AGV Status Monitoring and Fault Diagnosis based on CNN

Abstract In order to solve the problem of AGV fault detection system’s complexion and low accuracy, a convolutional neural network (CNN) based on status monitoring diagnosis method for automatic guided vehicle (AGV) is proposed. Firstly, vibration signals core components are converted into two-dimensional (2D) images. Secondly, 2D images input convolution training. Finally, trained model used monitor running identify faults. The results show that proposed can effectively in operation.