Aiming at the rubbing fault of tilting pad sliding bearing of heavy gas turbine, acoustic emission sensor, eddy current sensor and acceleration sensor are used as measuring means to observe the rubbing phenomenon between tilting pad and journal. The rubbing test is carried out on the gas turbine molded rotor-tilting pad bearing test bench. In the test, the failure phenomenon of tilting pad bearing segment instability is simulated. In the test, the segment will periodically rub against the journal, and the swing frequency of the failed segment is about 0.5 times of the rotation frequency of the journal. The test results show that the rubbing frequency of the faulty segment and journal is also about 0.5 times of the rotating frequency, and the rubbing position is at the edge of segment. According to the intensity of acoustic emission signals at different measuring points, the position of the fault segment can be judged.
{"title":"Experimental Study on Rubbing Failure of Tilting Pad Bearing in Heavy Duty Gas Turbine","authors":"Yongzhi Feng, Yushu Chen, Ning Yu, Fangang Meng, Qian Jia, Xiaoyang Yuan","doi":"10.1109/PHM-Yantai55411.2022.9941760","DOIUrl":"https://doi.org/10.1109/PHM-Yantai55411.2022.9941760","url":null,"abstract":"Aiming at the rubbing fault of tilting pad sliding bearing of heavy gas turbine, acoustic emission sensor, eddy current sensor and acceleration sensor are used as measuring means to observe the rubbing phenomenon between tilting pad and journal. The rubbing test is carried out on the gas turbine molded rotor-tilting pad bearing test bench. In the test, the failure phenomenon of tilting pad bearing segment instability is simulated. In the test, the segment will periodically rub against the journal, and the swing frequency of the failed segment is about 0.5 times of the rotation frequency of the journal. The test results show that the rubbing frequency of the faulty segment and journal is also about 0.5 times of the rotating frequency, and the rubbing position is at the edge of segment. According to the intensity of acoustic emission signals at different measuring points, the position of the fault segment can be judged.","PeriodicalId":315994,"journal":{"name":"2022 Global Reliability and Prognostics and Health Management (PHM-Yantai)","volume":"67 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":"127248908","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-Yantai55411.2022.9942210
Shuang Chen, Xi Yang, Zhen Gao, Xun Cui, Rong Liang, Lan Cheng
Because the traditional substation relay protection device automatic detection system has the problem of inaccurate detection results, the substation relay protection device automatic detection system based on the failure density function is designed. The hardware structure of the system is designed by the high-performance C8051F040 single chip microcomputer and the insulation detection sensor. On the basis of the system hardware design, the system software function is optimized. According to the relay protection current setting calculation flow, the genetic algorithm is derived to construct the failure density function, and the automatic detection of the relay protection device in the substation is carried out, Through the hardware design and software design of the system, the design of automatic detection system of substation relay protection device based on genetic algorithm is completed. The experimental results show that the designed system can detect the insulation voltage of positive and negative bus more accurately and has high practicability in the practical application process, which fully meets the research requirements.
{"title":"Automatic Detection System of Substation Relay Protection Device Based on Failure Density Function","authors":"Shuang Chen, Xi Yang, Zhen Gao, Xun Cui, Rong Liang, Lan Cheng","doi":"10.1109/PHM-Yantai55411.2022.9942210","DOIUrl":"https://doi.org/10.1109/PHM-Yantai55411.2022.9942210","url":null,"abstract":"Because the traditional substation relay protection device automatic detection system has the problem of inaccurate detection results, the substation relay protection device automatic detection system based on the failure density function is designed. The hardware structure of the system is designed by the high-performance C8051F040 single chip microcomputer and the insulation detection sensor. On the basis of the system hardware design, the system software function is optimized. According to the relay protection current setting calculation flow, the genetic algorithm is derived to construct the failure density function, and the automatic detection of the relay protection device in the substation is carried out, Through the hardware design and software design of the system, the design of automatic detection system of substation relay protection device based on genetic algorithm is completed. The experimental results show that the designed system can detect the insulation voltage of positive and negative bus more accurately and has high practicability in the practical application process, which fully meets the research requirements.","PeriodicalId":315994,"journal":{"name":"2022 Global Reliability and Prognostics and Health Management (PHM-Yantai)","volume":"15 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":"127276252","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-Yantai55411.2022.9942002
Dan Zhao, Ming-fei Qu
Aero engine is the focus of aero power research and development. Due to its complex structure, long development cycle and high scientific research investment, the cost and risk of engine test are high, and the advantages of 3D virtual design are reflected. For this reason, the aeroengine component model based on 3D virtual design is designed. This paper deeply analyzes the aeroengine exterior components, applies the 3D virtual technology to realize the 3D virtual visualization of aeroengine exterior components, and then establishes the exterior component model base through Virtual reality modeling language (VRML). Finally, the 3D virtual model of shape components is simplified based on Level of detail (LOD) algorithm. The experimental results show that compared with the given maximum limit, the design delay of the model in this paper is small, and the deviation between the model and the entity is small, indicating that the application performance of the model is good.
{"title":"Aeroengine Robust Component Model Design Based on 3D Virtual Design","authors":"Dan Zhao, Ming-fei Qu","doi":"10.1109/PHM-Yantai55411.2022.9942002","DOIUrl":"https://doi.org/10.1109/PHM-Yantai55411.2022.9942002","url":null,"abstract":"Aero engine is the focus of aero power research and development. Due to its complex structure, long development cycle and high scientific research investment, the cost and risk of engine test are high, and the advantages of 3D virtual design are reflected. For this reason, the aeroengine component model based on 3D virtual design is designed. This paper deeply analyzes the aeroengine exterior components, applies the 3D virtual technology to realize the 3D virtual visualization of aeroengine exterior components, and then establishes the exterior component model base through Virtual reality modeling language (VRML). Finally, the 3D virtual model of shape components is simplified based on Level of detail (LOD) algorithm. The experimental results show that compared with the given maximum limit, the design delay of the model in this paper is small, and the deviation between the model and the entity is small, indicating that the application performance of the model is good.","PeriodicalId":315994,"journal":{"name":"2022 Global Reliability and Prognostics and Health Management (PHM-Yantai)","volume":"79 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":"124842505","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-Yantai55411.2022.9941791
Zhenzhen Liu, Yan Liu, Hongfu Zuo, Han Wang, Hang Fei, Zhiqiang Jiang
The health status of an aero-engine provides the basic guarantee for the safe flight of an aircraft, and the oil monitoring technology based on oil wear particles analysis is a standard method in the field of aero-engine condition monitoring. This paper aims to design miniaturization, intelligence, and real-time monitoring equipment. Firstly, an experimental monitoring platform is built based on Raspberry Pi. Then images of moving particles flowing through the microfluidic chip are collected by image acquisition software. Finally, the target particles are accurately extracted, and parameters are calculated using significance analysis. The experimental results show that the system is easy to use and provides an efficient and accurate contour identification method, which can be used for intelligent industrial applications in aero-engines and large rotating machines.
{"title":"A Microfluidic Oil Particles Monitoring System based on Raspberry Pi","authors":"Zhenzhen Liu, Yan Liu, Hongfu Zuo, Han Wang, Hang Fei, Zhiqiang Jiang","doi":"10.1109/PHM-Yantai55411.2022.9941791","DOIUrl":"https://doi.org/10.1109/PHM-Yantai55411.2022.9941791","url":null,"abstract":"The health status of an aero-engine provides the basic guarantee for the safe flight of an aircraft, and the oil monitoring technology based on oil wear particles analysis is a standard method in the field of aero-engine condition monitoring. This paper aims to design miniaturization, intelligence, and real-time monitoring equipment. Firstly, an experimental monitoring platform is built based on Raspberry Pi. Then images of moving particles flowing through the microfluidic chip are collected by image acquisition software. Finally, the target particles are accurately extracted, and parameters are calculated using significance analysis. The experimental results show that the system is easy to use and provides an efficient and accurate contour identification method, which can be used for intelligent industrial applications in aero-engines and large rotating machines.","PeriodicalId":315994,"journal":{"name":"2022 Global Reliability and Prognostics and Health Management (PHM-Yantai)","volume":"111 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":"116016979","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}
Reliability analysis based on data from various source is common today. Bayes theory is proved effectively in integrating prior information and field information. However, the complicated calculation and limited applicability have a negative effect on solution. And the fusion is imbalanced in some case. This paper investigates a novel approach to integrate degradation data and lifetime data for reliability analysis. Firstly, inverse Gaussian process model is adopted to model the degradation and the crude estimation can be solved by degradation data. After that, a constrained maximum-entropy Bayesian integration model is proposed for exploring more information from reliability life test. For simplifying the calculation, a pivot variable, failure probability, is defined and updated in this model. This allows us to derive the model parameters by fitting the failure probability curve rather than the calculation on Bayes posterior distribution. Accordingly, the reliability assessment can be conducted based on the inverse Gaussian process model. A case study illustrates the validity and improvement of the proposed method.
{"title":"A Novel Maximum-Entropy Bayesian Integration Approach for Reliability Analysis","authors":"Bowen Li, Bingyi Li, Jiahui He, Hongbin Liu, X. Jia, B. Guo","doi":"10.1109/PHM-Yantai55411.2022.9942055","DOIUrl":"https://doi.org/10.1109/PHM-Yantai55411.2022.9942055","url":null,"abstract":"Reliability analysis based on data from various source is common today. Bayes theory is proved effectively in integrating prior information and field information. However, the complicated calculation and limited applicability have a negative effect on solution. And the fusion is imbalanced in some case. This paper investigates a novel approach to integrate degradation data and lifetime data for reliability analysis. Firstly, inverse Gaussian process model is adopted to model the degradation and the crude estimation can be solved by degradation data. After that, a constrained maximum-entropy Bayesian integration model is proposed for exploring more information from reliability life test. For simplifying the calculation, a pivot variable, failure probability, is defined and updated in this model. This allows us to derive the model parameters by fitting the failure probability curve rather than the calculation on Bayes posterior distribution. Accordingly, the reliability assessment can be conducted based on the inverse Gaussian process model. A case study illustrates the validity and improvement of the proposed method.","PeriodicalId":315994,"journal":{"name":"2022 Global Reliability and Prognostics and Health Management (PHM-Yantai)","volume":"26 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":"116551044","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-Yantai55411.2022.9942034
S. Han, Zhong-Min Wang
Based on the Regional Ocean Modeling System (ROMS) to simulate the water temperature in the Bohai Sea, the Yellow Sea and the East China Sea with high resolution. By processing and analyzing of the simulation results and comparison with WOA13 data and previous research data, it is proved that the ROMS model has a good simulation effect on seawater temperature. At the same time, the seasonal variation characteristic and distribution law of water temperature in the Bohai Sea, the Yellow Sea and the East China Sea are obtained.
{"title":"Simulation of seasonal variation characteristics of offshore water temperature based on ROMS model","authors":"S. Han, Zhong-Min Wang","doi":"10.1109/PHM-Yantai55411.2022.9942034","DOIUrl":"https://doi.org/10.1109/PHM-Yantai55411.2022.9942034","url":null,"abstract":"Based on the Regional Ocean Modeling System (ROMS) to simulate the water temperature in the Bohai Sea, the Yellow Sea and the East China Sea with high resolution. By processing and analyzing of the simulation results and comparison with WOA13 data and previous research data, it is proved that the ROMS model has a good simulation effect on seawater temperature. At the same time, the seasonal variation characteristic and distribution law of water temperature in the Bohai Sea, the Yellow Sea and the East China Sea are obtained.","PeriodicalId":315994,"journal":{"name":"2022 Global Reliability and Prognostics and Health Management (PHM-Yantai)","volume":"3 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":"114163443","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-Yantai55411.2022.9942208
Min Luo, Yimiao Yao
In order to solve the problem that the current importance measures cannot fully reflect the position of the components in rail transit vehicle, this paper proposes an importance measures method that considering system topology. Firstly, this method describes the topological structure of the system by complex network theory, and distinguishes different nodes by assigning attributes to them. Then, the improved grey relational analysis method is adopted to evaluate the importance of the components in the system by considering the properties of the components themselves and the statistical characteristics based on the complex network. Finally, the feasibility of the method is verified by a case study.
{"title":"A Component Importance Measure Considering System Topology","authors":"Min Luo, Yimiao Yao","doi":"10.1109/PHM-Yantai55411.2022.9942208","DOIUrl":"https://doi.org/10.1109/PHM-Yantai55411.2022.9942208","url":null,"abstract":"In order to solve the problem that the current importance measures cannot fully reflect the position of the components in rail transit vehicle, this paper proposes an importance measures method that considering system topology. Firstly, this method describes the topological structure of the system by complex network theory, and distinguishes different nodes by assigning attributes to them. Then, the improved grey relational analysis method is adopted to evaluate the importance of the components in the system by considering the properties of the components themselves and the statistical characteristics based on the complex network. Finally, the feasibility of the method is verified by a case study.","PeriodicalId":315994,"journal":{"name":"2022 Global Reliability and Prognostics and Health Management (PHM-Yantai)","volume":"23 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":"117013469","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-Yantai55411.2022.9942214
Xinjiu Liang, Shuilan Song
In view of the relatively poor index selection and sorting ability of the current comprehensive evaluation method of moral education in colleges and universities, which leads to serious distortion of the evaluation results, a comprehensive evaluation method of moral education in colleges and universities is proposed. Using the Viterbi method to analyze the factors that affect the quality of moral education of college students, an index system for the evaluation of moral education in colleges is established. Using the analytic hierarchy process, on this basis, the weight of the comprehensive evaluation index of university moral education is calculated. The fuzzy comprehensive evaluation method is used to construct a comprehensive evaluation model of moral education in colleges and universities, and obtain the evaluation results. So far, the design of the comprehensive evaluation method of moral education in colleges and universities based on the Viterbi algorithm is completed. The experimental link is constructed, and the experimental results confirm that the evaluation results of this method have high reliability and are better than the evaluation effect of the current method.
{"title":"Comprehensive Evaluation Method of Moral Education in Colleges And Universities Based on Viterbi Algorithm","authors":"Xinjiu Liang, Shuilan Song","doi":"10.1109/PHM-Yantai55411.2022.9942214","DOIUrl":"https://doi.org/10.1109/PHM-Yantai55411.2022.9942214","url":null,"abstract":"In view of the relatively poor index selection and sorting ability of the current comprehensive evaluation method of moral education in colleges and universities, which leads to serious distortion of the evaluation results, a comprehensive evaluation method of moral education in colleges and universities is proposed. Using the Viterbi method to analyze the factors that affect the quality of moral education of college students, an index system for the evaluation of moral education in colleges is established. Using the analytic hierarchy process, on this basis, the weight of the comprehensive evaluation index of university moral education is calculated. The fuzzy comprehensive evaluation method is used to construct a comprehensive evaluation model of moral education in colleges and universities, and obtain the evaluation results. So far, the design of the comprehensive evaluation method of moral education in colleges and universities based on the Viterbi algorithm is completed. The experimental link is constructed, and the experimental results confirm that the evaluation results of this method have high reliability and are better than the evaluation effect of the current method.","PeriodicalId":315994,"journal":{"name":"2022 Global Reliability and Prognostics and Health Management (PHM-Yantai)","volume":"55 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":"129785217","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-yantai55411.2022.9942104
Boyang Zhao, Tong Li, Wei Dai, Junjun Dong
Data-driven intelligent fault diagnosis is now a research hotspot. However, the fault data collected in actual working conditions is limited, which leads to a decline in the diagnostic ability of fault diagnosis models that rely on balanced data in actual engineering. Fortunately, the zero-shot problem for some fault classes can be solved by transferring zero-shot learning from machine vision to rotating machinery fault diagnosis. Inspired by this, we propose an attribute description method based on Failure Mode and Effects Analysis (FMEA) to solve the problem of semantic description of rotating machinery fault data, so as to be used for zero-shot fault diagnosis of rotating machinery. The framework analyzes the failure modes of rotating machinery based on FMEA, and establishes a fault attribute dictionary. After that, the attribute classifier is trained using the multi-domain features of the data. Finally, the fault data of unknown class is diagnosed based on Euclidean distance. The effectiveness of the framework is verified by public datasets. This framework provides a new perspective for zero-shot fault diagnosis of rotating machinery.
{"title":"Fault Diagnosis of Rotating Machinery Based on FMEA and Zero-shot Learning","authors":"Boyang Zhao, Tong Li, Wei Dai, Junjun Dong","doi":"10.1109/phm-yantai55411.2022.9942104","DOIUrl":"https://doi.org/10.1109/phm-yantai55411.2022.9942104","url":null,"abstract":"Data-driven intelligent fault diagnosis is now a research hotspot. However, the fault data collected in actual working conditions is limited, which leads to a decline in the diagnostic ability of fault diagnosis models that rely on balanced data in actual engineering. Fortunately, the zero-shot problem for some fault classes can be solved by transferring zero-shot learning from machine vision to rotating machinery fault diagnosis. Inspired by this, we propose an attribute description method based on Failure Mode and Effects Analysis (FMEA) to solve the problem of semantic description of rotating machinery fault data, so as to be used for zero-shot fault diagnosis of rotating machinery. The framework analyzes the failure modes of rotating machinery based on FMEA, and establishes a fault attribute dictionary. After that, the attribute classifier is trained using the multi-domain features of the data. Finally, the fault data of unknown class is diagnosed based on Euclidean distance. The effectiveness of the framework is verified by public datasets. This framework provides a new perspective for zero-shot fault diagnosis of rotating machinery.","PeriodicalId":315994,"journal":{"name":"2022 Global Reliability and Prognostics and Health Management (PHM-Yantai)","volume":"54 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":"128373819","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-yantai55411.2022.9941914
Yafei Zhu, Xiang Li, Wei Zhang
Nowadays, prognosis methods based on deep learning have been successfully developed and applied in many industrial fields, such as energy, transportation, aero-space engineering etc. Lithium-ion battery prognosis is very important to indicate the health states of the energy system, which has been a hot topic in the past decades. In this paper, a new method is proposed for battery prognosis. The proposed architecture integrates the traditional DNN and CNN models, and divides the feature graph into two branches for separate computation. Residual network is also used in the prediction model for pursuing better effects. Residual block is implemented by a hidden layer connecting each branch’s inputs and outputs, which improves the model’s generalization ability. The proposed method takes up one-step prediction for CALCE lithium-ion data set. Experimental results show that the proposed method has a better prediction effect. Therefore, it is of great significance to predict the life of lithiumion batteries and become a new basis for a deep learning-based method to predict the life of lithium-ion batteries.
{"title":"Deep Residual Net-Based Prognosis Method for Lithium-ion Batteries with Information Fusion from Different Scales","authors":"Yafei Zhu, Xiang Li, Wei Zhang","doi":"10.1109/phm-yantai55411.2022.9941914","DOIUrl":"https://doi.org/10.1109/phm-yantai55411.2022.9941914","url":null,"abstract":"Nowadays, prognosis methods based on deep learning have been successfully developed and applied in many industrial fields, such as energy, transportation, aero-space engineering etc. Lithium-ion battery prognosis is very important to indicate the health states of the energy system, which has been a hot topic in the past decades. In this paper, a new method is proposed for battery prognosis. The proposed architecture integrates the traditional DNN and CNN models, and divides the feature graph into two branches for separate computation. Residual network is also used in the prediction model for pursuing better effects. Residual block is implemented by a hidden layer connecting each branch’s inputs and outputs, which improves the model’s generalization ability. The proposed method takes up one-step prediction for CALCE lithium-ion data set. Experimental results show that the proposed method has a better prediction effect. Therefore, it is of great significance to predict the life of lithiumion batteries and become a new basis for a deep learning-based method to predict the life of lithium-ion batteries.","PeriodicalId":315994,"journal":{"name":"2022 Global Reliability and Prognostics and Health Management (PHM-Yantai)","volume":"102 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":"124720881","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：