Fault Diagnosis Method of Mine Hoist Braking System Based on Convolutional Neural Network

Abstract

A reliable braking system is an important guarantee for safe operation of mine hoist. In order to make full use of the monitoring data in the operation process of mine hoist, identify its operation status and further diagnose its fault, the deep learning method was introduced into the fault diagnosis of the hoist, and a fault diagnosis method of hoist braking system based on convolutional neural network (CNN) was proposed. First, the failure mechanism of the hoist braking system was analyzed, the monitoring parameters were determined, and the monitoring data under the normal state and fault simulation state of the hoist were collected. Then, a fault diagnosis model of the hoist braking system based on CNN was established. The monitoring data is encoded to generate a fault diagnosis data set, and the neural network is trained by the gradient descent method, and the structural parameters of the network are updated iteratively. Finally, the traditional back propagation (BP) neural network and CNN fault diagnosis model were compared and verified by test data set. The results show that the accuracy of CNN is higher than that of BP neural network, and the accuracy rate can reach 99.37%. This method can make full use of the monitoring data for diagnosis, without subjective intervention of experts, thus improving the accuracy of diagnosis.

Keywords

• deep learning
• mine hoist
• braking system
• fault diagnosis
• cnn