Automatic Detection of Common Faults in Railway Passenger Car Bogies Based on Deep Learning
The bogies of railway passenger cars play an important role in the safe operation of passenger cars.Therefore,this paper studies the application of artificial intelligence in railway safety,and uses YOLOv4's single-stage deep learning method to detect oil leakage,foreign object inclusion,and coupler buffer failure faults in the visible parts of railway passenger car bogies.Firstly,the structure of the target detection model is introduced,and the K-means++ clustering method is used to generate more accurate anchor orbital position and parameters.Then,the fault image data set of the key parts of the bogie is established,and the data enhancement processing is carried out to reduce the overfitting as much as possible and improve the performance of the deep neural network model.Finally,through comparative experiments,it is proved that the fault detection accuracy based on deep learning has better effect in different fault detection scenarios of different positions of passenger car bogies.
passenger car bogiedeep learningfault detectionYOLOv4
NETL
NSTL
万方数据
