Pub Date : 2022-10-13DOI: 10.1109/PHM-Yantai55411.2022.9941937
Xiaofang Huang, LingXiang Liu, Li Xie
The conventional evaluation method is to give weight according to the subjective feelings of experts and scholars, and often different people have different judgments or even different views on the weight of a certain index, and the evaluation results will lack recognition at this time. This paper designs an evaluation algorithm of vocational undergraduate education quality based on entropy weight method. According to the evaluation principles, the evaluation system is constructed and the evaluation data is collected. The entropy weight method is used to calculate the index weight, and the result is multiplied with the decision matrix to obtain the optimal solution and the worst solution of the index, calculate the closeness between the optimal solution and the evaluation value, and take it as the evaluation result. The experimental results show that the algorithm can accurately evaluate the quality of vocational undergraduate education and provide reference for educational decision-making.
{"title":"Evaluation Algorithm of Vocational Undergraduate Education Quality Based on Entropy Weight Method","authors":"Xiaofang Huang, LingXiang Liu, Li Xie","doi":"10.1109/PHM-Yantai55411.2022.9941937","DOIUrl":"https://doi.org/10.1109/PHM-Yantai55411.2022.9941937","url":null,"abstract":"The conventional evaluation method is to give weight according to the subjective feelings of experts and scholars, and often different people have different judgments or even different views on the weight of a certain index, and the evaluation results will lack recognition at this time. This paper designs an evaluation algorithm of vocational undergraduate education quality based on entropy weight method. According to the evaluation principles, the evaluation system is constructed and the evaluation data is collected. The entropy weight method is used to calculate the index weight, and the result is multiplied with the decision matrix to obtain the optimal solution and the worst solution of the index, calculate the closeness between the optimal solution and the evaluation value, and take it as the evaluation result. The experimental results show that the algorithm can accurately evaluate the quality of vocational undergraduate education and provide reference for educational decision-making.","PeriodicalId":315994,"journal":{"name":"2022 Global Reliability and Prognostics and Health Management (PHM-Yantai)","volume":"19 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2022-10-13","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"129395088","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 : 2022-10-13DOI: 10.1109/phm-yantai55411.2022.9942136
Yanbo Zhang, G. Lu
With the development of computer technology, machine vision plays an increasingly important function in industrial detection, and light source is a very important part of it. At present, most of the light sources are based on a single way of illumination, which results in limitations in the detection of multiple types of defects on 3D optical surfaces (such as lenses). Therefore, the images acquired by industrial cameras cannot fully present these defect information. In order to overcome the above problems, this article proposes an intelligent method of composite light source fusion image processing, which realizes high-quality imaging of multi-defect targets. Finally, an experimental verification system is built to verify the effectiveness of the method proposed in this article.
{"title":"An Imaging Method for Sculptured Surface Defect Detection Based on Compound Lighting and Image Fusion","authors":"Yanbo Zhang, G. Lu","doi":"10.1109/phm-yantai55411.2022.9942136","DOIUrl":"https://doi.org/10.1109/phm-yantai55411.2022.9942136","url":null,"abstract":"With the development of computer technology, machine vision plays an increasingly important function in industrial detection, and light source is a very important part of it. At present, most of the light sources are based on a single way of illumination, which results in limitations in the detection of multiple types of defects on 3D optical surfaces (such as lenses). Therefore, the images acquired by industrial cameras cannot fully present these defect information. In order to overcome the above problems, this article proposes an intelligent method of composite light source fusion image processing, which realizes high-quality imaging of multi-defect targets. Finally, an experimental verification system is built to verify the effectiveness of the method proposed in this article.","PeriodicalId":315994,"journal":{"name":"2022 Global Reliability and Prognostics and Health Management (PHM-Yantai)","volume":"37 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2022-10-13","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"128890724","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 : 2022-10-13DOI: 10.1109/PHM-Yantai55411.2022.9942013
Shuang Chen, Xi Yang, Zhen Gao, Xun Cui, Rong Liang, Lan Cheng
In order to better guarantee the operation effect of substation, a substation telecontrol fast point-to-point system based on Naive Bayesian algorithm is designed. The hardware structure configuration of the system is designed, the system software function is improved, and the fast point-to-point steps of substation telecontrol are simplified. And the experiment proves that the performance of the substation telecontrol fast point-to-point system based on Naive Bayesian algorithm is significantly improved, which can better ensure the operation safety of the substation.
{"title":"Substation Telecontrol Fast Stable Point-to-Point System Based on Naive Bayesian Algorithm","authors":"Shuang Chen, Xi Yang, Zhen Gao, Xun Cui, Rong Liang, Lan Cheng","doi":"10.1109/PHM-Yantai55411.2022.9942013","DOIUrl":"https://doi.org/10.1109/PHM-Yantai55411.2022.9942013","url":null,"abstract":"In order to better guarantee the operation effect of substation, a substation telecontrol fast point-to-point system based on Naive Bayesian algorithm is designed. The hardware structure configuration of the system is designed, the system software function is improved, and the fast point-to-point steps of substation telecontrol are simplified. And the experiment proves that the performance of the substation telecontrol fast point-to-point system based on Naive Bayesian algorithm is significantly improved, which can better ensure the operation safety of the substation.","PeriodicalId":315994,"journal":{"name":"2022 Global Reliability and Prognostics and Health Management (PHM-Yantai)","volume":"24 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2022-10-13","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"132177383","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 : 2022-10-13DOI: 10.1109/PHM-Yantai55411.2022.9942186
Xinjiu Liang, Shuilan Song
In order to improve the recommendation accuracy of teaching resources, a recommendation algorithm for campus cultural education resources based on collaborative filtering is designed. The method proposes to build a user interest model, dynamically fine-tune the teacher and student models as the amount of data continues to increase, and acquire students' interest models in a course in real time. Based on the collaborative filtering algorithm, the similarity of recommended resources is calculated, and the similarity between students' interests and the course is calculated; the recommendation algorithm of campus cultural education resources is designed, and the recommendation method of teaching resources is obtained. Comparing several different resource recommendation algorithms, it can be seen from the experimental data that when the similarity threshold is the same, the accuracy of the collaborative filtering method is the maximum among the three comparison methods, and the recall rate is the minimum. The average absolute error of the four algorithms can reach the minimum value when the similarity threshold is 0.3-0.4. At this time, the error value of the collaborative filtering method is 0.62, and the average absolute errors of the other two methods are 0.63 and 0.88, respectively. It can be seen that the recommendation accuracy of this method is better than the other two methods.
{"title":"A Robust Recommendation Algorithm for Campus Cultural Education Resources Based on Collaborative Filtering","authors":"Xinjiu Liang, Shuilan Song","doi":"10.1109/PHM-Yantai55411.2022.9942186","DOIUrl":"https://doi.org/10.1109/PHM-Yantai55411.2022.9942186","url":null,"abstract":"In order to improve the recommendation accuracy of teaching resources, a recommendation algorithm for campus cultural education resources based on collaborative filtering is designed. The method proposes to build a user interest model, dynamically fine-tune the teacher and student models as the amount of data continues to increase, and acquire students' interest models in a course in real time. Based on the collaborative filtering algorithm, the similarity of recommended resources is calculated, and the similarity between students' interests and the course is calculated; the recommendation algorithm of campus cultural education resources is designed, and the recommendation method of teaching resources is obtained. Comparing several different resource recommendation algorithms, it can be seen from the experimental data that when the similarity threshold is the same, the accuracy of the collaborative filtering method is the maximum among the three comparison methods, and the recall rate is the minimum. The average absolute error of the four algorithms can reach the minimum value when the similarity threshold is 0.3-0.4. At this time, the error value of the collaborative filtering method is 0.62, and the average absolute errors of the other two methods are 0.63 and 0.88, respectively. It can be seen that the recommendation accuracy of this method is better than the other two methods.","PeriodicalId":315994,"journal":{"name":"2022 Global Reliability and Prognostics and Health Management (PHM-Yantai)","volume":"1 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2022-10-13","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"130813472","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}
Railway bridge is an important infrastructure along the railway, which needs regular inspection and maintenance. Using UAV technology to inspect railway infrastructure is a hot issue in current research. However, because of the detection target of steel structure of railway bridge girder, such as bolts, rust, etc., are small and dense targets, and the manual annotation workload is huge in the early stage. Therefore, this paper first proposes a method for constructing the sample set of semi-automatic annotation of railway bridge defects, which can greatly improve the efficiency of data annotation. Secondly, in order to solve the problem that it is difficult to detect large-scale images of UAV and the target scale changes dramatically due to the flight distance and height changes, this paper proposes an adaptive cropping strategy for image of steel structure UAV of railway bridge girder. Compared with YOLOv5s that does not adopt the strategy, its mAP improves by 32%. In order to reduce the GPU memory usage and the number of parameters, and improve the parallel running efficiency of the model, the GYOLOv5 model is proposed by combining Ghost Bottleneck and SIoU loss function. Compared with YOLOv5s, which also adopts the adaptive cropping strategy, the mAP of GYOLOv5 model increases by 6%, and the number of parameters can be reduced by 1.7 million. Finally, in order to help the network to find the region of interest in the images covered by the UAV and improve the detection accuracy, the Attention mechanism of CBAM (Convolutional Block Attention Module) is combined with YOLOv5s. Compared with the original YOLOv5s model, the number of parameters is only 600, but the total mAP is increased by 12%.
{"title":"UAV image defect detection method for steel structure of high-speed railway bridge girder","authors":"Zonghan Mu, Yong Qin, Chongchong Yu, Huaizhi Yang, Ninghai Qiu","doi":"10.1109/PHM-Yantai55411.2022.9942099","DOIUrl":"https://doi.org/10.1109/PHM-Yantai55411.2022.9942099","url":null,"abstract":"Railway bridge is an important infrastructure along the railway, which needs regular inspection and maintenance. Using UAV technology to inspect railway infrastructure is a hot issue in current research. However, because of the detection target of steel structure of railway bridge girder, such as bolts, rust, etc., are small and dense targets, and the manual annotation workload is huge in the early stage. Therefore, this paper first proposes a method for constructing the sample set of semi-automatic annotation of railway bridge defects, which can greatly improve the efficiency of data annotation. Secondly, in order to solve the problem that it is difficult to detect large-scale images of UAV and the target scale changes dramatically due to the flight distance and height changes, this paper proposes an adaptive cropping strategy for image of steel structure UAV of railway bridge girder. Compared with YOLOv5s that does not adopt the strategy, its mAP improves by 32%. In order to reduce the GPU memory usage and the number of parameters, and improve the parallel running efficiency of the model, the GYOLOv5 model is proposed by combining Ghost Bottleneck and SIoU loss function. Compared with YOLOv5s, which also adopts the adaptive cropping strategy, the mAP of GYOLOv5 model increases by 6%, and the number of parameters can be reduced by 1.7 million. Finally, in order to help the network to find the region of interest in the images covered by the UAV and improve the detection accuracy, the Attention mechanism of CBAM (Convolutional Block Attention Module) is combined with YOLOv5s. Compared with the original YOLOv5s model, the number of parameters is only 600, but the total mAP is increased by 12%.","PeriodicalId":315994,"journal":{"name":"2022 Global Reliability and Prognostics and Health Management (PHM-Yantai)","volume":"1 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2022-10-13","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"130437403","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 : 2022-10-13DOI: 10.1109/PHM-Yantai55411.2022.9941836
Y. Jia, J. Yuan, Xiao Dong Wang
As an energy storage component, capacitor is widely used in the field of aerospace. Surface mounted capacitor has the characteristics of small volume and easy to automatic assembly. But it is extremely sensitive to mechanical stress and thermal stress, failing frequently in the harsh environment of aerospace. In this paper, we used the steady-state thermal module and static structure module of ANSYS to carry out the thermal simulation and vibration simulation analysis of tantalum capacitor, and the maximum and minimum stress under different solder joint process parameters were obtained. Based on the simulation results, the thermal fatigue life of solder joint was calculated by Darveaux fatigue model, and the vibration fatigue life of the solder joint was evaluated by S-N double logarithm vibration fatigue curve. The highest life of solder joint was selected as the optimal combination of solder joint process parameters. In this paper, the optimal solder joint process parameters of tantalum capacitors were analyzed, which can guide the improvement of capacitor assembly process.
{"title":"Simulation Analysis of The Optimal Process Parameters of Surface Mount Capacitor","authors":"Y. Jia, J. Yuan, Xiao Dong Wang","doi":"10.1109/PHM-Yantai55411.2022.9941836","DOIUrl":"https://doi.org/10.1109/PHM-Yantai55411.2022.9941836","url":null,"abstract":"As an energy storage component, capacitor is widely used in the field of aerospace. Surface mounted capacitor has the characteristics of small volume and easy to automatic assembly. But it is extremely sensitive to mechanical stress and thermal stress, failing frequently in the harsh environment of aerospace. In this paper, we used the steady-state thermal module and static structure module of ANSYS to carry out the thermal simulation and vibration simulation analysis of tantalum capacitor, and the maximum and minimum stress under different solder joint process parameters were obtained. Based on the simulation results, the thermal fatigue life of solder joint was calculated by Darveaux fatigue model, and the vibration fatigue life of the solder joint was evaluated by S-N double logarithm vibration fatigue curve. The highest life of solder joint was selected as the optimal combination of solder joint process parameters. In this paper, the optimal solder joint process parameters of tantalum capacitors were analyzed, which can guide the improvement of capacitor assembly process.","PeriodicalId":315994,"journal":{"name":"2022 Global Reliability and Prognostics and Health Management (PHM-Yantai)","volume":"13 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2022-10-13","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"130511307","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 : 2022-10-13DOI: 10.1109/PHM-Yantai55411.2022.9942058
Yuanting Lu, Weiwei Zhang, Lingming Cao
There is a certain correlation between the keys in the process of e-commerce transaction data encryption, and due to the large data, the encryption time is too long, leaving serious security risks. In order to solve this problem, this paper designs a secure encryption method of electronic commerce transaction data based on improved AES algorithm. Firstly, the e-commerce transaction mode is analyzed, and multiple private chains are established to realize transaction processing. In the database, each enterprise uses its own certificate to generate the key of AES encryption algorithm. Affine transformation is used to transform the affine S-box of AES encryption algorithm, and use pseudo-random number key stream to realize data encryption and decryption. So far, the design of secure encryption method for e-commerce transaction data has been completed. The experimental results show that this method can shorten the data encryption time and has certain application value.
{"title":"Data Security Encryption Method Based on Improved AES Algorithm","authors":"Yuanting Lu, Weiwei Zhang, Lingming Cao","doi":"10.1109/PHM-Yantai55411.2022.9942058","DOIUrl":"https://doi.org/10.1109/PHM-Yantai55411.2022.9942058","url":null,"abstract":"There is a certain correlation between the keys in the process of e-commerce transaction data encryption, and due to the large data, the encryption time is too long, leaving serious security risks. In order to solve this problem, this paper designs a secure encryption method of electronic commerce transaction data based on improved AES algorithm. Firstly, the e-commerce transaction mode is analyzed, and multiple private chains are established to realize transaction processing. In the database, each enterprise uses its own certificate to generate the key of AES encryption algorithm. Affine transformation is used to transform the affine S-box of AES encryption algorithm, and use pseudo-random number key stream to realize data encryption and decryption. So far, the design of secure encryption method for e-commerce transaction data has been completed. The experimental results show that this method can shorten the data encryption time and has certain application value.","PeriodicalId":315994,"journal":{"name":"2022 Global Reliability and Prognostics and Health Management (PHM-Yantai)","volume":"43 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2022-10-13","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"127861298","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 : 2022-10-13DOI: 10.1109/PHM-Yantai55411.2022.9941759
Xun Dong, Gang Niu
Motor is the pillar of industrial development, and the motor diagnosis method based on current signal analysis is gaining popularity due to its non-invasive nature. In order to solve the incipient fault diagnosis problem of induction motor based on current signal, a method based on Frequency-domain Teager Energy Operator(FTEO) and Square Envelope Spectrum(SES) is proposed. To begin, a notch filter is used to remove the supply frequency in the current signal. Second, the instantaneous amplitude and frequency are calculated and the energy operator is calculated in the frequency domain. Finally, the energy operator is processed by Square Envelope Spectrum and then compared with the fault characteristic frequency of each component of induction motor, so as to realize the accurate identification of incipient faults. In order to verify the effectiveness of the proposed method, different degrees of bearing damage and rotor broken bar are injected into the motor towing test rig to obtain the stator current dataset, and the incipient failure detection performance of the proposed method is verified by comparing with that of the unimproved method.
{"title":"Incipient Fault Diagnosis of Asynchronous Motor Based on Stator Current Signal Analysis","authors":"Xun Dong, Gang Niu","doi":"10.1109/PHM-Yantai55411.2022.9941759","DOIUrl":"https://doi.org/10.1109/PHM-Yantai55411.2022.9941759","url":null,"abstract":"Motor is the pillar of industrial development, and the motor diagnosis method based on current signal analysis is gaining popularity due to its non-invasive nature. In order to solve the incipient fault diagnosis problem of induction motor based on current signal, a method based on Frequency-domain Teager Energy Operator(FTEO) and Square Envelope Spectrum(SES) is proposed. To begin, a notch filter is used to remove the supply frequency in the current signal. Second, the instantaneous amplitude and frequency are calculated and the energy operator is calculated in the frequency domain. Finally, the energy operator is processed by Square Envelope Spectrum and then compared with the fault characteristic frequency of each component of induction motor, so as to realize the accurate identification of incipient faults. In order to verify the effectiveness of the proposed method, different degrees of bearing damage and rotor broken bar are injected into the motor towing test rig to obtain the stator current dataset, and the incipient failure detection performance of the proposed method is verified by comparing with that of the unimproved method.","PeriodicalId":315994,"journal":{"name":"2022 Global Reliability and Prognostics and Health Management (PHM-Yantai)","volume":"65 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2022-10-13","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"131733662","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 : 2022-10-13DOI: 10.1109/PHM-Yantai55411.2022.9942086
Haoxuan Wei, Zhongxun Wang, Hao Ding, Yong Huang
Constant false alarm rate (CFAR) detector is the key device in radar system, which usually needs two-dimensional processing for sea surface scene. In order to improve the detection ability and accuracy of the detector, an improved two-dimensional CFAR detection window is proposed by optimizing the selection rules of reference cells. The performance of the window is tested with simulated data and measured data. Among them, the processing of measured data is realized based on Zynq platform, and the overall scheme of radar data reading, writing and processing is innovatively designed, whose working stability and processing accuracy meet the requirements. CFAR detection results indicate that the improved reference window can effectively improve the ability of sea surface target detection and false alarm suppression, which shows certain engineering application value.
{"title":"Design of Improved Reference Window for 2D CFAR and Implementation on Zynq","authors":"Haoxuan Wei, Zhongxun Wang, Hao Ding, Yong Huang","doi":"10.1109/PHM-Yantai55411.2022.9942086","DOIUrl":"https://doi.org/10.1109/PHM-Yantai55411.2022.9942086","url":null,"abstract":"Constant false alarm rate (CFAR) detector is the key device in radar system, which usually needs two-dimensional processing for sea surface scene. In order to improve the detection ability and accuracy of the detector, an improved two-dimensional CFAR detection window is proposed by optimizing the selection rules of reference cells. The performance of the window is tested with simulated data and measured data. Among them, the processing of measured data is realized based on Zynq platform, and the overall scheme of radar data reading, writing and processing is innovatively designed, whose working stability and processing accuracy meet the requirements. CFAR detection results indicate that the improved reference window can effectively improve the ability of sea surface target detection and false alarm suppression, which shows certain engineering application value.","PeriodicalId":315994,"journal":{"name":"2022 Global Reliability and Prognostics and Health Management (PHM-Yantai)","volume":"1 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2022-10-13","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"129177584","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 : 2022-10-13DOI: 10.1109/PHM-Yantai55411.2022.9942059
Yun Kong, Fulei Chu
Machinery intelligent diagnostics is taking on a key role in enabling smart operation and maintenance of modern industrial equipment, especially in the prospective era of industry 4.0. Sparse representation-assisted intelligent diagnostics (SR-ID) framework shows great prospects to obtain promising diagnostic performance without designing complex deep network architectures compared with deep learning models. However, the existing SR-ID approach still suffers to obtain superior and robust diagnostic accuracy in noisy circumstances. To tackle this challenge, a novel enhanced dictionary design-based sparse classification (EDD-SC) scheme is developed in this study, which comprises of enhanced dictionary design and intelligent health diagnostics. Firstly, the periodic similarity of vibration data is leveraged to fuse the physical priori information with dictionary design, thus enhancing reconstruction capability of EDD-SC. Secondly, a minimal sparse approximation error strategy is developed to accomplish superior health diagnosis. The presented EDD-SC scheme has been detailedly verified on the challenging task of planetary drivetrain fault diagnostics, showing that EDD-SC can yield robust and superior diagnostic results even in comparison to several state-of-the-art benchmarks. This work has provided a promising framework and paved a new direction towards robust data-driven machinery intelligent diagnostics.
{"title":"Enhanced Dictionary Design-based Sparse Classification Scheme Towards Machinery Intelligent Diagnostics","authors":"Yun Kong, Fulei Chu","doi":"10.1109/PHM-Yantai55411.2022.9942059","DOIUrl":"https://doi.org/10.1109/PHM-Yantai55411.2022.9942059","url":null,"abstract":"Machinery intelligent diagnostics is taking on a key role in enabling smart operation and maintenance of modern industrial equipment, especially in the prospective era of industry 4.0. Sparse representation-assisted intelligent diagnostics (SR-ID) framework shows great prospects to obtain promising diagnostic performance without designing complex deep network architectures compared with deep learning models. However, the existing SR-ID approach still suffers to obtain superior and robust diagnostic accuracy in noisy circumstances. To tackle this challenge, a novel enhanced dictionary design-based sparse classification (EDD-SC) scheme is developed in this study, which comprises of enhanced dictionary design and intelligent health diagnostics. Firstly, the periodic similarity of vibration data is leveraged to fuse the physical priori information with dictionary design, thus enhancing reconstruction capability of EDD-SC. Secondly, a minimal sparse approximation error strategy is developed to accomplish superior health diagnosis. The presented EDD-SC scheme has been detailedly verified on the challenging task of planetary drivetrain fault diagnostics, showing that EDD-SC can yield robust and superior diagnostic results even in comparison to several state-of-the-art benchmarks. This work has provided a promising framework and paved a new direction towards robust data-driven machinery intelligent diagnostics.","PeriodicalId":315994,"journal":{"name":"2022 Global Reliability and Prognostics and Health Management (PHM-Yantai)","volume":"1 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2022-10-13","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"128815145","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：