Performance degradation trend prediction method based on collaborative derivation related entropy extreme learning machine

Abstract

The invention discloses a performance degradation trend prediction method based on a collaborative derivation related entropy extreme learning machine. The method comprises the following steps: firstly, calculating hidden layer output of an input sample based on an extreme learning machine of collaborative derivation correlation entropy; and corresponding prediction error, solving an optimal correlation entropy variance and an influence weight through a collaborative derivation algorithm; performing update iteration, until a global optimal solution [sigma]gbest in the particle swarm is found;q2 and the corresponding influence weight serving as the optimal correlation entropy variance and the influence weight, finally, under the condition that calculation convergence of the extreme learning machine is met, outputting a prediction value of the input sample, and therefore the performance degradation trend of the input sample is obtained, and the method has the advantages of being high inprediction precision, high in robustness and the like.

Description

technical field [0001] The invention belongs to the technical field of electronic devices, and more specifically relates to a performance degradation trend prediction method based on a cooperative derivation correlation entropy extreme learning machine. Background technique [0002] With the increasing update speed of electronic systems, the requirements for reliability analysis of electronic devices are further increased. The prediction of the degradation trend of electronic devices can better improve the maintenance efficiency of the system, so the related research has extremely high application value. In recent years, the degradation trend prediction method based on extreme learning machine has been widely used in the fault diagnosis of electronic devices due to its fast model training, simple structure, and high prediction accuracy. However, the vast majority of extreme learning machine prediction methods use the least mean square criterion as the training basis for the...

AI Technical Summary

Problems solved by technology

Since the criterion assumes that the model error obeys a normal distribution condition, non-normally distributed noise and singular values ​​in the training data can easily have a negative impact on the prediction model, causing the model to fail to give correct prediction results

Images