A step-down DC-DC power supply module remaining service life prediction and health assessment method

Abstract

The invention discloses a step-down DC-DC power supply module remaining service life prediction and health assessment method, and the steps are as follows: 1. establishing a fault information analysissystem by analyzing the failure reasons of overcurrent, short circuit caused by surge strike, thermal shock, vibration and corrosion of a DC-DC power supply module under the influence of electrical over stress and environment stress; 2. inputting corresponding test signals, monitoring output characteristic signal of the step-down DC-DC power supply module and collecting monitoring data for preprocessing, which is used as learning sample data of a SVM; 3. establishing a prediction model of output abnormality of the DC-DC power supply module by the support vector machine, using the collected sample data for training and learning; 4, training errors between the sample data and the prediction result by establishing a time series, and adding the result with the original prediction data; 5. according to the output signal characteristics of the step-down DC-DC power supply module, establishing health state classification; 6. establishing an artificial neural network system to perform original state identification, and using the collected sample data to train and learn; 7. inputting real-time signals into a prediction system, and comprehensively analyzing the results of the support vectormachine model and artificial neural network system modified by the time series. An intelligent algorithm is utilized to perform step-down DC-DC power module fault prediction and health state assessment, the technical threshold of power supply system maintenance guarantee is lowered, and the method has certain engineering practical value.

Description

technical field [0001] The invention relates to a remaining service life prediction and health evaluation method of a step-down DC-DC power supply module, which belongs to the field of failure prediction of electronic devices. Background technique [0002] The DC conversion (DC-DC) power supply module is the power supply of the electronic system. There are two types of step-up and step-down. Programmable Gate Array (FPGA) and other digital or analog loads. With the improvement of electronic information technology, the step-down DC-DC power supply module is widely used in various fields such as electric power, industrial control, medical treatment and military industry, and its functional characteristics and reliability are very important. [0003] Improving the adaptability of the power supply system and its components under special working conditions has become a key consideration. In order to avoid the failure of the power system caused by the step-down DC-DC power suppl...

AI Technical Summary

Problems solved by technology

[0008] The purpose of the present invention is to solve the deficiencies in the prior art, to provide an intelligent step-down method based on support vector machines and artificial neural networks that can solve the problem of predicting the remaining service life and health status of step-down DC-DC power supply modules. Fault Prediction Method for Type DC-DC Power Module

Images