Fusion model prediction of rolling bearing vibration signal based on chaos theory,

The fusion algorithm model was used to predict the vibration signal of rolling bearing on the basis of chaos theory. Based on the phase diagram method, the maximum Lyapunov exponent method and the correlation dimension method, the chaos characteristic of rolling bearing vibration signal was proved. The weights of Kriging model, least squares support vector machine（LSSVM）model and extreme learning machine（ELM）model were optimized to minimize the norm of the difference between the predicted value and the true value, and the fusion algorithm model was constructed by weighting method. The phase space reconstruction method was used to construct the training samples of the rolling bearing vibration signal prediction, and the fusion model, Kriging model, LSSVM model and ELM model were trained. The trained model was used to predict the vibration signal of rolling bearing. For case 1 and case 2, the rolling bearing vibration signals of two experiments were used to verify the results. The maximum Lyapunov exponent for two cases was greater than 0, from which chaotic characteristic on bearing vibration signal can be determined. Besides, the index value for fusion model was less than the single model from the evaluation index of mean squared error, root mean squared error and mean absolute error, so the prediction accuracy of the fusion algorithm model was better than that of the single algorithm model.