Pub Date : 2022-05-01DOI: 10.1109/PHM2022-London52454.2022.00050
Long Yang, Hanqing Yu, Junfu Li
With the widespread application of lithium-ion batteries, state of power (SOP) estimation has become a challenge and a hot research issue in many fields. In order to solve the problem of complex steps and low accuracy of SOP estimation, this paper proposes a novel SOP estimation method for lithium-ion batteries based on electrochemical model and multiple restrictions, and the validity of the model and the accuracy of the method are verified by experiments on varied conditions. The mean relative error of SOP estimation is lower than 2%, which proves the accuracy and practicability of SOP estimation based on the developed method.
{"title":"State of Power Estimation for Lithium-ion Battery Based on Electrochemical Model and Multiple Restrictions","authors":"Long Yang, Hanqing Yu, Junfu Li","doi":"10.1109/PHM2022-London52454.2022.00050","DOIUrl":"https://doi.org/10.1109/PHM2022-London52454.2022.00050","url":null,"abstract":"With the widespread application of lithium-ion batteries, state of power (SOP) estimation has become a challenge and a hot research issue in many fields. In order to solve the problem of complex steps and low accuracy of SOP estimation, this paper proposes a novel SOP estimation method for lithium-ion batteries based on electrochemical model and multiple restrictions, and the validity of the model and the accuracy of the method are verified by experiments on varied conditions. The mean relative error of SOP estimation is lower than 2%, which proves the accuracy and practicability of SOP estimation based on the developed method.","PeriodicalId":269605,"journal":{"name":"2022 Prognostics and Health Management Conference (PHM-2022 London)","volume":"83 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":"128168046","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-London52454.2022.00100
Huan Wang, Dan Xu
Accelerated degradation test (ADT) plays an important role in products reliability evaluation and lifetime prediction. When less data is obtained, the traditional method based on probability theory has some defects in the cognitive uncertainty of quantitative data. Therefore, based on the uncertainty theory and belief reliability theory, this paper establishes a new uncertainty accelerated degradation model, which takes into account the cognitive uncertainty of time, sample, and double stress dimensions at the same time. Then, the parameter estimation method of the model is given based on the least square principle. Finally, take the temperature and humidity stress ADT of the sealing rubber ring as an example, establish double-stress accelerated degradation model and evaluate its reliability.
{"title":"Double-Stress Accelerated Degradation Modeling Based on Uncertain Process","authors":"Huan Wang, Dan Xu","doi":"10.1109/PHM2022-London52454.2022.00100","DOIUrl":"https://doi.org/10.1109/PHM2022-London52454.2022.00100","url":null,"abstract":"Accelerated degradation test (ADT) plays an important role in products reliability evaluation and lifetime prediction. When less data is obtained, the traditional method based on probability theory has some defects in the cognitive uncertainty of quantitative data. Therefore, based on the uncertainty theory and belief reliability theory, this paper establishes a new uncertainty accelerated degradation model, which takes into account the cognitive uncertainty of time, sample, and double stress dimensions at the same time. Then, the parameter estimation method of the model is given based on the least square principle. Finally, take the temperature and humidity stress ADT of the sealing rubber ring as an example, establish double-stress accelerated degradation model and evaluate its reliability.","PeriodicalId":269605,"journal":{"name":"2022 Prognostics and Health Management Conference (PHM-2022 London)","volume":"228 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":"116197702","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-London52454.2022.00054
Yingqi Wang, Shengwei Meng, Yuchen Song, Datong Liu
With the advancement of the fifth-generation (5G) mobile communication networks, the number of subscribers in the interior environment continues to grow. The large-scale indoor distributed antenna system (DAS) is one of the critical approaches for bringing macro base station signals indoors. As the DAS becomes larger and the composition becomes more and more complex, the probability of system failure gradually increases. Therefore, it is very important to detect the failure of the DAS. Through actual research, limited by the user’s usage pattern, distribution, and regional functions, the daily power slave data of the room distribution system has a certain periodicity and similarity, but when a fault occurs, it will break this rule, and then be detected. However, the similarity and periodicity of the data are also affected by the randomness of users, which brings difficulties to fault detection. This paper will use the fault detection method based on N-dimensional Euclidean distance to mine the anomalies in the DAS detection data, and then carry out fault detection. To solve the influence of user randomness on the detection results, this paper will introduce a sliding window and a selection window. Although the filtering reduces the timeliness, it greatly reduces the false alarm rate. Finally, the simulation data and real data at DAS will be used to verify the method proposed in this paper.
{"title":"Fault detection for large scale indoor distributed antenna system based on time series similarity","authors":"Yingqi Wang, Shengwei Meng, Yuchen Song, Datong Liu","doi":"10.1109/PHM2022-London52454.2022.00054","DOIUrl":"https://doi.org/10.1109/PHM2022-London52454.2022.00054","url":null,"abstract":"With the advancement of the fifth-generation (5G) mobile communication networks, the number of subscribers in the interior environment continues to grow. The large-scale indoor distributed antenna system (DAS) is one of the critical approaches for bringing macro base station signals indoors. As the DAS becomes larger and the composition becomes more and more complex, the probability of system failure gradually increases. Therefore, it is very important to detect the failure of the DAS. Through actual research, limited by the user’s usage pattern, distribution, and regional functions, the daily power slave data of the room distribution system has a certain periodicity and similarity, but when a fault occurs, it will break this rule, and then be detected. However, the similarity and periodicity of the data are also affected by the randomness of users, which brings difficulties to fault detection. This paper will use the fault detection method based on N-dimensional Euclidean distance to mine the anomalies in the DAS detection data, and then carry out fault detection. To solve the influence of user randomness on the detection results, this paper will introduce a sliding window and a selection window. Although the filtering reduces the timeliness, it greatly reduces the false alarm rate. Finally, the simulation data and real data at DAS will be used to verify the method proposed in this paper.","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":"130845418","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-London52454.2022.00026
Xiaobo Li, Xiaofeng Jiao, H. Zu, Lihui Zhang, Jie Yun, C. He, Qiangqiang Wang
The operation condition of pumped storage unit is complex and switch frequently, which is easy to cause unit instability fault. Firstly, the pumped storage unit structure is decomposed according to the level of ‘system- subsystem- component’. The unit is divided into four subsystems in structure: motor-generator subsystem, pump turbine subsystem, pressure diversion subsystem and speed control subsystem. The unit equipment tree is established. Combined with unit operation characteristics and typical instability fault cases, the typical instability fault modes of pumped storage unit are determined. Then, FTA (Fault Tree Analysis) and FMEA (Failure Mode And Effects Analysis) are combined to obtain the instability fault knowledge of the unit by performing FTA first and then FMEA. Finally, aiming at the equipment structure information, FTA information and FMEA information of pumped storage unit, combined with ontology theory, the class and attribute relationship of the three types information ontology are analyzed. And the equipment information ontology, FTA ontology and FMEA ontology models are constructed respectively to realize the representation and management of fault knowledge.
{"title":"Instability Fault Knowledge Acquisition and Management of Pumped Storage Unit Based on FTA / FMEA and Ontology Theory","authors":"Xiaobo Li, Xiaofeng Jiao, H. Zu, Lihui Zhang, Jie Yun, C. He, Qiangqiang Wang","doi":"10.1109/PHM2022-London52454.2022.00026","DOIUrl":"https://doi.org/10.1109/PHM2022-London52454.2022.00026","url":null,"abstract":"The operation condition of pumped storage unit is complex and switch frequently, which is easy to cause unit instability fault. Firstly, the pumped storage unit structure is decomposed according to the level of ‘system- subsystem- component’. The unit is divided into four subsystems in structure: motor-generator subsystem, pump turbine subsystem, pressure diversion subsystem and speed control subsystem. The unit equipment tree is established. Combined with unit operation characteristics and typical instability fault cases, the typical instability fault modes of pumped storage unit are determined. Then, FTA (Fault Tree Analysis) and FMEA (Failure Mode And Effects Analysis) are combined to obtain the instability fault knowledge of the unit by performing FTA first and then FMEA. Finally, aiming at the equipment structure information, FTA information and FMEA information of pumped storage unit, combined with ontology theory, the class and attribute relationship of the three types information ontology are analyzed. And the equipment information ontology, FTA ontology and FMEA ontology models are constructed respectively to realize the representation and management of fault knowledge.","PeriodicalId":269605,"journal":{"name":"2022 Prognostics and Health Management Conference (PHM-2022 London)","volume":"23 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":"130907640","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-London52454.2022.00060
P. Lu
Electroencephalogram (EEG) signal is often used in emotion recognition tasks to classify human emotions. In this paper, we propose a new approach to learn the temporal features of EEG using long and short-term memory (LSTM), which is a type of Recurrent Neural network (RNN), especially suitable for solving the problem of long-term dependencies such as gradients vanishing and exploding. In addition, to enhance the interaction between EEG signals and to learn the non-linear characteristics between EEG electrodes, we use 1D-Convolution kernel to pre-process the input EEG data. To justify the capability of this method, we set the subject-independent experiments via adopting the leave-one-out experimental strategy on SEED dataset. The result of our experiments shows that this method can effectively capture the timing relationships in EEG signals with high classification accuracy around 93%.
{"title":"Human emotion recognition based on multi-channel EEG signals using LSTM neural network","authors":"P. Lu","doi":"10.1109/PHM2022-London52454.2022.00060","DOIUrl":"https://doi.org/10.1109/PHM2022-London52454.2022.00060","url":null,"abstract":"Electroencephalogram (EEG) signal is often used in emotion recognition tasks to classify human emotions. In this paper, we propose a new approach to learn the temporal features of EEG using long and short-term memory (LSTM), which is a type of Recurrent Neural network (RNN), especially suitable for solving the problem of long-term dependencies such as gradients vanishing and exploding. In addition, to enhance the interaction between EEG signals and to learn the non-linear characteristics between EEG electrodes, we use 1D-Convolution kernel to pre-process the input EEG data. To justify the capability of this method, we set the subject-independent experiments via adopting the leave-one-out experimental strategy on SEED dataset. The result of our experiments shows that this method can effectively capture the timing relationships in EEG signals with high classification accuracy around 93%.","PeriodicalId":269605,"journal":{"name":"2022 Prognostics and Health Management Conference (PHM-2022 London)","volume":"16 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":"122798315","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-London52454.2022.00082
Xueli Jia, Xiaohui Liu, Yilin Zhou
In order to reduce the air pollution caused by automobile exhaust emissions, the proton exchange membrane fuel cell (PEMFC) is more and more widely used in automobile field. While the durability is an important reason hindering the development of fuel cell. In order to popularize the use of PEMFC, it is important to improve durability and prolong service life of PEMFC. Based on the working mechanism of PEMFC and the analysis of durability test conditions, methods and health indicators, this paper compares the durability test data of fuel cells under three different working conditions, analyzes the influence of different working conditions on performance degradation of fuel cells, and discusses the reasons for different performance degradation laws. Finally, the advantages and disadvantages of fuel cell life prediction algorithms are summarized.
{"title":"Performance Degradation and Life Prediction of Proton Exchange Membrane Fuel Cell","authors":"Xueli Jia, Xiaohui Liu, Yilin Zhou","doi":"10.1109/PHM2022-London52454.2022.00082","DOIUrl":"https://doi.org/10.1109/PHM2022-London52454.2022.00082","url":null,"abstract":"In order to reduce the air pollution caused by automobile exhaust emissions, the proton exchange membrane fuel cell (PEMFC) is more and more widely used in automobile field. While the durability is an important reason hindering the development of fuel cell. In order to popularize the use of PEMFC, it is important to improve durability and prolong service life of PEMFC. Based on the working mechanism of PEMFC and the analysis of durability test conditions, methods and health indicators, this paper compares the durability test data of fuel cells under three different working conditions, analyzes the influence of different working conditions on performance degradation of fuel cells, and discusses the reasons for different performance degradation laws. Finally, the advantages and disadvantages of fuel cell life prediction algorithms are summarized.","PeriodicalId":269605,"journal":{"name":"2022 Prognostics and Health Management Conference (PHM-2022 London)","volume":"2015 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":"127601096","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-London52454.2022.00089
Yun Zhao, Xianghua Ma, Yinzhong Ye
Aiming at the problems of low accuracy and poor robustness of current multi-robot cooperative visual simultaneous localization and mapping (SLAM) algorithms in complex environments, a multi-robot cooperative monocular SLAM algorithm based on the semi-direct method is proposed. The algorithm adopts a centralized collaborative framework. In this framework, each robot runs a direct-method based visual odometry, which can both preserves their own autonomy and enables fast and robust pose tracking on local maps. The central server uses the communication module to receive the marginalized keyframes and keypoints of all robots, and utilizes the feature method to further refine the poses of these keyframes and build reusable local sparse feature maps. These maps are fused to build a global map when they are detected to overlap. Experiments are carried out on TUM and EuRoC datasets and the results show that the algorithm in this paper has higher accuracy and robustness in co-localization.
{"title":"A Multi-Robot Collaborative Monocular SLAM Based on Semi-Direct Method","authors":"Yun Zhao, Xianghua Ma, Yinzhong Ye","doi":"10.1109/PHM2022-London52454.2022.00089","DOIUrl":"https://doi.org/10.1109/PHM2022-London52454.2022.00089","url":null,"abstract":"Aiming at the problems of low accuracy and poor robustness of current multi-robot cooperative visual simultaneous localization and mapping (SLAM) algorithms in complex environments, a multi-robot cooperative monocular SLAM algorithm based on the semi-direct method is proposed. The algorithm adopts a centralized collaborative framework. In this framework, each robot runs a direct-method based visual odometry, which can both preserves their own autonomy and enables fast and robust pose tracking on local maps. The central server uses the communication module to receive the marginalized keyframes and keypoints of all robots, and utilizes the feature method to further refine the poses of these keyframes and build reusable local sparse feature maps. These maps are fused to build a global map when they are detected to overlap. Experiments are carried out on TUM and EuRoC datasets and the results show that the algorithm in this paper has higher accuracy and robustness in co-localization.","PeriodicalId":269605,"journal":{"name":"2022 Prognostics and Health Management Conference (PHM-2022 London)","volume":"36 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":"116329977","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-London52454.2022.00012
Zhenwei Zhou, Tong Li, Tao Liu, Kaiwei Wang, Yun Huang, Linlin Shi
This paper proposes a fault diagnosis method for the complex electronic system based on multi-source diagnostic information such as complex electronic system topological connections, fault propagation effects, abnormal event information, usage time, and mean time between failures (MTBF), which are relatively easy to obtain under conditions such as airborne, shipborne, vehicle-mounted, and spaceborne, etc. Firstly, the basis of directed graph theory and fault propagation capability index matrix are used to describe the diagnosis problem. Secondly, the robustness index, credibility index and the remaining life index are composited to obtain fault diagnosis index. Lastly, a simulation example is given to demonstrate the efficiency of the proposed diagnosis algorithm. which not only realizes the integration of multi-source diagnostic information of each component of the complex electronic system in space and time, but also reduces the dependence of fault diagnosis on special test equipment.
{"title":"Fault Diagnosis Method for Complex Electronic System","authors":"Zhenwei Zhou, Tong Li, Tao Liu, Kaiwei Wang, Yun Huang, Linlin Shi","doi":"10.1109/PHM2022-London52454.2022.00012","DOIUrl":"https://doi.org/10.1109/PHM2022-London52454.2022.00012","url":null,"abstract":"This paper proposes a fault diagnosis method for the complex electronic system based on multi-source diagnostic information such as complex electronic system topological connections, fault propagation effects, abnormal event information, usage time, and mean time between failures (MTBF), which are relatively easy to obtain under conditions such as airborne, shipborne, vehicle-mounted, and spaceborne, etc. Firstly, the basis of directed graph theory and fault propagation capability index matrix are used to describe the diagnosis problem. Secondly, the robustness index, credibility index and the remaining life index are composited to obtain fault diagnosis index. Lastly, a simulation example is given to demonstrate the efficiency of the proposed diagnosis algorithm. which not only realizes the integration of multi-source diagnostic information of each component of the complex electronic system in space and time, but also reduces the dependence of fault diagnosis on special test equipment.","PeriodicalId":269605,"journal":{"name":"2022 Prognostics and Health Management Conference (PHM-2022 London)","volume":"56 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":"124519256","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-London52454.2022.00024
Bin Yu, Xu-yun Fu, Wei Jiang, Z. Bai
The exchange problem of modules and life-limited parts when two aeroengines are sent for the shop visit at the same time is studied. Taking the lowest total loss cost of modules maintenance and life-limited parts replacement as the optimization objective, this paper establishes a single-aeroengine opportunistic maintenance model. A heuristic search algorithm based on two reduction rules is used to improve search efficiency. The genetic algorithm is used to solve the problem that the solution space of the exchange problem is too large. Finally, numerical experiments and application cases are used to prove the efficiency of the algorithm. The results show that the exchange algorithm proposed in this paper can calculate the exchange scheme to reduce the loss cost of two aeroengines in a short time and the optimization rate is about 18%.
{"title":"Exchange problem optimization between aeroengines with multiple modules and life-limited parts","authors":"Bin Yu, Xu-yun Fu, Wei Jiang, Z. Bai","doi":"10.1109/PHM2022-London52454.2022.00024","DOIUrl":"https://doi.org/10.1109/PHM2022-London52454.2022.00024","url":null,"abstract":"The exchange problem of modules and life-limited parts when two aeroengines are sent for the shop visit at the same time is studied. Taking the lowest total loss cost of modules maintenance and life-limited parts replacement as the optimization objective, this paper establishes a single-aeroengine opportunistic maintenance model. A heuristic search algorithm based on two reduction rules is used to improve search efficiency. The genetic algorithm is used to solve the problem that the solution space of the exchange problem is too large. Finally, numerical experiments and application cases are used to prove the efficiency of the algorithm. The results show that the exchange algorithm proposed in this paper can calculate the exchange scheme to reduce the loss cost of two aeroengines in a short time and the optimization rate is about 18%.","PeriodicalId":269605,"journal":{"name":"2022 Prognostics and Health Management Conference (PHM-2022 London)","volume":"52 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":"115314875","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-London52454.2022.00062
Huanjun Zhao, Bin Zheng, Le Wang
The human forearm Surface Electromyography signal (sEMG) is related to gesture activities, and the human body movement intention can be predicted by analyzing and identifying the forearm sEMG signal. Deep learning has been widely used in gesture recognition research because of its ability to extract deep features. On this basis, this paper introduces an attention mechanism to assign weights to different channels, so that the acquisition of the model is more dependent on some explicit channels to obtain a model with better performance. Compared with other models, the model proposed in this paper not only has fewer parameters, but the experimental accuracy rate on private datasets can reach up to 99.6%, which is comparable to some current CNN network models with good classification effects; In the case of the smaller datasets, the model can still maintain more than 95% accuracy and has good adaptability.
{"title":"Deep Learning with Attention on Hand Gesture Recognition Based on sEMG","authors":"Huanjun Zhao, Bin Zheng, Le Wang","doi":"10.1109/PHM2022-London52454.2022.00062","DOIUrl":"https://doi.org/10.1109/PHM2022-London52454.2022.00062","url":null,"abstract":"The human forearm Surface Electromyography signal (sEMG) is related to gesture activities, and the human body movement intention can be predicted by analyzing and identifying the forearm sEMG signal. Deep learning has been widely used in gesture recognition research because of its ability to extract deep features. On this basis, this paper introduces an attention mechanism to assign weights to different channels, so that the acquisition of the model is more dependent on some explicit channels to obtain a model with better performance. Compared with other models, the model proposed in this paper not only has fewer parameters, but the experimental accuracy rate on private datasets can reach up to 99.6%, which is comparable to some current CNN network models with good classification effects; In the case of the smaller datasets, the model can still maintain more than 95% accuracy and has good adaptability.","PeriodicalId":269605,"journal":{"name":"2022 Prognostics and Health Management Conference (PHM-2022 London)","volume":"3 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":"115072695","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：