The Application Of The Particle Filter Technology In The Diagnosis Of The Gearbox

Gearbox is an important part of mechanical equipment, and the research of monitoring and fault diagnosis has great guidance. Because the gear box's structure is complex and its working environment is bad, when the fault of gear box occurs, the vibration signals often show non-stationary characteristics and the fault information is often submerged in the strong background noise, it needs to carry out noise reduction before failure analysis.The Particle Filter is a filter method based on Monte-Carlo Simulation and Recursive Beyesian Estimation. The state space is recursively got from measure space with system model by using the Particle Filter. It uses particles to describe the state space. The discretely random measure composed by particles and associated weights approximates to the true posterior state distribution, and is updated by iteration of the algorithm. The Particle Filter can resolve a problem on nonlinear and non-Gaussian model. Based on the deeply studying of the principle of particle filter ,this article use the particle filter to reduce the noise of gear vibration acceleration signals. ARMA model of the gear vibration signal is established and state the vibration signal in a state-space form. Then the assignment of denoising is treated as a filer problem.Through the above theoretical analysis, in this article,we take the gearbox as the experimental subject, measures vibration signal of gear-box by using the sensor which install on the measuring point, then reduce the noise by the particle filter, test and verify the algorithm through simulation and the measured signals. Finally, in this paper a fault detection approach based on PF state estimation is designed for fault detection of nonlinear system,then is applied to the gearbox and achieve some results.