Gear box fault diagnosis device and method thereof based on improved WPA-BP neural network

Abstract

The invention provides a gear box fault diagnosis device and a method thereof based on an improved WPA-BP neural network. The method includes the steps that experimental data of a gear box under the states of various working conditions are collected, eigenvalue index data under various working conditions are obtained, and the eigenvalue index data are divided into training samples and test samples; a BP neural network is establish; neural network parameters and improved WPA optimization parameters are set; aimed at the training samples, an improved WPA optimization method is used for optimizing training of weights and thresholds of a neural network, and an error of the neural network is tested by the test samples, the neural network parameters and the improved WPA optimization parameters are corrected by error test results, the optimization training of the weights and the thresholds of the neural network is carried out iteratively until a preset allowable error precision is met, and the weights and the thresholds of the neural network are obtained; and the neural network used for diagnosis and recognition of the gear box faults is obtained for fault diagnosis in real time. According to the gear box fault diagnosis device and the method thereof based on the improved WPA-BP neural network, the fault types in the gear box operation process can be determined efficiently and accurately, and the diagnosis and recognition effect is acquired.

Description

technical field [0001] The invention belongs to the technical field of gearbox fault diagnosis, in particular to a gearbox fault diagnosis device and method based on an improved WPA-BP neural network. Background technique [0002] As one of the important components in mechanical equipment, the gearbox is mainly used to transmit torque and force. It is widely used in modern industrial equipment such as aerospace, power systems, automobile manufacturing, agricultural machinery, and metallurgical machinery. However, due to its complex structure and harsh working environment, the gearbox is prone to failure. Gear failure is an important factor inducing machine failure. According to statistics, 80% of the faults in transmission machinery are caused by gears, and gear faults in rotating machinery account for about 10% of the faults. Therefore, it is of great practical significance to detect the working state of the gearbox in time, study the diagnosis technology and method to s...

AI Technical Summary

Problems solved by technology

Therefore, the traditional fault diagnosis technology has been difficult to meet the needs of the current production development, intelligent fault diagnosis technology is emerging

Images