基于深度学习的铁路客车转向架常见故障的自动检测

Automatic Detection of Common Faults in Railway Passenger Car Bogies Based on Deep Learning

铁路客车转向架在客车安全运行中发挥重要作用,为此,研究了人工智能在铁路安全中的应用,并基于YOLOv4的单阶段深度学习方法对铁路客车转向架可视部位的油压减震器漏油、夹带异物和车钩缓冲器失效故障进行了检测。首先介绍了目标检测模型的结构,采用K-means++聚类方法生成了更准确的锚眶位置和参数。然后建立了转向架关键部位的故障图像数据集,并进行了数据增强处理,以尽可能地减少过拟合,提高深度神经网络模型的性能。最后通过对比实验,证明了基于深度学习的故障检测精度在不同客车转向架不同位置的故障检测场景中具有更好的效果。

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.