Relay storage life prediction method based on AMFO algorithm and SVM algorithm

Abstract

The invention relates to a relay storage life prediction method based on an AMFO algorithm and an SVM algorithm. The method comprises the following steps: step 1, obtaining material performance parameters; 2, performing principal component analysis on the parameter data to obtain principal component variables; 3, taking training set data and test set data from the principal component variables, and inputting the training set data into the SVM model for training learning; 4, optimizing parameters in a kernel function of the SVM model by adopting a self-adaptive moth flame optimization algorithm, constructing the SVM model by utilizing the optimal parameters, and establishing the optimized model for life prediction; 5, setting a failure threshold value, and predicting a degradation curve reaching the failure threshold value; and step 6, calculating a probability density function to obtain a final predicted life. According to the invention, the data sample is put into the SVM model for training and then life prediction is carried out, and a nonlinear dynamic adaptive step length method is introduced, so that the moth search capability can be enhanced, and the global optimization capability of moths can be improved.

Description

technical field [0001] The invention relates to a method for predicting the storage life of a relay, in particular to a method for predicting the storage life of a relay which combines an adaptive moth flame optimization algorithm and an SVM algorithm. Background technique [0002] As a basic electrical control device, the electromagnetic relay has the advantages of high switching depth and good physical isolation performance, and is widely used in aerospace, military and other electrical control fields. For relays on electronic devices, the long-term storage phase is an essential link. In the long-term storage link, due to the influence of environmental factors, the relay may fail when used, resulting in failure of electronic products. [0003] The storage life of the relay is an important parameter to study the storage reliability of the relay. Studying the prediction method of relay storage life can accurately predict the storage life of relays, and analyze the manifest...

AI Technical Summary

Problems solved by technology

[0006] In order to solve the problems of slow calculation speed and low prediction accuracy of the relay storage failure life prediction algorithm in the prior art, the present invention provides a relay storage life prediction method that combines the adaptive moth flame optimization algorithm (AMFO algorithm) and the SVM algorithm , from the perspective of safety and reliability, the present invention uses the principal component analysis method to perform feature dimension reduction processing on the data, uses the improved gray wolf algorithm to find the optimal parameters, puts the data samples into the SVM model for training, and then performs For life prediction, a nonlinear dynamic adaptive step size method is introduced. When moths approach the candle to find the optimal solution, the larger the value of the adaptive step size, the larger the search range of the algorithm and the greater the search strength. Larger so that the search ability of moths can be enhanced, and the global optimization ability of moths can be improved

Images