A New Health State Identification Method for Rotating Machinery Based on HHORF

The rotating machinery operates under complex conditions with high loads and is prone to failures, thus affecting the productivity of the machine or system. To solve the problem of health state identification of rotating machinery, the random forest (HHO-RF) algorithm based on Harris Hawk optimization (HHO) is proposed to optimize the number of decision trees and the maximum depth of the decision trees for random forests with the HHO algorithm, which avoids the arbitrariness of manually determining the model parameters. Experiments are carried out using the PHM2012 bearing full life-cycle degradation data. The results show that compared with the methods of support vector machine, K-nearest neighbor, decision tree and neural network, the proposed HHO-RF model can achieve effective health state identification of rotating machinery, and the model accuracy rate is about 8 4. 5 7%.