Pub Date : 2021-10-15DOI: 10.1109/PHM-Nanjing52125.2021.9612956
Wenyan Wang, Hai-xiao Gong
The fast fusion method of marine environment vector data currently studied requires high light wave resolution in the panchromatic band and multi-spectral band, and the fused data is relatively fuzzy. In view of the above problems, a new marine environment vector based on BP neural network is studied. Fast data fusion method, accurate data acquisition operation, the data is arranged according to the filter length, system collection and filtering operations are performed according to the arrangement standard, and effective data is obtained. Even the low-resolution data can be well after the filtering operation. Fusion, based on the collected data, effectively analyze the fusion rules, combine the data wavelength center point to perform point data collection operations, combine the collected data, improve the system combination performance, and record the data that meets the combination standard as a fusion The standards are stored in the system space. Finally, the fusion criteria are used to perform data fusion operations to match the data fusion similarity, and the data that meets the system similarity standards are retained, and irrelevant data parameters are filtered to achieve accurate and automated data fusion. The experimental results show that the fast fusion method of marine environment vector data based on BP neural network can analyze the light wave resolution of panchromatic band and multispectral band well, and can realize high-definition data fusion.
{"title":"Fast fusion method of marine environment vector data based on BP neural network","authors":"Wenyan Wang, Hai-xiao Gong","doi":"10.1109/PHM-Nanjing52125.2021.9612956","DOIUrl":"https://doi.org/10.1109/PHM-Nanjing52125.2021.9612956","url":null,"abstract":"The fast fusion method of marine environment vector data currently studied requires high light wave resolution in the panchromatic band and multi-spectral band, and the fused data is relatively fuzzy. In view of the above problems, a new marine environment vector based on BP neural network is studied. Fast data fusion method, accurate data acquisition operation, the data is arranged according to the filter length, system collection and filtering operations are performed according to the arrangement standard, and effective data is obtained. Even the low-resolution data can be well after the filtering operation. Fusion, based on the collected data, effectively analyze the fusion rules, combine the data wavelength center point to perform point data collection operations, combine the collected data, improve the system combination performance, and record the data that meets the combination standard as a fusion The standards are stored in the system space. Finally, the fusion criteria are used to perform data fusion operations to match the data fusion similarity, and the data that meets the system similarity standards are retained, and irrelevant data parameters are filtered to achieve accurate and automated data fusion. The experimental results show that the fast fusion method of marine environment vector data based on BP neural network can analyze the light wave resolution of panchromatic band and multispectral band well, and can realize high-definition data fusion.","PeriodicalId":436428,"journal":{"name":"2021 Global Reliability and Prognostics and Health Management (PHM-Nanjing)","volume":"109 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2021-10-15","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"131661183","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 : 2021-10-15DOI: 10.1109/PHM-Nanjing52125.2021.9612808
Zhenyu Wu, Yanting Li
Aiming at the operation and maintenance (O&M) of wind farms, this paper proposes an integrated maintenance strategy based on statistical process control (SPC). The operating condition of the wind turbine is evaluated through the SPC scheme and used as an input for maintenance decisions. Meanwhile, the aging information of wind turbines would also be used to reduce the sensitivity of the maintenance model to faulty signals and improve the credibility of the maintenance programmer. Furthermore, a three-stage integrated maintenance strategy is introduced, and this paper proposes a new optimization objective based on the expected revenue ratio of the wind farm. The effectiveness of the proposed maintenance model is verified through a real wind farm case. The results show that the proposed method can reduce the maintenance cost and increase the profitability of the wind farm compared with the existing maintenance models.
{"title":"An integrated maintenance strategy of wind turbine based on statistic process control","authors":"Zhenyu Wu, Yanting Li","doi":"10.1109/PHM-Nanjing52125.2021.9612808","DOIUrl":"https://doi.org/10.1109/PHM-Nanjing52125.2021.9612808","url":null,"abstract":"Aiming at the operation and maintenance (O&M) of wind farms, this paper proposes an integrated maintenance strategy based on statistical process control (SPC). The operating condition of the wind turbine is evaluated through the SPC scheme and used as an input for maintenance decisions. Meanwhile, the aging information of wind turbines would also be used to reduce the sensitivity of the maintenance model to faulty signals and improve the credibility of the maintenance programmer. Furthermore, a three-stage integrated maintenance strategy is introduced, and this paper proposes a new optimization objective based on the expected revenue ratio of the wind farm. The effectiveness of the proposed maintenance model is verified through a real wind farm case. The results show that the proposed method can reduce the maintenance cost and increase the profitability of the wind farm compared with the existing maintenance models.","PeriodicalId":436428,"journal":{"name":"2021 Global Reliability and Prognostics and Health Management (PHM-Nanjing)","volume":"2 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2021-10-15","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"131716396","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 : 2021-10-15DOI: 10.1109/PHM-Nanjing52125.2021.9612807
Yajun Zhang, M. Cao, Y. Wang, Tao Zhang, Yajie Liu
Accurate state-of-health (SOH) estimation for Lithiumion batteries (LIBs) is vital for the battery management systems (BMS). This paper puts forward a fusion method to estimate battery SOH, which incorporates the incremental capacity analysis (ICA) with the long short-term memory (LSTM) network. First, a revised Lorentzian function-based voltage-capacity (VC) model is adopted to capture the IC curve. By leveraging merely data logged during the constant current (CC) charging stage, battery degradation information contained in the IC curve is concretized as the parameters of the VC model by simple curve fitting. These parameters with specific physical meanings are deemed as features that characterize battery health status. Correlation analysis is then performed for these features, and features of interest (FOIs) are selected as inputs of the LSTM. The LSTM model can learn the long-term dependencies of battery degradation, and thus improve the robustness of the prediction model against noise. Finally, four battery aging datasets with different chemistries are employed for model validation, and results reveal that the proposed method can achieve accurate SOH estimation results, with the maximum mean absolute errors limited within 2%.
{"title":"A Fusion Method to Estimate the State-of-Health of Lithium-ion Batteries","authors":"Yajun Zhang, M. Cao, Y. Wang, Tao Zhang, Yajie Liu","doi":"10.1109/PHM-Nanjing52125.2021.9612807","DOIUrl":"https://doi.org/10.1109/PHM-Nanjing52125.2021.9612807","url":null,"abstract":"Accurate state-of-health (SOH) estimation for Lithiumion batteries (LIBs) is vital for the battery management systems (BMS). This paper puts forward a fusion method to estimate battery SOH, which incorporates the incremental capacity analysis (ICA) with the long short-term memory (LSTM) network. First, a revised Lorentzian function-based voltage-capacity (VC) model is adopted to capture the IC curve. By leveraging merely data logged during the constant current (CC) charging stage, battery degradation information contained in the IC curve is concretized as the parameters of the VC model by simple curve fitting. These parameters with specific physical meanings are deemed as features that characterize battery health status. Correlation analysis is then performed for these features, and features of interest (FOIs) are selected as inputs of the LSTM. The LSTM model can learn the long-term dependencies of battery degradation, and thus improve the robustness of the prediction model against noise. Finally, four battery aging datasets with different chemistries are employed for model validation, and results reveal that the proposed method can achieve accurate SOH estimation results, with the maximum mean absolute errors limited within 2%.","PeriodicalId":436428,"journal":{"name":"2021 Global Reliability and Prognostics and Health Management (PHM-Nanjing)","volume":"38 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2021-10-15","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"128819160","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 : 2021-10-15DOI: 10.1109/PHM-Nanjing52125.2021.9613127
Ruiyi Yang, Yiyong Xiao
With the continuous increase of global energy demand, unconventional oil and gas resources such as shale and tight reservoirs have occupied an important position in the global energy structure. Large-scale hydraulic fracturing is the main method used to extract shale and tight reservoirs. However, because hydraulic fracturing is affected by complex in-situ stress and reservoir heterogeneity, the generation and propagation of hydraulic fractures are complicated. In this paper, a finite element-discrete element-finite volume (FE-DE-FV) parallel computing method based on Open Multi-Processing (OpenMP) is proposed to accurately and efficiently simulate hydraulic fracturing. This parallel computing method can be effectively applied in practical engineering. The high efficiency of parallel computation is verified and numerical simulations under different in-situ stress conditions are analyzed in this paper. The results show that the FE-DE-FV parallel computing method can accurately and efficiently simulate hydraulic fracturing.
{"title":"A FE-DE-FV Parallel Computing Method Based on OpenMP for the Hydraulic Fracturing","authors":"Ruiyi Yang, Yiyong Xiao","doi":"10.1109/PHM-Nanjing52125.2021.9613127","DOIUrl":"https://doi.org/10.1109/PHM-Nanjing52125.2021.9613127","url":null,"abstract":"With the continuous increase of global energy demand, unconventional oil and gas resources such as shale and tight reservoirs have occupied an important position in the global energy structure. Large-scale hydraulic fracturing is the main method used to extract shale and tight reservoirs. However, because hydraulic fracturing is affected by complex in-situ stress and reservoir heterogeneity, the generation and propagation of hydraulic fractures are complicated. In this paper, a finite element-discrete element-finite volume (FE-DE-FV) parallel computing method based on Open Multi-Processing (OpenMP) is proposed to accurately and efficiently simulate hydraulic fracturing. This parallel computing method can be effectively applied in practical engineering. The high efficiency of parallel computation is verified and numerical simulations under different in-situ stress conditions are analyzed in this paper. The results show that the FE-DE-FV parallel computing method can accurately and efficiently simulate hydraulic fracturing.","PeriodicalId":436428,"journal":{"name":"2021 Global Reliability and Prognostics and Health Management (PHM-Nanjing)","volume":"8 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2021-10-15","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"128850472","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 : 2021-10-15DOI: 10.1109/PHM-Nanjing52125.2021.9612768
Yilin Song, Yi-Feng Niu
Logistics networks, as the fundamental infrastructure, play a critical role in boosting economic prosperity. In this paper, we model a logistics network as a multidistribution multi-state flow network (MFN) in which each arc has random capacity characterized by more than one probability distribution under different budget allocations. Accordingly, we construct an optimization model to minimize the total budget required for the network to achieve a given reliability value. To address this challenging reliability-related optimization problem, an effective method is developed by integrating the well-known binary-search method and an existing method that solves the budget-allocation multi-distribution MFN reliability problem. The effectiveness and time complexity of the proposed algorithm are analyzed, and a benchmark example is provided to demonstrate how to minimize the total budget under the condition that the network reliability is not below a specific threshold.
{"title":"A reliability-related optimization problem in multidistribution multi-state logistics network","authors":"Yilin Song, Yi-Feng Niu","doi":"10.1109/PHM-Nanjing52125.2021.9612768","DOIUrl":"https://doi.org/10.1109/PHM-Nanjing52125.2021.9612768","url":null,"abstract":"Logistics networks, as the fundamental infrastructure, play a critical role in boosting economic prosperity. In this paper, we model a logistics network as a multidistribution multi-state flow network (MFN) in which each arc has random capacity characterized by more than one probability distribution under different budget allocations. Accordingly, we construct an optimization model to minimize the total budget required for the network to achieve a given reliability value. To address this challenging reliability-related optimization problem, an effective method is developed by integrating the well-known binary-search method and an existing method that solves the budget-allocation multi-distribution MFN reliability problem. The effectiveness and time complexity of the proposed algorithm are analyzed, and a benchmark example is provided to demonstrate how to minimize the total budget under the condition that the network reliability is not below a specific threshold.","PeriodicalId":436428,"journal":{"name":"2021 Global Reliability and Prognostics and Health Management (PHM-Nanjing)","volume":"65 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2021-10-15","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"126677227","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 : 2021-10-15DOI: 10.1109/PHM-Nanjing52125.2021.9612929
Xiao-chao Li, Xia Yu
The current talent training model evaluation model uses the AHP method to calculate the evaluation index weights, which leads to the calculation of the evaluation index weights of the new English talent training model, which is difficult to pass the consistency test. To solve this problem, a new type of English talent training based on the AHP-entropy weight method is proposed. Model evaluation model. Based on the five principles of evaluation indicators, the evaluation indicators of the new English talent training model are divided into four levels: target level, criterion level, first-level index factor level and second-level index factor level, and establish an evaluation index system; The evaluation index system is divided into five levels and assigned to determine the set of evaluation system comments; The change of evaluation index is controlled between 0 and 1, and it is divided into positive index and negative index; Entropy weight method and AHP method are used to calculate the weight of evaluation index respectively. According to the calculation results, the weight of comprehensive evaluation index is obtained, and the final evaluation result is obtained through multi-level and step-by-step evaluation. The experimental results show that: the calculated evaluation index weight, the consistency test result is less than 0.1, and the consistency test is passed.
{"title":"Evaluation Model of New English Talents Training Model Based on AHP-Entropy Method","authors":"Xiao-chao Li, Xia Yu","doi":"10.1109/PHM-Nanjing52125.2021.9612929","DOIUrl":"https://doi.org/10.1109/PHM-Nanjing52125.2021.9612929","url":null,"abstract":"The current talent training model evaluation model uses the AHP method to calculate the evaluation index weights, which leads to the calculation of the evaluation index weights of the new English talent training model, which is difficult to pass the consistency test. To solve this problem, a new type of English talent training based on the AHP-entropy weight method is proposed. Model evaluation model. Based on the five principles of evaluation indicators, the evaluation indicators of the new English talent training model are divided into four levels: target level, criterion level, first-level index factor level and second-level index factor level, and establish an evaluation index system; The evaluation index system is divided into five levels and assigned to determine the set of evaluation system comments; The change of evaluation index is controlled between 0 and 1, and it is divided into positive index and negative index; Entropy weight method and AHP method are used to calculate the weight of evaluation index respectively. According to the calculation results, the weight of comprehensive evaluation index is obtained, and the final evaluation result is obtained through multi-level and step-by-step evaluation. The experimental results show that: the calculated evaluation index weight, the consistency test result is less than 0.1, and the consistency test is passed.","PeriodicalId":436428,"journal":{"name":"2021 Global Reliability and Prognostics and Health Management (PHM-Nanjing)","volume":"25 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2021-10-15","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"126678212","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}
In this paper, the dynamic model of a slender shaft flexible rotor is established by using the finite element method. The first two natural frequencies and mode shapes of the system are solved by using the characteristic equation, and the unbalanced vibration response of the flexible rotor system is calculated by using the Newmark numerical integration method. The sub critical, critical and supercritical states of the rotor are analyzed respectively. The sensitivity of the axial position of the slender shaft to the unbalance mass is analyzed through simulation calculation.
{"title":"Analysis of unbalance sensitive position of flexible slender shaft rotor","authors":"Shuo Han, Haobo Wang, Tongguang Yang, Qingkai Han, Hao Zhang","doi":"10.1109/PHM-Nanjing52125.2021.9613108","DOIUrl":"https://doi.org/10.1109/PHM-Nanjing52125.2021.9613108","url":null,"abstract":"In this paper, the dynamic model of a slender shaft flexible rotor is established by using the finite element method. The first two natural frequencies and mode shapes of the system are solved by using the characteristic equation, and the unbalanced vibration response of the flexible rotor system is calculated by using the Newmark numerical integration method. The sub critical, critical and supercritical states of the rotor are analyzed respectively. The sensitivity of the axial position of the slender shaft to the unbalance mass is analyzed through simulation calculation.","PeriodicalId":436428,"journal":{"name":"2021 Global Reliability and Prognostics and Health Management (PHM-Nanjing)","volume":"14 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2021-10-15","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"126844217","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 : 2021-10-15DOI: 10.1109/PHM-Nanjing52125.2021.9612880
Yulong Yang, Hao Fu, Jianhua Wang, Yongbo Li
Rubbing fault in rotor shafts severely affects the safe and stable operation of a rotating machine. Hence, in this paper a dual-rotor rub-impact fault simulation is designed through a small-scale experiment platform. In this context, rubbing fault of rotor shaft is analyzed with the help of vibration signal collected from the shaft, its rotating speed and corresponding motor current signal. By selecting and configuring sensors and different stopping methods, a small-scale rotor rubbing test system based on Arm is built. The designed test system can simulate the full periphery friction of the rotor shaft in different degrees. Using modular design ideas, a data acquisition and analysis system for the dual-rotor test bench was developed. Real time data corresponding to vibration acceleration signal, rotor rotating speed signal & used motor current signal have been collected in order to study different performance characteristics under the influence of rubbing phenomena. Experiments show that the proposed system can not only simulate the rubbing fault of the rotor system successfully but also can provide a dynamic demonstration of the rubbing fault diagnosis.
{"title":"Research on the rubbing fault diagnosis of rotor shafts using the double-rotor test bench","authors":"Yulong Yang, Hao Fu, Jianhua Wang, Yongbo Li","doi":"10.1109/PHM-Nanjing52125.2021.9612880","DOIUrl":"https://doi.org/10.1109/PHM-Nanjing52125.2021.9612880","url":null,"abstract":"Rubbing fault in rotor shafts severely affects the safe and stable operation of a rotating machine. Hence, in this paper a dual-rotor rub-impact fault simulation is designed through a small-scale experiment platform. In this context, rubbing fault of rotor shaft is analyzed with the help of vibration signal collected from the shaft, its rotating speed and corresponding motor current signal. By selecting and configuring sensors and different stopping methods, a small-scale rotor rubbing test system based on Arm is built. The designed test system can simulate the full periphery friction of the rotor shaft in different degrees. Using modular design ideas, a data acquisition and analysis system for the dual-rotor test bench was developed. Real time data corresponding to vibration acceleration signal, rotor rotating speed signal & used motor current signal have been collected in order to study different performance characteristics under the influence of rubbing phenomena. Experiments show that the proposed system can not only simulate the rubbing fault of the rotor system successfully but also can provide a dynamic demonstration of the rubbing fault diagnosis.","PeriodicalId":436428,"journal":{"name":"2021 Global Reliability and Prognostics and Health Management (PHM-Nanjing)","volume":"46 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2021-10-15","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"126339300","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 : 2021-10-15DOI: 10.1109/PHM-Nanjing52125.2021.9612903
Xiang Liu
This paper focuses on the principle of electromagnetic braking and energy feedback when the motor speed is lower than a certain speed of no-load motor, and puts forward a simple control method of low-speed energy feedback braking. Through computer simulation and prototype experiment, it can be seen that the control method proposed in this paper can easily achieve the low-speed energy feedback braking effect of the electric vehicle water magnetic brushless direct charging motor system, and ensure the safety of vehicle driving.
{"title":"Low-speed energy feedback braking method for motor system of rod pumping equipment","authors":"Xiang Liu","doi":"10.1109/PHM-Nanjing52125.2021.9612903","DOIUrl":"https://doi.org/10.1109/PHM-Nanjing52125.2021.9612903","url":null,"abstract":"This paper focuses on the principle of electromagnetic braking and energy feedback when the motor speed is lower than a certain speed of no-load motor, and puts forward a simple control method of low-speed energy feedback braking. Through computer simulation and prototype experiment, it can be seen that the control method proposed in this paper can easily achieve the low-speed energy feedback braking effect of the electric vehicle water magnetic brushless direct charging motor system, and ensure the safety of vehicle driving.","PeriodicalId":436428,"journal":{"name":"2021 Global Reliability and Prognostics and Health Management (PHM-Nanjing)","volume":"18 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2021-10-15","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"126481113","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 : 2021-10-15DOI: 10.1109/PHM-Nanjing52125.2021.9612799
Junjun Dong, W. Dai
Permutation entropy (PE) is usually used as a statistical feature combined with classification algorithms to identify the state of rolling bearings and has achieved high recognition accuracy. The purpose of this paper is to study the potential behavior of PE at varying parameters in rolling bearing vibration signals for the normal state and three fault states (including inner race, outer race, and ball fault). The influence of the vibration signal length (N) and the parameter embedding dimension (m) on the PE were studied, and the signal length when they reached stability was analyzed. Then PE with varying signal lengths of each state at m=3 and m=5 was compared. Finally, the ordinal patterns found and their relative frequency in each state’s vibration signal with varying m were analyzed, and the differences were discussed. The results indicated that the different states of rolling bearing could be effectively distinguished with a shorter time series than the $N gg m !$ recommendation. PE could sensitively distinguish between the normal state and fault states, which may be due to the difference in the number of ordinal patterns found at the same length signal and the difference in relatively high-frequency ordinal pattern types and their relative frequency. The identification of outer race and ball fault is more difficult than that of inner race fault by PE, which may be due to the fact that the ordinal patterns and their relative frequency in the vibration signals between the outer race and ball fault are similar to a certain extent, while inner race fault is different from them.
排列熵(PE)通常作为一种统计特征与分类算法相结合来识别滚动轴承的状态，并取得了较高的识别精度。本文的目的是研究正常状态和三种故障状态(包括内圈、外圈和球故障)下滚动轴承振动信号中PE在不同参数下的潜在行为。研究了振动信号长度(N)和参数嵌入维数(m)对PE的影响，并分析了它们达到稳定时的信号长度。然后比较m=3和m=5各状态下不同信号长度的PE。最后，分析了各状态振动信号中随m变化的序数模式及其相对频率，并讨论了差异。结果表明，与推荐的N gg m !$时间序列相比，该方法可以有效区分滚动轴承的不同状态。PE能够灵敏地区分正常状态和故障状态，这可能是由于在相同长度的信号中发现的序数模式数量不同，相对高频的序数模式类型及其相对频率不同。用PE识别外圈和球故障比识别内圈故障更困难，这可能是由于外圈和球故障之间的振动信号的序数模式和相对频率在一定程度上相似，而内圈故障与外圈和球故障不同。
{"title":"Vibration Signal Analysis of Rolling Bearing Based on Permutation Entropy","authors":"Junjun Dong, W. Dai","doi":"10.1109/PHM-Nanjing52125.2021.9612799","DOIUrl":"https://doi.org/10.1109/PHM-Nanjing52125.2021.9612799","url":null,"abstract":"Permutation entropy (PE) is usually used as a statistical feature combined with classification algorithms to identify the state of rolling bearings and has achieved high recognition accuracy. The purpose of this paper is to study the potential behavior of PE at varying parameters in rolling bearing vibration signals for the normal state and three fault states (including inner race, outer race, and ball fault). The influence of the vibration signal length (N) and the parameter embedding dimension (m) on the PE were studied, and the signal length when they reached stability was analyzed. Then PE with varying signal lengths of each state at m=3 and m=5 was compared. Finally, the ordinal patterns found and their relative frequency in each state’s vibration signal with varying m were analyzed, and the differences were discussed. The results indicated that the different states of rolling bearing could be effectively distinguished with a shorter time series than the $N gg m !$ recommendation. PE could sensitively distinguish between the normal state and fault states, which may be due to the difference in the number of ordinal patterns found at the same length signal and the difference in relatively high-frequency ordinal pattern types and their relative frequency. The identification of outer race and ball fault is more difficult than that of inner race fault by PE, which may be due to the fact that the ordinal patterns and their relative frequency in the vibration signals between the outer race and ball fault are similar to a certain extent, while inner race fault is different from them.","PeriodicalId":436428,"journal":{"name":"2021 Global Reliability and Prognostics and Health Management (PHM-Nanjing)","volume":"124 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2021-10-15","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"123081788","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：