Pub Date : 2022-10-13DOI: 10.1109/PHM-Yantai55411.2022.9941950
Wenjuan Xie, Feng Liu
The currently used resource recommendation algorithm mainly recommends resources according to the user's preference for a tag class, ignoring the relationship between user preferences and needs and learning scenarios under mobile learning, resulting in poor efficiency and accuracy of recommended resources. In order to improve the shortcomings of the algorithm, this paper studies the personalized recommendation algorithm of Ideological and political teaching multimedia resources based on mobile learning. By constructing the map of Ideological and political teaching knowledge, this paper analyzes the correlation between resources. The diagnosis result of students' cognitive level is one of the characteristics of personalized recommendation. Mobile learning devices are used to collect data, calculate and perceive mobile learning scenarios. By improving the collaborative filtering technology, the teaching resources of Ideological and political courses can be personalized recommended. In the algorithm experiment, the average absolute error of the algorithm recommendation is relatively reduced by about 14.67%, the recommendation efficiency is higher, and the personalized recommendation effect is better.
{"title":"Personalized Accurate Recommendation Algorithm of Ideological and Political Teaching Multimedia Resources Based on Mobile Learning","authors":"Wenjuan Xie, Feng Liu","doi":"10.1109/PHM-Yantai55411.2022.9941950","DOIUrl":"https://doi.org/10.1109/PHM-Yantai55411.2022.9941950","url":null,"abstract":"The currently used resource recommendation algorithm mainly recommends resources according to the user's preference for a tag class, ignoring the relationship between user preferences and needs and learning scenarios under mobile learning, resulting in poor efficiency and accuracy of recommended resources. In order to improve the shortcomings of the algorithm, this paper studies the personalized recommendation algorithm of Ideological and political teaching multimedia resources based on mobile learning. By constructing the map of Ideological and political teaching knowledge, this paper analyzes the correlation between resources. The diagnosis result of students' cognitive level is one of the characteristics of personalized recommendation. Mobile learning devices are used to collect data, calculate and perceive mobile learning scenarios. By improving the collaborative filtering technology, the teaching resources of Ideological and political courses can be personalized recommended. In the algorithm experiment, the average absolute error of the algorithm recommendation is relatively reduced by about 14.67%, the recommendation efficiency is higher, and the personalized recommendation effect is better.","PeriodicalId":315994,"journal":{"name":"2022 Global Reliability and Prognostics and Health Management (PHM-Yantai)","volume":"18 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":"115427146","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-Yantai55411.2022.9941863
Yanling Ji, N. Lu, Zujin Wang, Jianfei Chen, Ling Sun
The life of door system is closely related to the capacity of rail vehicle safe operation and maintenance. Rolling pin is a built-in mechanical component of the rail vehicle door system. Its wear degree is difficult to measure so that its lifetime is hard to predict in real time. In order to predict the life of rolling pin online and provide decision support for active maintenance, this paper proposes a data-driven life prediction method based on Linear Discriminant Analysis (LDA) and Extreme Learning Machine (ELM). Firstly, features related to the wear state of the rolling pin are extracted from raw data collected from motor of the door. Then, with the LDA, the features are fused to filter out the redundant features. Finally, the ELM model for predicting the diameter of small end is built, and the life of rolling pin is calculated according to the relationship between the run times and the diameter of small end. The simulation results show that the method enables to accurately predict the life of the product, which has reliability and important engineering application value.
{"title":"Life Prediction Method Based on LDA-ELM for Mechanical Components of Door Systems","authors":"Yanling Ji, N. Lu, Zujin Wang, Jianfei Chen, Ling Sun","doi":"10.1109/PHM-Yantai55411.2022.9941863","DOIUrl":"https://doi.org/10.1109/PHM-Yantai55411.2022.9941863","url":null,"abstract":"The life of door system is closely related to the capacity of rail vehicle safe operation and maintenance. Rolling pin is a built-in mechanical component of the rail vehicle door system. Its wear degree is difficult to measure so that its lifetime is hard to predict in real time. In order to predict the life of rolling pin online and provide decision support for active maintenance, this paper proposes a data-driven life prediction method based on Linear Discriminant Analysis (LDA) and Extreme Learning Machine (ELM). Firstly, features related to the wear state of the rolling pin are extracted from raw data collected from motor of the door. Then, with the LDA, the features are fused to filter out the redundant features. Finally, the ELM model for predicting the diameter of small end is built, and the life of rolling pin is calculated according to the relationship between the run times and the diameter of small end. The simulation results show that the method enables to accurately predict the life of the product, which has reliability and important engineering application value.","PeriodicalId":315994,"journal":{"name":"2022 Global Reliability and Prognostics and Health Management (PHM-Yantai)","volume":"68 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":"117024130","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-Yantai55411.2022.9942043
Panke Li, Ying Song
Because the existence of sensitive words will affect its text transmission, an intelligent location algorithm of sensitive words in English translation text based on association rules is designed. Mining sensitive words in English translation text based on association rule algorithm. In mining, Apriori algorithm is improved, an FT tree association rule algorithm is designed, and sensitive word data mining is implemented. A sensitive word detection model for English translation text is designed and implemented to detect sensitive words in the text. The model consists of four parts: user interface sub model, information preparation sub model, detection engine sub model and audit strategy sub model. The intelligent location of sensitive words in English translation text is realized through Yolo series algorithms. Build a test environment to test the positioning performance of the design method. The test results show that when there is attention mechanism in the model convolution neural network, the location of this method is more accurate and achieves the initial design goal.
{"title":"Intelligent Location Algorithm of Sensitive Words in English Translation Text Based on Association Rules","authors":"Panke Li, Ying Song","doi":"10.1109/PHM-Yantai55411.2022.9942043","DOIUrl":"https://doi.org/10.1109/PHM-Yantai55411.2022.9942043","url":null,"abstract":"Because the existence of sensitive words will affect its text transmission, an intelligent location algorithm of sensitive words in English translation text based on association rules is designed. Mining sensitive words in English translation text based on association rule algorithm. In mining, Apriori algorithm is improved, an FT tree association rule algorithm is designed, and sensitive word data mining is implemented. A sensitive word detection model for English translation text is designed and implemented to detect sensitive words in the text. The model consists of four parts: user interface sub model, information preparation sub model, detection engine sub model and audit strategy sub model. The intelligent location of sensitive words in English translation text is realized through Yolo series algorithms. Build a test environment to test the positioning performance of the design method. The test results show that when there is attention mechanism in the model convolution neural network, the location of this method is more accurate and achieves the initial design goal.","PeriodicalId":315994,"journal":{"name":"2022 Global Reliability and Prognostics and Health Management (PHM-Yantai)","volume":"49 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":"116607645","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-Yantai55411.2022.9942106
Xiaozhen Yan, Ruochen Ding, Qinghua Luo, Chunyu Ju, Di Wu
Because of its superior obstacle avoidance capability, the Dynamic Window Approach (DWA) algorithm has been widely used in local dynamic path planning nowadays. However, in areas with dense obstacles, the DWA algorithm prefers to go around the outside of the dense obstacle area, which increases the total distance. In addition, when encountering a "C" shaped obstacle, the objective cost function will fail and the path will not be found. Therefore, this paper proposes a method to improve the DWA algorithm. Based on the existing constraints, we also propose to score the distance between the current point and the target. In our experiments, we use the traditional DWA algorithm as a reference method and compare the two algorithms in maps with different characteristics. The experimental results demonstrate that the improved DWA algorithm achieves better results in obstacle avoidance.
{"title":"A Dynamic Path Planning Algorithm Based on the Improved DWA Algorithm","authors":"Xiaozhen Yan, Ruochen Ding, Qinghua Luo, Chunyu Ju, Di Wu","doi":"10.1109/PHM-Yantai55411.2022.9942106","DOIUrl":"https://doi.org/10.1109/PHM-Yantai55411.2022.9942106","url":null,"abstract":"Because of its superior obstacle avoidance capability, the Dynamic Window Approach (DWA) algorithm has been widely used in local dynamic path planning nowadays. However, in areas with dense obstacles, the DWA algorithm prefers to go around the outside of the dense obstacle area, which increases the total distance. In addition, when encountering a \"C\" shaped obstacle, the objective cost function will fail and the path will not be found. Therefore, this paper proposes a method to improve the DWA algorithm. Based on the existing constraints, we also propose to score the distance between the current point and the target. In our experiments, we use the traditional DWA algorithm as a reference method and compare the two algorithms in maps with different characteristics. The experimental results demonstrate that the improved DWA algorithm achieves better results in obstacle avoidance.","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":"123343273","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-Yantai55411.2022.9941998
Yong Zhang, Erqing Ren, Gang Li
Aiming at the resource allocation of ecological network courses in higher education, the corresponding allocation framework is constructed based on fuzzy particle swarm optimization. Because of the slow convergence speed of particle swarm optimization algorithm in the later stage, it is easy to converge in local optimization. Therefore, combined with the characteristics of resource allocation problem, particle swarm optimization algorithm is improved. The resource allocation model of ecological network courses in higher education is solved by using fuzzy particle swarm optimization algorithm under the constraints, and the resource allocation scheme is obtained. The results show that compared with the manual allocation scheme, the higher education ecological network curriculum resource allocation scheme obtained by the research algorithm has higher curriculum resource utilization efficiency and resource allocation efficiency, indicating the effectiveness of the research algorithm.
{"title":"Resource Security Allocation Algorithm of Ecological Network Curriculum in Higher Education Based on Fuzzy Particle Swarm Optimization","authors":"Yong Zhang, Erqing Ren, Gang Li","doi":"10.1109/PHM-Yantai55411.2022.9941998","DOIUrl":"https://doi.org/10.1109/PHM-Yantai55411.2022.9941998","url":null,"abstract":"Aiming at the resource allocation of ecological network courses in higher education, the corresponding allocation framework is constructed based on fuzzy particle swarm optimization. Because of the slow convergence speed of particle swarm optimization algorithm in the later stage, it is easy to converge in local optimization. Therefore, combined with the characteristics of resource allocation problem, particle swarm optimization algorithm is improved. The resource allocation model of ecological network courses in higher education is solved by using fuzzy particle swarm optimization algorithm under the constraints, and the resource allocation scheme is obtained. The results show that compared with the manual allocation scheme, the higher education ecological network curriculum resource allocation scheme obtained by the research algorithm has higher curriculum resource utilization efficiency and resource allocation efficiency, indicating the effectiveness of the research algorithm.","PeriodicalId":315994,"journal":{"name":"2022 Global Reliability and Prognostics and Health Management (PHM-Yantai)","volume":"27 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":"124238940","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-yantai55411.2022.9941855
Zheng Lan, Liu Zihang, Ye Qunfeng
Through the fuzzy comprehensive evaluation method, the simplicity of maintenance is analyzed. The maintenance simplicity of the scheme can be effectively analyzed from five aspects: the simplicity of fault isolation and installation test, simplicity of the access for maintenance, the simplicity of assembly and disassembly equipment, the simplicity of support sources and maintenance frequency. The method used in this paper can effectively reflect the maintenance simplicity of different schemes via fuzzy comprehensive evaluation method for decision-making.
{"title":"Research on the maintenance simplicity of civil aircraft based on the fuzzy comprehensive evaluation","authors":"Zheng Lan, Liu Zihang, Ye Qunfeng","doi":"10.1109/phm-yantai55411.2022.9941855","DOIUrl":"https://doi.org/10.1109/phm-yantai55411.2022.9941855","url":null,"abstract":"Through the fuzzy comprehensive evaluation method, the simplicity of maintenance is analyzed. The maintenance simplicity of the scheme can be effectively analyzed from five aspects: the simplicity of fault isolation and installation test, simplicity of the access for maintenance, the simplicity of assembly and disassembly equipment, the simplicity of support sources and maintenance frequency. The method used in this paper can effectively reflect the maintenance simplicity of different schemes via fuzzy comprehensive evaluation method for decision-making.","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":"125512234","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}
With China’s exploration of the sea, unmanned boats on the water are receiving more and more attention. Due to the complex situation on the water, unmanned boat obstacle avoidance still has defects. To address the above problems, this paper designs unmanned fish-finding and obstacle avoidance based on Pixhawk. The Kalman filter algorithm is used for sensor information fusion, which realizes the state estimation of the fish-finding unmanned ship. The BUG2 obstacle avoidance algorithm is used for obstacle avoidance, that optimizes the automatic obstacle avoidance function of the fish-finding unmanned ship. The fish finder is used to detect the position information of the fish, that realizes the function of the fish-finding unmanned ship tracking the fish. The PID control algorithm is used to control the driving of the ship, which makes the fish-finding unmanned ship converge to the desired course quickly and accurately. The lateral error of the vessel is within 1m. The simulation results verify the feasibility of the system, and the sea trial experiments of the unmanned fish-finding vessel prove the reliability and stability of the system.
{"title":"Design of Unmanned System for Fish-finding and Obstacle Avoidance Based on Pixhawk","authors":"Zhikuan Chen, Zhengxing Wang, Lan Xia, Zhiquan Zhou, Qinghua Luo, Zhenbin Lv","doi":"10.1109/PHM-Yantai55411.2022.9941991","DOIUrl":"https://doi.org/10.1109/PHM-Yantai55411.2022.9941991","url":null,"abstract":"With China’s exploration of the sea, unmanned boats on the water are receiving more and more attention. Due to the complex situation on the water, unmanned boat obstacle avoidance still has defects. To address the above problems, this paper designs unmanned fish-finding and obstacle avoidance based on Pixhawk. The Kalman filter algorithm is used for sensor information fusion, which realizes the state estimation of the fish-finding unmanned ship. The BUG2 obstacle avoidance algorithm is used for obstacle avoidance, that optimizes the automatic obstacle avoidance function of the fish-finding unmanned ship. The fish finder is used to detect the position information of the fish, that realizes the function of the fish-finding unmanned ship tracking the fish. The PID control algorithm is used to control the driving of the ship, which makes the fish-finding unmanned ship converge to the desired course quickly and accurately. The lateral error of the vessel is within 1m. The simulation results verify the feasibility of the system, and the sea trial experiments of the unmanned fish-finding vessel prove the reliability and stability of the system.","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":"122326891","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-Yantai55411.2022.9942085
Yuan Zhao, Yunxue Liu, Zhuoran Cai
Realizing highly accurate and noncontact heart rate estimation with frequency modulated continuous wave (FMCW) radar is a big challenge under the interference of background noise and respiration harmonics. In this paper, various methods are employed to eliminate the interference, including impulse noise removal, improved complete ensemble empirical mode decomposition with adaptive noise (ICEEMDAN) algorithm, peak-to-valley amplitude difference processing and peak-to-peak time interval processing. A novel heart rate estimation scheme that can efficiently suppress noise, interference and respiration signal for vital sign detection is proposed. After preprocessing the radar raw data, the scheme first removes the impulse noise of the vital signal. Then, the ICEEMDAN algorithm is used for further denoising, and the appropriate component is selected from the decomposition results to reconstruct the heartbeat signal. The heart rate is estimated in time domain and frequency domain, respectively. In the time domain, peak-to-valley amplitude difference and peak-to-peak time interval are used to eliminate noise and interference. In the frequency domain, fast Fourier transform (FFT) and Rife algorithms are applied to improve the estimation accuracy of the heart rate. Finally, the estimated data in the time and frequency domains are fused as the estimated heart rate of the scheme. Extensive experiments reveal that, compared with other methods, the root mean square error (RMSE) and mean absolute percentage error (MAPE) are greatly improved and the estimation accuracy of the heart rate is significantly enhanced by using the proposed scheme.
{"title":"A Novel Scheme for Vital Sign Detection with FMCW Radar","authors":"Yuan Zhao, Yunxue Liu, Zhuoran Cai","doi":"10.1109/PHM-Yantai55411.2022.9942085","DOIUrl":"https://doi.org/10.1109/PHM-Yantai55411.2022.9942085","url":null,"abstract":"Realizing highly accurate and noncontact heart rate estimation with frequency modulated continuous wave (FMCW) radar is a big challenge under the interference of background noise and respiration harmonics. In this paper, various methods are employed to eliminate the interference, including impulse noise removal, improved complete ensemble empirical mode decomposition with adaptive noise (ICEEMDAN) algorithm, peak-to-valley amplitude difference processing and peak-to-peak time interval processing. A novel heart rate estimation scheme that can efficiently suppress noise, interference and respiration signal for vital sign detection is proposed. After preprocessing the radar raw data, the scheme first removes the impulse noise of the vital signal. Then, the ICEEMDAN algorithm is used for further denoising, and the appropriate component is selected from the decomposition results to reconstruct the heartbeat signal. The heart rate is estimated in time domain and frequency domain, respectively. In the time domain, peak-to-valley amplitude difference and peak-to-peak time interval are used to eliminate noise and interference. In the frequency domain, fast Fourier transform (FFT) and Rife algorithms are applied to improve the estimation accuracy of the heart rate. Finally, the estimated data in the time and frequency domains are fused as the estimated heart rate of the scheme. Extensive experiments reveal that, compared with other methods, the root mean square error (RMSE) and mean absolute percentage error (MAPE) are greatly improved and the estimation accuracy of the heart rate is significantly enhanced by using the proposed scheme.","PeriodicalId":315994,"journal":{"name":"2022 Global Reliability and Prognostics and Health Management (PHM-Yantai)","volume":"118 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":"122469922","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-yantai55411.2022.9941984
Yanhui Bai, Honghui Li, Sen Zhao, Ning Zhang
The running conditions of wheels of Heavy-duty Railway Train are complex, and the real-time running state data is Multi-Dimension and Time-Sequence. Aiming at the problems that the traditional deep learning models have weak learning ability, cannot extract different scale information and gradient explosion in the prediction of remaining useful life (RUL), this paper proposes a multi-scale deep long short-term memory (MDLSTM) network model, which extracts time-series features of different scales through different number of hidden layer units of LSTM networks. In order to obtain more robust features under the premise of reducing the loss of original information and better to predict RUL of wheels, A Dual Channel Multi-scale Deep convolutional Multi-scale Deep long short-term memory (DC-MDCNN-MDLSTM) is proposed which combined the CNN and LSTM to extract multi-scale feature of wheels under different conditions and extract the different time step features of wheels from time series data. Using the actual wheels data to experiments. The results show that DC-MDCNN-MDLSTM network model is effective in predicting the degradation state of the wheels and provides technical support for repairing on condition of Heavy- duty Railway Train.
{"title":"Remaining Useful Life Prediction of Wheel of Heavy-duty Railway Train based on Dual Channel Multi-scale Deep convolution Multi-scale Deep Long Short-Term Memory network","authors":"Yanhui Bai, Honghui Li, Sen Zhao, Ning Zhang","doi":"10.1109/phm-yantai55411.2022.9941984","DOIUrl":"https://doi.org/10.1109/phm-yantai55411.2022.9941984","url":null,"abstract":"The running conditions of wheels of Heavy-duty Railway Train are complex, and the real-time running state data is Multi-Dimension and Time-Sequence. Aiming at the problems that the traditional deep learning models have weak learning ability, cannot extract different scale information and gradient explosion in the prediction of remaining useful life (RUL), this paper proposes a multi-scale deep long short-term memory (MDLSTM) network model, which extracts time-series features of different scales through different number of hidden layer units of LSTM networks. In order to obtain more robust features under the premise of reducing the loss of original information and better to predict RUL of wheels, A Dual Channel Multi-scale Deep convolutional Multi-scale Deep long short-term memory (DC-MDCNN-MDLSTM) is proposed which combined the CNN and LSTM to extract multi-scale feature of wheels under different conditions and extract the different time step features of wheels from time series data. Using the actual wheels data to experiments. The results show that DC-MDCNN-MDLSTM network model is effective in predicting the degradation state of the wheels and provides technical support for repairing on condition of Heavy- duty Railway Train.","PeriodicalId":315994,"journal":{"name":"2022 Global Reliability and Prognostics and Health Management (PHM-Yantai)","volume":"146 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":"128434830","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-Yantai55411.2022.9941919
Chunmei Zhao, Jun Liu
Aiming at the problem that it is easy to fall into local minimum in the multi domain resource allocation process of wireless communication in the Internet of things, a multi domain resource allocation algorithm of wireless communication in the Internet of things based on chaotic neural network is proposed. The effects of attenuation factor and temperature fading parameters on the chaotic characteristics of chaotic neural network are analyzed, and the network parameters are selected reasonably. This paper obtains the multi domain resources of integrated Internet of things wireless communication, updates the multi domain resources, and builds a multi domain resource configuration model through relevant network parameters. In this paper, we use data mining method to obtain the multi domain resource data of wireless communication. And the parameters of the network are appropriately selected to make the neural network appear chaotic, so the resource allocation process based on the chaotic neural network is designed. Therefore, the resource allocation process based on chaotic neural network is designed. The experimental results show that the configuration results of the algorithm are consistent with the ideal configuration results, and the shortest end-to-end delay is 10 ms, and the lowest packet loss rate is 4%.
{"title":"Multi Domain Resource Accurate Allocation Algorithm for Wireless Communication of Internet of Things Based on Chaotic Neural Network","authors":"Chunmei Zhao, Jun Liu","doi":"10.1109/PHM-Yantai55411.2022.9941919","DOIUrl":"https://doi.org/10.1109/PHM-Yantai55411.2022.9941919","url":null,"abstract":"Aiming at the problem that it is easy to fall into local minimum in the multi domain resource allocation process of wireless communication in the Internet of things, a multi domain resource allocation algorithm of wireless communication in the Internet of things based on chaotic neural network is proposed. The effects of attenuation factor and temperature fading parameters on the chaotic characteristics of chaotic neural network are analyzed, and the network parameters are selected reasonably. This paper obtains the multi domain resources of integrated Internet of things wireless communication, updates the multi domain resources, and builds a multi domain resource configuration model through relevant network parameters. In this paper, we use data mining method to obtain the multi domain resource data of wireless communication. And the parameters of the network are appropriately selected to make the neural network appear chaotic, so the resource allocation process based on the chaotic neural network is designed. Therefore, the resource allocation process based on chaotic neural network is designed. The experimental results show that the configuration results of the algorithm are consistent with the ideal configuration results, and the shortest end-to-end delay is 10 ms, and the lowest packet loss rate is 4%.","PeriodicalId":315994,"journal":{"name":"2022 Global Reliability and Prognostics and Health Management (PHM-Yantai)","volume":"7 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":"128796313","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：