Prediction Method of Equipment Degradation State Based on Improved RVM

In order to improve the prediction accuracy of the relevance vector machine model, an improved method for equipment condition prediction is proposed. First of all, an improved kernel function of variance Gauss kernel (VGKF) is constructed to improve the global performance and generalization ability of the kernel function. Then, by using the method of selecting the number of adjacent points in the chaotic sequence local prediction method, the HQ criterion was used to optimize the embedding dimension of the training space to avoid the blindness of subjective selection. Through the prediction example of terminal guidance radar equipment test parameters, the effectiveness and superiority of the improved RVM were verified.