Electronic device residual life prediction method based on extreme gradient boosting tree algorithm

Abstract

The invention discloses an electronic device residual life prediction method based on an extreme gradient boosting tree algorithm. The method comprises the steps of obtaining multiple groups of aging data of an electronic device under the same condition; preprocessing the multiple groups of aging data and obtaining a failure variable in combination with an electronic device failure mechanism; performing cross correlation coefficient calculation between variables on the preprocessed aging data to obtain characteristic variables, wherein the correlation degree between the characteristic variables and the failure variables is not smaller than a correlation threshold value; establishing an aging model based on an extreme gradient lifting tree algorithm according to the aging data corresponding to the characteristic variables; and obtaining a predicted change value of the failure variable according to the aging model, and obtaining the residual life of the electronic device in combination with a set failure threshold value. According to the electronic device residual life prediction method, the aging model based on the extreme gradient boosting tree algorithm is adopted to process the aging data corresponding to the characteristic variables of the electronic device, the prediction change value of the failure variables is obtained, the residual life is obtained, the prediction precision is high, and the generalization ability is high.

Description

technical field [0001] The invention relates to the technical field of microelectronics, in particular to a method for predicting the remaining life of an electronic device based on an extreme gradient boosting tree algorithm. Background technique [0002] Predicting the remaining life of electronic devices can effectively ensure the safe use of electronic devices, monitor the operating status of electronic devices, and take protective measures in advance according to the prediction results to ensure work and production safety and reduce maintenance costs. [0003] As the internal structure of electronic devices becomes more and more complex, the amount of aging data of electronic devices is also large, and the variables that affect the aging of electronic devices are multivariate. Therefore, the traditional method of using empirical knowledge to select key predictor variables has a large workload and the prediction The accuracy is low and cannot meet the existing needs. ...

AI Technical Summary

Problems solved by technology

[0003] As the internal structure of electronic devices becomes more and more complex, the amount of aging data of electronic devices is also large, and the variables that affect the aging of electronic devices are multivariate. Therefore, the traditional method of using empirical knowledge to select key predictor variables has a large workload and the prediction The accuracy is low and cannot meet the existing needs

Images