Gearbox fault diagnosis method based on minimum Bayesian risk reclassification and adaptive weight

Abstract

The invention discloses a gearbox fault diagnosis method based on minimum Bayesian risk reclassification and adaptive weight. The method comprises the steps of: collecting all operation monitoring parameters of a gearbox through employing a multi-path signal sensor, and obtaining multi-path time sequence parameter data; performing feature extraction and dimension reduction based on the multi-path time sequence parameter data to obtain a dimension-reduced feature vector after dimension reduction; inputting the dimension-reduced reduction feature vector of each path of the multi-path signal into a probabilistic neural network (PNN) classifier, and training the PNN classifier; constructing a minimum Bayesian risk reclassification model, and inputting the preliminary classification result into the minimum Bayesian risk reclassification model to obtain a reclassification result; and automatically fusing the reclassification results by using a decision information fusion algorithm based on a self-adaptive weighting mechanism to obtain a more stable final classification result of fault diagnosis of the gearbox.

Description

technical field [0001] The invention relates to the field of equipment fault diagnosis, in particular to a gearbox fault diagnosis method based on minimum Bayesian risk reclassification and self-adaptive weight. Background technique [0002] With the rapid development of industry, mechanical equipment tends to become larger, more complex and more important. The health problems of mechanical equipment have attracted more and more attention. Gearboxes are widely used in wind power generation, aviation and other industrial fields as rotating machinery to adjust speed and torque. Due to the particularity of the industrial environment, important parts of the gearbox, such as gears and bearings, usually run for a long time in a high-speed, heavy-loaded industrial environment, which often leads to gearbox failures. Once a failure occurs, long-term maintenance and high maintenance costs are inevitable, which will bring huge economic losses. Therefore, how to effectively diagnose ...

AI Technical Summary

Problems solved by technology

[0006] In addition, due to the different quality, installation position and anti-interference ability of each sensor, the fault diagnosis ability of each sensor is unba

Images