Pub Date : 2022-05-01DOI: 10.1109/PHM2022-London52454.2022.00088
Di Wu, Xizhong Shen, Ling Chen
Aluminum material is widely used in production and life, and it is a material with high requirements on surface treatment. Detecting its surface defects is the key to improving its utilization efficiency. To improve the accuracy and reliability of surface defect detection of aluminum material, this paper uses YOLO X with flexibility, lightness, and accuracy to build a training network, and proposes a defect detection model based on YOLO X, which replaces the original CSP-DarkNet with CSP-ResNeXt and integrates the Attention Mechanism. The network's ability to classify defects is strengthened, so the detection accuracy of multiple defects is improved. The Transfer Learning method is used in training, which shortens the training cycle and improves the detection performance of the short-term training network. The experimental results show that the Average Precision (AP) and mean Average Precision (mAP) of the model have been significantly improved, and the detection speed Frame Per Second (FPS) has not decreased significantly.
{"title":"Detection of Defects on Aluminum Profile Surface Based on Improved YOLO","authors":"Di Wu, Xizhong Shen, Ling Chen","doi":"10.1109/PHM2022-London52454.2022.00088","DOIUrl":"https://doi.org/10.1109/PHM2022-London52454.2022.00088","url":null,"abstract":"Aluminum material is widely used in production and life, and it is a material with high requirements on surface treatment. Detecting its surface defects is the key to improving its utilization efficiency. To improve the accuracy and reliability of surface defect detection of aluminum material, this paper uses YOLO X with flexibility, lightness, and accuracy to build a training network, and proposes a defect detection model based on YOLO X, which replaces the original CSP-DarkNet with CSP-ResNeXt and integrates the Attention Mechanism. The network's ability to classify defects is strengthened, so the detection accuracy of multiple defects is improved. The Transfer Learning method is used in training, which shortens the training cycle and improves the detection performance of the short-term training network. The experimental results show that the Average Precision (AP) and mean Average Precision (mAP) of the model have been significantly improved, and the detection speed Frame Per Second (FPS) has not decreased significantly.","PeriodicalId":269605,"journal":{"name":"2022 Prognostics and Health Management Conference (PHM-2022 London)","volume":"22 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2022-05-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"115669232","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 : 2022-05-01DOI: 10.1109/PHM2022-London52454.2022.00073
Pan Zhang
In order to solve the problem of poor detect effectiveness of small target objects in the process of algorithm, a feature fusion method for Faster R-CNN has been proposed. This method fully fuses the deep and shallow feature information, which well improves the detection model for small objects. Meanwhile, in order to better detect small objects, oversampling is used to preprocess the data, and the corresponding hyperparameter values of the Faster R-CNN model are adjusted. From the experimental results, it is easy to see that the detection accuracy is improved by 7.6%, and for small target objects Bottle, Plant, Cow and Boat is improved by 13.9%, 11.2%, 6.7% and 9.5%, respectively. The detection effect of this model has been substantially improved.
{"title":"Detection of small objects based on feature fusion","authors":"Pan Zhang","doi":"10.1109/PHM2022-London52454.2022.00073","DOIUrl":"https://doi.org/10.1109/PHM2022-London52454.2022.00073","url":null,"abstract":"In order to solve the problem of poor detect effectiveness of small target objects in the process of algorithm, a feature fusion method for Faster R-CNN has been proposed. This method fully fuses the deep and shallow feature information, which well improves the detection model for small objects. Meanwhile, in order to better detect small objects, oversampling is used to preprocess the data, and the corresponding hyperparameter values of the Faster R-CNN model are adjusted. From the experimental results, it is easy to see that the detection accuracy is improved by 7.6%, and for small target objects Bottle, Plant, Cow and Boat is improved by 13.9%, 11.2%, 6.7% and 9.5%, respectively. The detection effect of this model has been substantially improved.","PeriodicalId":269605,"journal":{"name":"2022 Prognostics and Health Management Conference (PHM-2022 London)","volume":"2016 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2022-05-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"114691502","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}
Wireless power transfer (WPT) technology achieves complete electrical isolation between power supply and electronic load. It has attracted worldwide attention due to its advantages of safety, reliability and flexibility. However, limited transfer distance and low transfer efficiency have always restricted the further application and promotion of WPT technology. In this paper, the WPT systems based on magnetic dipole-coil structure are proposed, the system has a multi-directional wireless power transfer (MD-WPT) ability within 360erange though optimizing design of a long-bar ferrite core. The optimum design method has been provided and equivalent circuit of the MD-WPT is given for better analysis. The electromagnetic properties of ferrite core in the dipole-coil multi-directional WPT systems are also studied. The power transfer efficiency of the dipole-coil MD-WPT systems can be in-creased by more than 75% and the output power is more than 45W when the ratio of transfer distance to coil length is 1, which can greatly improve the power transfer efficiency and the degree of freedom of power supply. The research results can provide valuable guidelines for multi-directional WPT technologies in the fields such as unmanned aerial vehicle, portable devices, and Internet of Things in the future.
{"title":"Research on High Degree-of-Freedom WPT Systems Based on Dipole Coil","authors":"Qiqi Luan, Qingsheng Yang, Chunpeng Li, Xinping Wang, Chao Jiang, Guofei Guan","doi":"10.1109/PHM2022-London52454.2022.00099","DOIUrl":"https://doi.org/10.1109/PHM2022-London52454.2022.00099","url":null,"abstract":"Wireless power transfer (WPT) technology achieves complete electrical isolation between power supply and electronic load. It has attracted worldwide attention due to its advantages of safety, reliability and flexibility. However, limited transfer distance and low transfer efficiency have always restricted the further application and promotion of WPT technology. In this paper, the WPT systems based on magnetic dipole-coil structure are proposed, the system has a multi-directional wireless power transfer (MD-WPT) ability within 360erange though optimizing design of a long-bar ferrite core. The optimum design method has been provided and equivalent circuit of the MD-WPT is given for better analysis. The electromagnetic properties of ferrite core in the dipole-coil multi-directional WPT systems are also studied. The power transfer efficiency of the dipole-coil MD-WPT systems can be in-creased by more than 75% and the output power is more than 45W when the ratio of transfer distance to coil length is 1, which can greatly improve the power transfer efficiency and the degree of freedom of power supply. The research results can provide valuable guidelines for multi-directional WPT technologies in the fields such as unmanned aerial vehicle, portable devices, and Internet of Things in the future.","PeriodicalId":269605,"journal":{"name":"2022 Prognostics and Health Management Conference (PHM-2022 London)","volume":"1 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2022-05-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"128514716","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 : 2022-05-01DOI: 10.1109/PHM2022-London52454.2022.00074
Zhongyuan Zhao, Zhaohui Liu, Bei Wang, Lijun Ouyang, Can Wang, Yan Ouyang
The current mainstream knowledge tracking model is based on the neural network of deep learning, which has a certain improvement in performance. However, due to the difficulty of interpretability of the deep learning methods, and the previous literature did not involve the high-dimensional information between problems and knowledge points when their model used the answer record, there is a situation that the relevant information is not sufficiently extracted. In order to solve the above problems, a knowledge tracing model based on the graph attention network mechanism is proposed, which uses the graph attention network to reveal the potential graph structure between knowledge points in answer records, and aggregates the correlation degree through the attention mechanism, so that the input information of the model includes the relationship information between problems and knowledge points, which enhances the interpretability of the model and improves the prediction accuracy of the model. On the three commonly used public datasets, the proposed model can better reflect learners’ mastery of knowledge points.
{"title":"Research on Deep Knowledge Tracing Model Integrating Graph Attention Network","authors":"Zhongyuan Zhao, Zhaohui Liu, Bei Wang, Lijun Ouyang, Can Wang, Yan Ouyang","doi":"10.1109/PHM2022-London52454.2022.00074","DOIUrl":"https://doi.org/10.1109/PHM2022-London52454.2022.00074","url":null,"abstract":"The current mainstream knowledge tracking model is based on the neural network of deep learning, which has a certain improvement in performance. However, due to the difficulty of interpretability of the deep learning methods, and the previous literature did not involve the high-dimensional information between problems and knowledge points when their model used the answer record, there is a situation that the relevant information is not sufficiently extracted. In order to solve the above problems, a knowledge tracing model based on the graph attention network mechanism is proposed, which uses the graph attention network to reveal the potential graph structure between knowledge points in answer records, and aggregates the correlation degree through the attention mechanism, so that the input information of the model includes the relationship information between problems and knowledge points, which enhances the interpretability of the model and improves the prediction accuracy of the model. On the three commonly used public datasets, the proposed model can better reflect learners’ mastery of knowledge points.","PeriodicalId":269605,"journal":{"name":"2022 Prognostics and Health Management Conference (PHM-2022 London)","volume":"1 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2022-05-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"116214653","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 : 2022-05-01DOI: 10.1109/PHM2022-London52454.2022.00028
R. K. Mishra, Anurag Choudhary, A. Mohanty, S. Fatima
Rotating elements are the essential part of various industries. Progressive degradation of rotating parts leads to system failure and economic losses. Several studies have been carried out to diagnose incipient faults in rotating components using the knowledge-based self-diagnosis Machine Learning (ML) models. But in real scenarios expecting the occurrence of one fault at a time is very unlikely. Multiple components and subcomponent faults take place simultaneously in a system. In most industries, machine parts are replaced directly to avoid downtime. Hence detection of multi-faults at a system level is very much important. In this paper, two major rotating components (motor and bearing) were considered, and all possible multi-fault conditions were simulated under different speed and load conditions. The raw vibration signals were acquired from three different locations and used directly for the training of the Support Vector Machine (SVM) model. The highest classification accuracy of 100% was achieved for the multi-fault diagnosis. Performance evaluation of the SVM model was done using eleven different performance matrixes. The model showed a greater potential to identify different multi-faults using the raw signal without using any further data processing or feature engineering techniques.
{"title":"Performance Evaluation of Support Vector Machine for System Level Multi-fault Diagnosis","authors":"R. K. Mishra, Anurag Choudhary, A. Mohanty, S. Fatima","doi":"10.1109/PHM2022-London52454.2022.00028","DOIUrl":"https://doi.org/10.1109/PHM2022-London52454.2022.00028","url":null,"abstract":"Rotating elements are the essential part of various industries. Progressive degradation of rotating parts leads to system failure and economic losses. Several studies have been carried out to diagnose incipient faults in rotating components using the knowledge-based self-diagnosis Machine Learning (ML) models. But in real scenarios expecting the occurrence of one fault at a time is very unlikely. Multiple components and subcomponent faults take place simultaneously in a system. In most industries, machine parts are replaced directly to avoid downtime. Hence detection of multi-faults at a system level is very much important. In this paper, two major rotating components (motor and bearing) were considered, and all possible multi-fault conditions were simulated under different speed and load conditions. The raw vibration signals were acquired from three different locations and used directly for the training of the Support Vector Machine (SVM) model. The highest classification accuracy of 100% was achieved for the multi-fault diagnosis. Performance evaluation of the SVM model was done using eleven different performance matrixes. The model showed a greater potential to identify different multi-faults using the raw signal without using any further data processing or feature engineering techniques.","PeriodicalId":269605,"journal":{"name":"2022 Prognostics and Health Management Conference (PHM-2022 London)","volume":"31 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2022-05-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"122487779","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 : 2022-05-01DOI: 10.1109/PHM2022-London52454.2022.00014
Yangyang Ding, Jieming Yin, Wenlin Liao, Liu Hong
As one of the most used fundamental components, the plate structure is commonly employed in the civil and mechanical engineering fields. However, due to the harsh external environmental impact or manual factors, plate structures may be damaged during their design service life, which even threatens the safe operation of the overall system. Therefore, it is necessary to develop the health condition monitoring technique to diagnose the defect for the plate structure. In this paper, a theoretical model of the plate structure is derived based on the perturbation method to study the changes of the modal characteristics caused by the structural damages. It is found that the variation of strain mode shapes is sensitive to the damages. Based on this fact, a response-only diagnostic system for the plate structure is proposed that applies a fiber Bragg grating based strain sensing network to capture the dynamic response and then obtain the strain mode information from the captured response to locate the damage position. The performance of the proposed diagnostic system is validated by a laboratory test bed.
{"title":"A damage detection method for plate structures based on dynamic strain measurements","authors":"Yangyang Ding, Jieming Yin, Wenlin Liao, Liu Hong","doi":"10.1109/PHM2022-London52454.2022.00014","DOIUrl":"https://doi.org/10.1109/PHM2022-London52454.2022.00014","url":null,"abstract":"As one of the most used fundamental components, the plate structure is commonly employed in the civil and mechanical engineering fields. However, due to the harsh external environmental impact or manual factors, plate structures may be damaged during their design service life, which even threatens the safe operation of the overall system. Therefore, it is necessary to develop the health condition monitoring technique to diagnose the defect for the plate structure. In this paper, a theoretical model of the plate structure is derived based on the perturbation method to study the changes of the modal characteristics caused by the structural damages. It is found that the variation of strain mode shapes is sensitive to the damages. Based on this fact, a response-only diagnostic system for the plate structure is proposed that applies a fiber Bragg grating based strain sensing network to capture the dynamic response and then obtain the strain mode information from the captured response to locate the damage position. The performance of the proposed diagnostic system is validated by a laboratory test bed.","PeriodicalId":269605,"journal":{"name":"2022 Prognostics and Health Management Conference (PHM-2022 London)","volume":"1 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2022-05-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"125997215","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 : 2022-05-01DOI: 10.1109/PHM2022-London52454.2022.00032
X. Shu, Shigang Zhang, Yue Li, G. Shen, Peiyi Liu, Gu Ran
This study proposes a method of anomaly detection based on a combination of distance correlation coefficient-based feature selection algorithm and autoencoder. In this paper, we use the distance correlation coefficient to analyze the correlation of the original feature set, and divides the feature set into multiple feature subsets according to the correlation between features. The features within each feature subset are filtered by the constructed feature representativeness evaluation indexes to remove redundant features. Then, we built a convolutional denoising autoencoder to enhance the anomaly detection ability of the autoencoder in the time dimension. In the constructed autoencoder, a modular design approach is used to divide the encoder and decoder structures into encoding and decoding units, and the accuracy of fitting the network to the training data can be tuned by adjusting the number of these two units. Finally, the proposed method is validated with a turbofan engine. The results show that the proposed method outperforms other traditional methods in accuracy and has application value.
{"title":"Research on anomaly detection method combining distance correlation coefficient and autoencode","authors":"X. Shu, Shigang Zhang, Yue Li, G. Shen, Peiyi Liu, Gu Ran","doi":"10.1109/PHM2022-London52454.2022.00032","DOIUrl":"https://doi.org/10.1109/PHM2022-London52454.2022.00032","url":null,"abstract":"This study proposes a method of anomaly detection based on a combination of distance correlation coefficient-based feature selection algorithm and autoencoder. In this paper, we use the distance correlation coefficient to analyze the correlation of the original feature set, and divides the feature set into multiple feature subsets according to the correlation between features. The features within each feature subset are filtered by the constructed feature representativeness evaluation indexes to remove redundant features. Then, we built a convolutional denoising autoencoder to enhance the anomaly detection ability of the autoencoder in the time dimension. In the constructed autoencoder, a modular design approach is used to divide the encoder and decoder structures into encoding and decoding units, and the accuracy of fitting the network to the training data can be tuned by adjusting the number of these two units. Finally, the proposed method is validated with a turbofan engine. The results show that the proposed method outperforms other traditional methods in accuracy and has application value.","PeriodicalId":269605,"journal":{"name":"2022 Prognostics and Health Management Conference (PHM-2022 London)","volume":"9 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2022-05-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"126409180","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 : 2022-05-01DOI: 10.1109/PHM2022-London52454.2022.00080
Shaoqiang Li
In this paper, the solution based on fuzzy logic is proposed to optimize the recognition accuracy, and fuzzy reasoning does not need to consider the mathematical model of the problem, so as to realize the imitation of human thinking process to deal with the problem, and solve the problem according to different fuzzy rules. Fuzzy logic is good at processing fuzzy information and is widely used in fuzzy control, fuzzy neural network, fuzzy decision making and many other fields. This scheme improves the accuracy of character recognition, and the recognition effect is proved to be ideal by experimental simulation. The author designed license plate recognition system based on Android platform, and applied the optimized recognition algorithm to license plate recognition to improve the convenience and accuracy of license plate recognition.
{"title":"Android Mobile Platform Image Processing System Development Based on Fuzzy Logic Enhancement","authors":"Shaoqiang Li","doi":"10.1109/PHM2022-London52454.2022.00080","DOIUrl":"https://doi.org/10.1109/PHM2022-London52454.2022.00080","url":null,"abstract":"In this paper, the solution based on fuzzy logic is proposed to optimize the recognition accuracy, and fuzzy reasoning does not need to consider the mathematical model of the problem, so as to realize the imitation of human thinking process to deal with the problem, and solve the problem according to different fuzzy rules. Fuzzy logic is good at processing fuzzy information and is widely used in fuzzy control, fuzzy neural network, fuzzy decision making and many other fields. This scheme improves the accuracy of character recognition, and the recognition effect is proved to be ideal by experimental simulation. The author designed license plate recognition system based on Android platform, and applied the optimized recognition algorithm to license plate recognition to improve the convenience and accuracy of license plate recognition.","PeriodicalId":269605,"journal":{"name":"2022 Prognostics and Health Management Conference (PHM-2022 London)","volume":"15 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2022-05-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"127962386","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}
Power Electronic Systems (PES) is widely used in energy sectors such as renewable energy and aerospace. It is very important to design a reliable PES health monitoring system. This paper provides a new condition monitoring method based on Physics-informed Neural Network (PINN). Although the actual PES has a complex topology and is in a dynamically changing operating environment, the operation process does not violate the circuit physical models. Considering the charge and discharge process in the DC-DC converter, the physical formula is derived through the state-space average method. Then the physical formula is added to the deep learning model of LSTM as prior knowledge, to estimate the degradation parameters of the DC-DC converter. The uncertainty method is used to determine the weighting coefficients for data fitting and physical information fitting tasks. The PINN method can improve the estimation accuracy and generalization ability of the model in the case of limited data, which is conducive to the realization of the condition monitoring of complex PES. It is significant to improve the reliability of new energy vehicles and military equipment.
{"title":"Circuit Parameter Identification of Degrading DC-DC Converters Based on Physics-informed Neural Network","authors":"Shaowei Chen, Jinling Zhang, Shengyue Wang, Pengfei Wen, Shuai Zhao","doi":"10.1109/PHM2022-London52454.2022.00053","DOIUrl":"https://doi.org/10.1109/PHM2022-London52454.2022.00053","url":null,"abstract":"Power Electronic Systems (PES) is widely used in energy sectors such as renewable energy and aerospace. It is very important to design a reliable PES health monitoring system. This paper provides a new condition monitoring method based on Physics-informed Neural Network (PINN). Although the actual PES has a complex topology and is in a dynamically changing operating environment, the operation process does not violate the circuit physical models. Considering the charge and discharge process in the DC-DC converter, the physical formula is derived through the state-space average method. Then the physical formula is added to the deep learning model of LSTM as prior knowledge, to estimate the degradation parameters of the DC-DC converter. The uncertainty method is used to determine the weighting coefficients for data fitting and physical information fitting tasks. The PINN method can improve the estimation accuracy and generalization ability of the model in the case of limited data, which is conducive to the realization of the condition monitoring of complex PES. It is significant to improve the reliability of new energy vehicles and military equipment.","PeriodicalId":269605,"journal":{"name":"2022 Prognostics and Health Management Conference (PHM-2022 London)","volume":"1 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2022-05-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"130687996","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 : 2022-05-01DOI: 10.1109/PHM2022-London52454.2022.00010
Xiaopu Zhang, Zhenbang Lv, Qian Sun
Traditional vibration fault diagnosis methods include wavelet transform, modal analysis and so on. It is found that the instantaneous impact components associated with the fault in the engine bearing vibration signals are sparse in the time-frequency transform domain. For this property, a sparse signal representation using dictionary learning based on EMD decomposition and a sparse signal reconstruction method based on orthogonal matching pursuit (OMP) algorithm are proposed in this paper. Firstly, empirical mode decomposition (EMD) and wavelet denoising methods are used to pre-process the vibration signal to eliminate the harmonic and noise interference; Secondly, a super complete dictionary is constructed by using singular value decomposition algorithm to achieve the sparse representation of the signal; Finally, the sparse reconstruction of fault features is realized by using orthogonal matching pursuit algorithm. Simulation and experimental results show that the proposed method can reduce the interference of background noise and impurity frequency more effectively, and verify the effectiveness and applicability of the proposed method for aero-engine bearing fault feature extraction.
{"title":"A New Method of Aero-engine Bearing Fault Diagnosis Based on EMD Decomposition","authors":"Xiaopu Zhang, Zhenbang Lv, Qian Sun","doi":"10.1109/PHM2022-London52454.2022.00010","DOIUrl":"https://doi.org/10.1109/PHM2022-London52454.2022.00010","url":null,"abstract":"Traditional vibration fault diagnosis methods include wavelet transform, modal analysis and so on. It is found that the instantaneous impact components associated with the fault in the engine bearing vibration signals are sparse in the time-frequency transform domain. For this property, a sparse signal representation using dictionary learning based on EMD decomposition and a sparse signal reconstruction method based on orthogonal matching pursuit (OMP) algorithm are proposed in this paper. Firstly, empirical mode decomposition (EMD) and wavelet denoising methods are used to pre-process the vibration signal to eliminate the harmonic and noise interference; Secondly, a super complete dictionary is constructed by using singular value decomposition algorithm to achieve the sparse representation of the signal; Finally, the sparse reconstruction of fault features is realized by using orthogonal matching pursuit algorithm. Simulation and experimental results show that the proposed method can reduce the interference of background noise and impurity frequency more effectively, and verify the effectiveness and applicability of the proposed method for aero-engine bearing fault feature extraction.","PeriodicalId":269605,"journal":{"name":"2022 Prognostics and Health Management Conference (PHM-2022 London)","volume":"77 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2022-05-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"128619842","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：