the primary research goal. In this paper, a design method of component multi-stress RET based on fuzzy theory is presented. First, we use the FMECA to obtain the sensitive stresses of components. The sensitive stresses order is measured by the fuzzy theory. Second, we use the double-crossed stepwise stress method to verify the sensitive stresses sequence. Third, the stress combination of RET is determined by using the fuzzy matrix calculation results and the data distribution characteristics. Fourth, using the failure physics theory and orthogonal experiment methods to optimize the design of RET. Finally, a case study with A/D converter is carried out to verify the above methods. The optimization method of multi-stress RET is helpful to quantify different factors and quickly excite potential defects of components by using failure physical simulations.","PeriodicalId":259179,"journal":{"name":"2019 Prognostics and System Health Management Conference (PHM-Qingdao)","volume":"269 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":"123482690","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：