Research on track fault diagnosis method of mechanical parking equipment based on deep learning

With the development of China's urbanization and economy, the problem of parking difficulties in big cities has gradually become prominent, and the parking equipment used to alleviate such problems has emerged, but the accompanying safety problems of parking equipment such as trapped car accidents have gradually attracted attention. The research on safety guarantee of parking equipment needs to be carried out urgently, and the work of safety assessment and fault prevention of parking equipment is constantly carried out. This paper presents a new fault diagnosis model for the track of mechanical parking equipment. The vibration signal data of the running track of the mechanical parking equipment under different operating conditions were collected, and the time-frequency diagram of the vibration signal was obtained by using wavelet transform. The time-frequency diagram of the fault samples was expanded by SinGAN, and the BiLSTM-CNN neural network fault diagnosis model was built for training. The example shows that the track fault diagnosis model based on BiLSTM-CNN is suitable for practical application and can accurately diagnose the track fault of mechanical parking equipment.