BP neural network intelligent gearbox fault
diagnosis Based on Matlab
Student's name: Sun Zhi Gang Director: Jiang YU
(School of Mechanical Electronic & Information Engineering，Huang Shan University，245041） Abstract: This article is aiming at study on neural network fault diagnosis of gearbox.Gear transmission is one of the most important drive of mechanical transmission.Mechanical damage and failure often result in equipment failure which lead to significant safety accident.Therefore，condition monitoring and fault diagnosis of gearbox gear have been more and more attention and research.This paper briefly introduce the mechanism of gear vibration and the principle and structure of the BP neural network, and neural network was applied to gearbox fault detection and diagnosis. The neural network model is established based on matlab language，and the feature vector which is extracted through the vibration signal is trained in the established neural network model.The trained BP neural network model is used to simulate the gear box fault detection，and good results have been achieved.
Keywords: BP neural network; fault diagnosis; gear box ;feature vector
