Search

When a gearbox transmission system fails, the multi-scale mean permutation entropy （MMPE） of different vibration signals corresponds to the fault state to a certain extent. However, the effect of multi-scale mean permutation entropy extraction fault features depends on the selection of parameters. Therefore, this study proposes a gearbox fault identification method based on the improved multi-scale mean permutation entropy and the parameter optimization support vector machine（SVM）. Firstly, the particle swarm optimization （PSO） is referenced to optimize parameters of multi-scale mean permutation entropy. Secondly, the multi-scale mean permutation entropy of the collected gear vibration signals is calculated.Finally, the particle swarm optimization is used to optimize the support vector machine to identify the fault state of the gear. Experimental analysis results are conducted to validate the effectiveness of this proposed method.

When a gearbox transmission system fails, the multi-scale mean permutation entropy (MMPE) of different vibration signals corresponds to the fault state to a certain extent. However, the effect of multi-scale mean permutation entropy extraction fault features depends on the selection of parameters. Therefore, this paper proposes a gearbox fault identification method based on improved multi-scale mean permutation entropy and parameter optimization support vector machine. The particle swarm optimization (PSO) is referenced to optimize parameters of multi-scale mean permutation entropy; the multi-scale mean permutation entropy of the collected gear vibration signals wis calculated; the particle swarm optimization is used to optimize the support vector machine to identify the fault state of the gear. Experimental analysis results are conducted to validate the effectiveness of this proposed.