The aging prediction of railway catenary is of profound significance for ensuring the regular operation of electrified trains.However,in real-world scenarios,accurate predictions are challenging due to various interfe...The aging prediction of railway catenary is of profound significance for ensuring the regular operation of electrified trains.However,in real-world scenarios,accurate predictions are challenging due to various interferences.This paper addresses this challenge by proposing a novel method for predicting the aging of railway catenary based on an improved Kalman filter(KF).The proposed method focuses on modifying the priori state estimate covariance and measurement error covariance of the KF to enhance accuracy in complex environments.By comparing the optimal displacement value with the theoretically calculated value based on the thermal expansion effect of metals,it becomes possible to ascertain the aging status of the catenary.To improve prediction accuracy,a railway catenary aging prediction model is constructed by integrating the Takagi-Sugeno(T-S)fuzzy neural network(FNN)and KF.In this model,an adaptive training method is introduced,allowing the FNN to use fewer fuzzy rules.The inputs of the model include time,temperature,and historical displacement,while the output is the predicted displacement.Furthermore,the KF is enhanced by modifying its prior state estimate covariance and measurement error covariance.These modifications contribute to more accurate predictions.Lastly,a low-power experimental platform based on FPGA is implemented to verify the effectiveness of the proposed method.The test results demonstrate that the proposed method outperforms the compared method,showcasing its superior performance.展开更多
With the wide application of the LFP lithium-ion batteries,more attention is paid to the battery life and future aging behaviors as the safety and performance of the battery are guaranteed by accurate battery aging mo...With the wide application of the LFP lithium-ion batteries,more attention is paid to the battery life and future aging behaviors as the safety and performance of the battery are guaranteed by accurate battery aging monitoring.In recent years,long-term aging trajectory prediction of the lithium-ion battery is always a challenge due to its complex nonlinear aging behaviors especially the aging behaviors in the two aging stages are quite different when the battery experiences the two-stage aging process under fast-charging conditions.Thus,it is harder to achieve accurate long-term aging trajectory prediction of the LFP lithium-ion batteries on the condition of the two-stage aging process.To address it,a novel transfer learning strategy combined with the cycle life prediction technology is presented in this paper.Specifically,a new cycle life prediction method is proposed based on feature extraction and deep learning technology and achieves accurate cycle life prediction.The transfer learning is started by developing a base aging model offline to learn the information of the two-stage aging process.Then,taking the predicted cycle life as its prior information,the Bayesian model migration technology is employed to predict the aging trajectory accurately,and the uncertainty of the aging trajectory is quantified.Two batches of the battery datasets are used for performance evaluation and comparison with two benchmarks.It is novel to combine the cycle life prediction and transfer learning technique to achieve accurate two-stage aging trajectory prediction with only a few data available(first 30%).展开更多
基金supported by the Science and Technology Research Project of Henan Province (No.222102210087)the Science and Technology Research Project of Henan Province (No.222102220102).
文摘The aging prediction of railway catenary is of profound significance for ensuring the regular operation of electrified trains.However,in real-world scenarios,accurate predictions are challenging due to various interferences.This paper addresses this challenge by proposing a novel method for predicting the aging of railway catenary based on an improved Kalman filter(KF).The proposed method focuses on modifying the priori state estimate covariance and measurement error covariance of the KF to enhance accuracy in complex environments.By comparing the optimal displacement value with the theoretically calculated value based on the thermal expansion effect of metals,it becomes possible to ascertain the aging status of the catenary.To improve prediction accuracy,a railway catenary aging prediction model is constructed by integrating the Takagi-Sugeno(T-S)fuzzy neural network(FNN)and KF.In this model,an adaptive training method is introduced,allowing the FNN to use fewer fuzzy rules.The inputs of the model include time,temperature,and historical displacement,while the output is the predicted displacement.Furthermore,the KF is enhanced by modifying its prior state estimate covariance and measurement error covariance.These modifications contribute to more accurate predictions.Lastly,a low-power experimental platform based on FPGA is implemented to verify the effectiveness of the proposed method.The test results demonstrate that the proposed method outperforms the compared method,showcasing its superior performance.
基金the National Natural Science Foundation of China(No.52172400).
文摘With the wide application of the LFP lithium-ion batteries,more attention is paid to the battery life and future aging behaviors as the safety and performance of the battery are guaranteed by accurate battery aging monitoring.In recent years,long-term aging trajectory prediction of the lithium-ion battery is always a challenge due to its complex nonlinear aging behaviors especially the aging behaviors in the two aging stages are quite different when the battery experiences the two-stage aging process under fast-charging conditions.Thus,it is harder to achieve accurate long-term aging trajectory prediction of the LFP lithium-ion batteries on the condition of the two-stage aging process.To address it,a novel transfer learning strategy combined with the cycle life prediction technology is presented in this paper.Specifically,a new cycle life prediction method is proposed based on feature extraction and deep learning technology and achieves accurate cycle life prediction.The transfer learning is started by developing a base aging model offline to learn the information of the two-stage aging process.Then,taking the predicted cycle life as its prior information,the Bayesian model migration technology is employed to predict the aging trajectory accurately,and the uncertainty of the aging trajectory is quantified.Two batches of the battery datasets are used for performance evaluation and comparison with two benchmarks.It is novel to combine the cycle life prediction and transfer learning technique to achieve accurate two-stage aging trajectory prediction with only a few data available(first 30%).
