Jixie chuandong (Apr 2021)
Fault Diagnosis of Gearbox Multi-channel Vibration Signal based on Improved Multivariate Multiscale Dispersion Entropy
Abstract
When the gearbox fails， its vibration signal is unstable and nonlinear. The commonly applied gearbox fault diagnosis methods are almost all based on the single-channel vibration signal analysis，which is easy to cause the loss of fault information，so the practicality in industrial production is limited. In order to overcome this defect， the multivariate multiscale dispersion entropy is introduced into the gearbox fault diagnosis. Meanwhile， the coarse graining method of it is improved， and improved multivariate multiscale dispersion entropy（IMMDE） is proposed to extract fault information of multi-channel vibration signal of gearbox. Based on this，a new gearbox fault diagnosis method based on ensemble empirical mode decomposition （EEMD），IMMDE and genetic algorithm optimization support vector machine（GA-SVM） is proposed. Through the analysis of experimental data， it can be seen that this method has higher accuracy and stability compared with multivariate multiscale sample entropy（MMSE） and multivariate multiscale fuzzy entropy （MMFE），and has obvious advantages in dealing with short time series.
