As an important component of load transfer,various fatigue damages occur in the track as the rail service life and train traffic increase gradually,such as rail corrugation,rail joint damage,uneven thermite welds,rail ...As an important component of load transfer,various fatigue damages occur in the track as the rail service life and train traffic increase gradually,such as rail corrugation,rail joint damage,uneven thermite welds,rail squats fas-tener defects,etc.Real-time recognition of track defects plays a vital role in ensuring the safe and stable operation of rail transit.In this paper,an intelligent and innovative method is proposed to detect the track defects by using axle-box vibration acceleration and deep learning network,and the coexistence of the above-mentioned typical track defects in the track system is considered.Firstly,the dynamic relationship between the track defects(using the example of the fastening defects)and the axle-box vibration acceleration(ABVA)is investigated using the dynamic vehicle-track model.Then,a simulation model for the coupled dynamics of the vehicle and track with different track defects is established,and the wavelet power spectrum(WPS)analysis is performed for the vibra-tion acceleration signals of the axle box to extract the characteristic response.Lastly,using wavelet spectrum photos as input,an automatic detection technique based on the deep convolution neural network(DCNN)is sug-gested to realize the real-time intelligent detection and identification of various track problems.Thefindings demonstrate that the suggested approach achieves a 96.72%classification accuracy.展开更多
Many researchers are committed to improving the diagnosis accuracy and solving the few-shot problem on circuit breakers(CBs).However,the research on the vibration transmission mechanism of the fault is insufficient,wh...Many researchers are committed to improving the diagnosis accuracy and solving the few-shot problem on circuit breakers(CBs).However,the research on the vibration transmission mechanism of the fault is insufficient,which makes it difficult to find the potential design defects of CBs through vibration.This study proposes a quantitative evaluation method of mechanical defects,which can track and quantify mechanical defects caused by faults adaptively.The fault feature tracking based on ResNet-SHAP can locate the fault feature area in the time-frequency domain and generate the feature distribution maps of faults.Then,the feature factor F is defined to represent the energy of the fault feature.By weighted allocation and extracting positive F,the mechanical defect feature maps are formed.After time-frequency space reconstruction and contact travel matching,the mechanical defects are traced.Experiments show that the quantitative evaluation of mechanical defects has a strong action sequence and structural correlation,and is expandable to different structures of CBs.In addition,it is found that fault feature tracking can adaptively find latent fault features and has strong stability.展开更多
基金supported by the Doctoral Fund Project(Grant No.X22003Z).
文摘As an important component of load transfer,various fatigue damages occur in the track as the rail service life and train traffic increase gradually,such as rail corrugation,rail joint damage,uneven thermite welds,rail squats fas-tener defects,etc.Real-time recognition of track defects plays a vital role in ensuring the safe and stable operation of rail transit.In this paper,an intelligent and innovative method is proposed to detect the track defects by using axle-box vibration acceleration and deep learning network,and the coexistence of the above-mentioned typical track defects in the track system is considered.Firstly,the dynamic relationship between the track defects(using the example of the fastening defects)and the axle-box vibration acceleration(ABVA)is investigated using the dynamic vehicle-track model.Then,a simulation model for the coupled dynamics of the vehicle and track with different track defects is established,and the wavelet power spectrum(WPS)analysis is performed for the vibra-tion acceleration signals of the axle box to extract the characteristic response.Lastly,using wavelet spectrum photos as input,an automatic detection technique based on the deep convolution neural network(DCNN)is sug-gested to realize the real-time intelligent detection and identification of various track problems.Thefindings demonstrate that the suggested approach achieves a 96.72%classification accuracy.
基金supported by Smart Grid-National Science and Technology Major Project(Grant 2024ZD0802500).
文摘Many researchers are committed to improving the diagnosis accuracy and solving the few-shot problem on circuit breakers(CBs).However,the research on the vibration transmission mechanism of the fault is insufficient,which makes it difficult to find the potential design defects of CBs through vibration.This study proposes a quantitative evaluation method of mechanical defects,which can track and quantify mechanical defects caused by faults adaptively.The fault feature tracking based on ResNet-SHAP can locate the fault feature area in the time-frequency domain and generate the feature distribution maps of faults.Then,the feature factor F is defined to represent the energy of the fault feature.By weighted allocation and extracting positive F,the mechanical defect feature maps are formed.After time-frequency space reconstruction and contact travel matching,the mechanical defects are traced.Experiments show that the quantitative evaluation of mechanical defects has a strong action sequence and structural correlation,and is expandable to different structures of CBs.In addition,it is found that fault feature tracking can adaptively find latent fault features and has strong stability.
