Pub Date : 2021-10-15DOI: 10.1109/PHM-Nanjing52125.2021.9612949
Ziqian Shen, Wei Guo
Knowledge distillation (KD) is one of popular algorithms for compressing deep neural networks because it generates a compact but still powerful deep neural network for the cases of complicated situations and limited computation resources. In this study, an intelligent fault diagnosis method is developed based on the probabilistic knowledge distillation (PKD) and deep convolutional neural network (CNN) to determine the health states of bearings. First, the one-dimensional vibration signal is reshaped as a two-dimensional matrix to input the teacher or student network. Then, a deeper neural network and small network are trained as the teacher and student networks, respectively. The probability distribution (PD) is learned by minimizing the difference of the joint density probability estimation between the teacher and student networks, that is, the lightweight network learns to integrate the PD of the deeper neural network in the high-dimensional feature space and realizes the knowledge transfer from training samples to test samples. The results of experimental bearings indicate that the proposed diagnosis method has higher diagnosis accuracy than the other two popular knowledge distillation methods and its student network only has about one 700-th parameter of the teacher network. Therefore, the proposed method achieves a good balance between the classification accuracy and network compression, and demonstrates potential application to intelligent fault diagnosis of bearings under varying working conditions.
{"title":"An Intelligent Bearing Fault Diagnosis based on Modified Probabilistic Knowledge Distillation","authors":"Ziqian Shen, Wei Guo","doi":"10.1109/PHM-Nanjing52125.2021.9612949","DOIUrl":"https://doi.org/10.1109/PHM-Nanjing52125.2021.9612949","url":null,"abstract":"Knowledge distillation (KD) is one of popular algorithms for compressing deep neural networks because it generates a compact but still powerful deep neural network for the cases of complicated situations and limited computation resources. In this study, an intelligent fault diagnosis method is developed based on the probabilistic knowledge distillation (PKD) and deep convolutional neural network (CNN) to determine the health states of bearings. First, the one-dimensional vibration signal is reshaped as a two-dimensional matrix to input the teacher or student network. Then, a deeper neural network and small network are trained as the teacher and student networks, respectively. The probability distribution (PD) is learned by minimizing the difference of the joint density probability estimation between the teacher and student networks, that is, the lightweight network learns to integrate the PD of the deeper neural network in the high-dimensional feature space and realizes the knowledge transfer from training samples to test samples. The results of experimental bearings indicate that the proposed diagnosis method has higher diagnosis accuracy than the other two popular knowledge distillation methods and its student network only has about one 700-th parameter of the teacher network. Therefore, the proposed method achieves a good balance between the classification accuracy and network compression, and demonstrates potential application to intelligent fault diagnosis of bearings under varying working conditions.","PeriodicalId":436428,"journal":{"name":"2021 Global Reliability and Prognostics and Health Management (PHM-Nanjing)","volume":"183 5 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2021-10-15","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"133384005","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 : 2021-10-15DOI: 10.1109/PHM-Nanjing52125.2021.9613071
Na Wang, Jie Ren, Yue Luo, Kaihua Guo, Datong Liu
Actuator is a critical part of the unmanned aerial vehicle (UAV), for which accurate and speedy fault detection is of great significance in practical application. Data-driven method becomes more appealing due to its feasibility and high performance. However, the current fault detection method based on machine learning cannot realize feature selection and real-time detection, and its feature extraction and learning ability of time series is not high enough. To solve the above problems, we propose a new fault detection method based on maximal information coefficient and one dimensional convolutional neural network (MIC-1DCNN) approach. It combines the high feature extraction ability of one dimensional convolutional neural network (1DCNN) for time series and the good feature selection ability of maximal information coefficient (MIC) for nonlinear data, which complete UAV actuator fault detection well and improve its efficiency greatly. The benchmark flight data set of the UAV is adopted for conducting experimental verification. The experimental results indicate that the proposed method can achieve satisfied performance in UAV actuator fault detection regarding speed and accuracy indices.
{"title":"UAV Actuator Fault Detection using Maximal Information Coefficient and 1-D Convolutional Neural Network","authors":"Na Wang, Jie Ren, Yue Luo, Kaihua Guo, Datong Liu","doi":"10.1109/PHM-Nanjing52125.2021.9613071","DOIUrl":"https://doi.org/10.1109/PHM-Nanjing52125.2021.9613071","url":null,"abstract":"Actuator is a critical part of the unmanned aerial vehicle (UAV), for which accurate and speedy fault detection is of great significance in practical application. Data-driven method becomes more appealing due to its feasibility and high performance. However, the current fault detection method based on machine learning cannot realize feature selection and real-time detection, and its feature extraction and learning ability of time series is not high enough. To solve the above problems, we propose a new fault detection method based on maximal information coefficient and one dimensional convolutional neural network (MIC-1DCNN) approach. It combines the high feature extraction ability of one dimensional convolutional neural network (1DCNN) for time series and the good feature selection ability of maximal information coefficient (MIC) for nonlinear data, which complete UAV actuator fault detection well and improve its efficiency greatly. The benchmark flight data set of the UAV is adopted for conducting experimental verification. The experimental results indicate that the proposed method can achieve satisfied performance in UAV actuator fault detection regarding speed and accuracy indices.","PeriodicalId":436428,"journal":{"name":"2021 Global Reliability and Prognostics and Health Management (PHM-Nanjing)","volume":"53 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2021-10-15","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"124611024","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}
The honeycomb cavity periodic strut structure with 3D printing technology can achieve the purpose of lightweight and vibration reduction on the basis of ensuring the stiffness and strength of the bar. In this paper, the stiffness characteristics and antivibration (resonance / flutter) ability of solid strut and regular hexahedral honeycomb periodic strut are studied by finite element analysis. The results show that the maximum deformation and maximum stress of honeycomb periodic strut are greater than that of solid strut. The maximum deformation of two kinds of rods occurs at the top of the rod, and the maximum stress of solid strut occurs at the root of the rod. The maximum stress of the honeycomb periodic strut occurs at the root of the internal honeycomb structure near the fixed end. The first six frequencies of the regular hexahedral honeycomb periodic strut are lower than those of the solid strut. The first five and seventh modes of the regular hexahedral honeycomb periodic strut are the same. The sixth, eighth, ninth and tenth modes of deformation are different.
{"title":"Research On Vibration Reduction Of Regular Hexahedral Honeycomb Structure With Periodic Strut","authors":"Bin Wu, Xinhang Shen, Qingpeng Han, Rui Zhu, Daolei Wang, Binxia Yuan","doi":"10.1109/PHM-Nanjing52125.2021.9612991","DOIUrl":"https://doi.org/10.1109/PHM-Nanjing52125.2021.9612991","url":null,"abstract":"The honeycomb cavity periodic strut structure with 3D printing technology can achieve the purpose of lightweight and vibration reduction on the basis of ensuring the stiffness and strength of the bar. In this paper, the stiffness characteristics and antivibration (resonance / flutter) ability of solid strut and regular hexahedral honeycomb periodic strut are studied by finite element analysis. The results show that the maximum deformation and maximum stress of honeycomb periodic strut are greater than that of solid strut. The maximum deformation of two kinds of rods occurs at the top of the rod, and the maximum stress of solid strut occurs at the root of the rod. The maximum stress of the honeycomb periodic strut occurs at the root of the internal honeycomb structure near the fixed end. The first six frequencies of the regular hexahedral honeycomb periodic strut are lower than those of the solid strut. The first five and seventh modes of the regular hexahedral honeycomb periodic strut are the same. The sixth, eighth, ninth and tenth modes of deformation are different.","PeriodicalId":436428,"journal":{"name":"2021 Global Reliability and Prognostics and Health Management (PHM-Nanjing)","volume":"33 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2021-10-15","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"131736641","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 : 2021-10-15DOI: 10.1109/PHM-Nanjing52125.2021.9612773
Siqi Gong, Jiantao Lu, Shunming Li, Huijie Ma, Wang Yan-feng, Teng Guang-rong
In recent years, as a simple and effective method of noise reduction, singular value decomposition (SVD) has been widely concerned and applied. The idea of SVD to denoising is mainly to drop out singular components (SCs) with small singular value (SV), which ignores the weak signals buried in strong noise. Aiming to extract the weak signals in strong noise, this paper proposed a method of selecting SCs by the correntropy induced metric (CIM). Then the frequency components of characteristic signals can be found through cyclic correntropy spectrum (CCES) which is the extension of the correntropy (CE). The proposed method SVD-CIM firstly performs SVD on the signal, secondly calculates the CIM between SCs and the original signal, thirdly selects the SCs by CIM, fourthly reconstructs the retained SCs, and finally performs the CCES on the reconstructed signal to enhance the frequency of the characteristic signal. Experimental results have demonstrated that the proposed method can enhance the weak signal features effectively.
{"title":"The Correntropy Induced Metric and Cyclic Correntropy Spectrum Method Combined With Singular Value Decomposition for Weak Signal Detection","authors":"Siqi Gong, Jiantao Lu, Shunming Li, Huijie Ma, Wang Yan-feng, Teng Guang-rong","doi":"10.1109/PHM-Nanjing52125.2021.9612773","DOIUrl":"https://doi.org/10.1109/PHM-Nanjing52125.2021.9612773","url":null,"abstract":"In recent years, as a simple and effective method of noise reduction, singular value decomposition (SVD) has been widely concerned and applied. The idea of SVD to denoising is mainly to drop out singular components (SCs) with small singular value (SV), which ignores the weak signals buried in strong noise. Aiming to extract the weak signals in strong noise, this paper proposed a method of selecting SCs by the correntropy induced metric (CIM). Then the frequency components of characteristic signals can be found through cyclic correntropy spectrum (CCES) which is the extension of the correntropy (CE). The proposed method SVD-CIM firstly performs SVD on the signal, secondly calculates the CIM between SCs and the original signal, thirdly selects the SCs by CIM, fourthly reconstructs the retained SCs, and finally performs the CCES on the reconstructed signal to enhance the frequency of the characteristic signal. Experimental results have demonstrated that the proposed method can enhance the weak signal features effectively.","PeriodicalId":436428,"journal":{"name":"2021 Global Reliability and Prognostics and Health Management (PHM-Nanjing)","volume":"35 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2021-10-15","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"134093938","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 : 2021-10-15DOI: 10.1109/PHM-Nanjing52125.2021.9612661
Yingying Wu
Aiming at the current information needs of English learning, combined with the current problems of multimedia-assisted teaching, a multimedia-assisted English online teaching model based on flipped classrooms is designed. Analyze the characteristics of multimedia-assisted English online teaching and optimize the functions of the teaching model; based on the dual-agent teaching theory of flipped classroom English teaching, the model’s login module and personalized recommendation module are designed with emphasis on the online assisted teaching function optimize management. Experimental results show that after using this model, the accuracy of classroom exercises has been effectively improved, indicating that it can provide a reference for the application of intelligent recommendation algorithms in English teaching.
{"title":"Design of Multimedia Assisted English online teaching model based on flipped classroom","authors":"Yingying Wu","doi":"10.1109/PHM-Nanjing52125.2021.9612661","DOIUrl":"https://doi.org/10.1109/PHM-Nanjing52125.2021.9612661","url":null,"abstract":"Aiming at the current information needs of English learning, combined with the current problems of multimedia-assisted teaching, a multimedia-assisted English online teaching model based on flipped classrooms is designed. Analyze the characteristics of multimedia-assisted English online teaching and optimize the functions of the teaching model; based on the dual-agent teaching theory of flipped classroom English teaching, the model’s login module and personalized recommendation module are designed with emphasis on the online assisted teaching function optimize management. Experimental results show that after using this model, the accuracy of classroom exercises has been effectively improved, indicating that it can provide a reference for the application of intelligent recommendation algorithms in English teaching.","PeriodicalId":436428,"journal":{"name":"2021 Global Reliability and Prognostics and Health Management (PHM-Nanjing)","volume":"7 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2021-10-15","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"131969996","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 : 2021-10-15DOI: 10.1109/PHM-Nanjing52125.2021.9612986
Yimin Jiang, L. Cao, Rourou Li, Kaigan Zhang, Tangbin Xia
The effectiveness of conventional deep learning-based intelligent fault diagnosis models depends on the training data and testing data following the same probability distribution. But the discrepancy in cross-domain distributions is inherent because of changes in external and internal conditions, resulting in a decline in diagnosis performance. Recently, transfer learning is employed to induce an adaptive diagnosis network in the scenario of distribution discrepancies. However, little attention has been paid to fully consider the cross-layer interaction and feature transferability for traditional transfer learning-based diagnosis networks. To overcome these problems, this paper presents a novel transferable bilinear neural network for cross-domain diagnosis. First, the bilinear map between bi-layer features is used to implement a novel information fusion and significantly improves the feature representation capability. It also realizes the embedding of bi-layer joint distributions into the reproducing kernel Hilbert space. Based on the embedding and feature transferability analysis, a reliable adaptive framework is designed to enable effective cross-domain transfer learning. The effectiveness of the proposed approach is validated using experiments with various transfer scenarios.
{"title":"Cross-domain Intelligent Fault Diagnosis Using Transferable Bilinear Neural Network","authors":"Yimin Jiang, L. Cao, Rourou Li, Kaigan Zhang, Tangbin Xia","doi":"10.1109/PHM-Nanjing52125.2021.9612986","DOIUrl":"https://doi.org/10.1109/PHM-Nanjing52125.2021.9612986","url":null,"abstract":"The effectiveness of conventional deep learning-based intelligent fault diagnosis models depends on the training data and testing data following the same probability distribution. But the discrepancy in cross-domain distributions is inherent because of changes in external and internal conditions, resulting in a decline in diagnosis performance. Recently, transfer learning is employed to induce an adaptive diagnosis network in the scenario of distribution discrepancies. However, little attention has been paid to fully consider the cross-layer interaction and feature transferability for traditional transfer learning-based diagnosis networks. To overcome these problems, this paper presents a novel transferable bilinear neural network for cross-domain diagnosis. First, the bilinear map between bi-layer features is used to implement a novel information fusion and significantly improves the feature representation capability. It also realizes the embedding of bi-layer joint distributions into the reproducing kernel Hilbert space. Based on the embedding and feature transferability analysis, a reliable adaptive framework is designed to enable effective cross-domain transfer learning. The effectiveness of the proposed approach is validated using experiments with various transfer scenarios.","PeriodicalId":436428,"journal":{"name":"2021 Global Reliability and Prognostics and Health Management (PHM-Nanjing)","volume":"27 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2021-10-15","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"132233201","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 : 2021-10-15DOI: 10.1109/PHM-Nanjing52125.2021.9612767
Qingchuan He, Jun Pan, Wh H. Chen
Power supplies are widely used in commercial applications and military. The power supply is always found to be a weak point because its failure can cause a malfunction in the system. The power supply manufacturers often struggle with the conundrum of trying to quantify the lifespan of a power supply. This paper developed an approach to quantify the lifetime of a power supply based on the accelerated degradation test (ADT). The major originalities involve identification of degradation parameters, degradation indictor, end-of-life criterion, and also designing stress loading profile and analyzing degradation data. A case study is given to illustrate the new approach. Experimental results show the mean RMS output voltage of the power supply can be selected as a degradation measuring parameter, the difference between mean RMS voltages measured under two thermal stress levels can be identified as a degradation indictor, and also the proposed ADT method can be used to quantify the lifetime of a power supply within a short period.
{"title":"An Accelerated Degradation Testing Method for Quantifying Lifetime of DC-DC Power Supply","authors":"Qingchuan He, Jun Pan, Wh H. Chen","doi":"10.1109/PHM-Nanjing52125.2021.9612767","DOIUrl":"https://doi.org/10.1109/PHM-Nanjing52125.2021.9612767","url":null,"abstract":"Power supplies are widely used in commercial applications and military. The power supply is always found to be a weak point because its failure can cause a malfunction in the system. The power supply manufacturers often struggle with the conundrum of trying to quantify the lifespan of a power supply. This paper developed an approach to quantify the lifetime of a power supply based on the accelerated degradation test (ADT). The major originalities involve identification of degradation parameters, degradation indictor, end-of-life criterion, and also designing stress loading profile and analyzing degradation data. A case study is given to illustrate the new approach. Experimental results show the mean RMS output voltage of the power supply can be selected as a degradation measuring parameter, the difference between mean RMS voltages measured under two thermal stress levels can be identified as a degradation indictor, and also the proposed ADT method can be used to quantify the lifetime of a power supply within a short period.","PeriodicalId":436428,"journal":{"name":"2021 Global Reliability and Prognostics and Health Management (PHM-Nanjing)","volume":"26 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2021-10-15","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"132574005","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 : 2021-10-15DOI: 10.1109/phm-nanjing52125.2021.9612822
{"title":"PHM-Nanjing 2021 Blank Page","authors":"","doi":"10.1109/phm-nanjing52125.2021.9612822","DOIUrl":"https://doi.org/10.1109/phm-nanjing52125.2021.9612822","url":null,"abstract":"","PeriodicalId":436428,"journal":{"name":"2021 Global Reliability and Prognostics and Health Management (PHM-Nanjing)","volume":"25 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2021-10-15","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"132897778","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 : 2021-10-15DOI: 10.1109/PHM-Nanjing52125.2021.9612924
Xiaoli Zhao, Jianyong Yao, W. Deng, M. Jia
The distribution of mechanical system health data monitored in the industrial field is imbalanced mainly. To this end, this paper designs a new imbalanced fault diagnosis framework of the mechanical system based on Normalized Conditional Variational Auto-Encoder with Adaptive Focal Loss (NCVAE-AFL). The core of this diagnostic framework is to use the designed NCVAE model to enhance the data’s feature learning ability. The multi-layer sensitive feature vector of the data can be extracted, the generalization performance of the diagnostic model is further improved. Meanwhile, a new Adaptive Focus Loss (AFL) function is designed for NCVAE model, which focuses training on a few samples of health conditions that are difficult to classify and balance the diagnosis difficulty of samples of different categories. Finally, the double-span rotor-bearing system fault simulation experiment platform verifies the effectiveness and superiority of the proposed NCVAE-AFL algorithm and its diagnostic framework.
{"title":"Imbalanced Fault Diagnosis of Bearing-Rotor System via Normalized Conditional Variational Auto-Encoder with Adaptive Focal Loss","authors":"Xiaoli Zhao, Jianyong Yao, W. Deng, M. Jia","doi":"10.1109/PHM-Nanjing52125.2021.9612924","DOIUrl":"https://doi.org/10.1109/PHM-Nanjing52125.2021.9612924","url":null,"abstract":"The distribution of mechanical system health data monitored in the industrial field is imbalanced mainly. To this end, this paper designs a new imbalanced fault diagnosis framework of the mechanical system based on Normalized Conditional Variational Auto-Encoder with Adaptive Focal Loss (NCVAE-AFL). The core of this diagnostic framework is to use the designed NCVAE model to enhance the data’s feature learning ability. The multi-layer sensitive feature vector of the data can be extracted, the generalization performance of the diagnostic model is further improved. Meanwhile, a new Adaptive Focus Loss (AFL) function is designed for NCVAE model, which focuses training on a few samples of health conditions that are difficult to classify and balance the diagnosis difficulty of samples of different categories. Finally, the double-span rotor-bearing system fault simulation experiment platform verifies the effectiveness and superiority of the proposed NCVAE-AFL algorithm and its diagnostic framework.","PeriodicalId":436428,"journal":{"name":"2021 Global Reliability and Prognostics and Health Management (PHM-Nanjing)","volume":"4 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2021-10-15","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"121999514","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 : 2021-10-15DOI: 10.1109/PHM-Nanjing52125.2021.9612891
Jun Pan, Hui Li, Wenhua Chen, Yimin Wei
The sound signal during the operation of an elevator is related to the performance of which, so the current performance of an elevator can be obtained through the analysis of the sound signal. This paper proposes a performance evaluation method by the analysis of the sound signal for an elevator. The sound acquisition method for elevators is designed, and the sound signals of normal elevators and abnormal ones are collected separately. According to the operation of the door and the car, the sound signals are processed respectively to extract the features. Combined with the Grey Relational Analysis and Fuzzy Comprehensive Appraisal, a performance evaluation method based on the features of the elevator sound is constructed for elevators. Finally, the experimental verification is carried out. The results show that the evaluation error of the method is small compared with the actual situation, so the method can be used to evaluate the performance of elevators.
{"title":"Elevator Performance Evaluation Based on the Analysis of the Running Sound","authors":"Jun Pan, Hui Li, Wenhua Chen, Yimin Wei","doi":"10.1109/PHM-Nanjing52125.2021.9612891","DOIUrl":"https://doi.org/10.1109/PHM-Nanjing52125.2021.9612891","url":null,"abstract":"The sound signal during the operation of an elevator is related to the performance of which, so the current performance of an elevator can be obtained through the analysis of the sound signal. This paper proposes a performance evaluation method by the analysis of the sound signal for an elevator. The sound acquisition method for elevators is designed, and the sound signals of normal elevators and abnormal ones are collected separately. According to the operation of the door and the car, the sound signals are processed respectively to extract the features. Combined with the Grey Relational Analysis and Fuzzy Comprehensive Appraisal, a performance evaluation method based on the features of the elevator sound is constructed for elevators. Finally, the experimental verification is carried out. The results show that the evaluation error of the method is small compared with the actual situation, so the method can be used to evaluate the performance of elevators.","PeriodicalId":436428,"journal":{"name":"2021 Global Reliability and Prognostics and Health Management (PHM-Nanjing)","volume":"3 1 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2021-10-15","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"116825262","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：