Battery fault detection model training method, device and equipment and storage medium

Abstract

The invention relates to the field of battery fault detection, and provides a battery fault detection model training method and device, equipment and a storage medium. The method comprises the steps of obtaining a plurality of preset system variables; acquiring a plurality of battery data to be processed; extracting a plurality of to-be-processed battery data according to a plurality of preset system variables to obtain at least one corresponding characteristic value; calculating at least one corresponding feature vector according to the at least one feature value to obtain at least one targetvector; inputting the at least one target vector into a support vector machine model under a plurality of parameters to obtain a plurality of trained support vector machine models; calculating the accuracy of each trained support vector machine model to obtain the accuracy of a plurality of models; and selecting the trained support vector machine model with the highest accuracy as a target model.And the detection efficiency of the battery fault is improved.

Description

technical field [0001] The present invention relates to the field of battery fault detection, in particular to a battery fault detection model training method, device, equipment and storage medium. Background technique [0002] Solid oxide fuel cell system (Solid Oxide Fuel Cell, SOFC) is a new type of high-efficiency and environmentally friendly energy conversion device, which is mainly used in combined heat and power generation such as cycle power plants, hotels, residential buildings, and transportation. However, its widespread commercial application still faces the challenges of low durability, reliability, and high cost. At present, the research on fault diagnosis of SOFC is concentrated on the stack or single cell level, and the research on fault diagnosis on the system level is very lacking. In addition, at this stage, because many research teams have failed to build a complete SOFC independent power generation system, most of the research is to simulate the fault by...

AI Technical Summary

Problems solved by technology

However, its wide commercial application still faces challenges of low durability, reliability and high cost

At present, the research on SOFC fault diagnosis is concentrated on the stack or single cell level, and the research on fault diagnosis at the system level is very lacking.

In addition, at this stage, because many research teams have failed to build a complete SOFC independent power generation system, most of the research is to simulate the fault by establishing a simulation model, and the difference between the simulation model and the actual system is significant, resulting in the researched faults departing from the real SOFC system.

Make SOFC system cannot be diagnosed in time when it is running efficiently

Images