Lightweight method and equipment for power battery module and maximum stress value calculation method

Abstract

The invention discloses a power battery pack lightweight method based on a neural network. The method comprises the following steps: determining a first constraint range of a design variable and a second constraint range of a maximum stress value; acquiring a variable sample set, wherein the variable sample set comprises a plurality of design variable combinations conforming to the first constraint range, and the design variable combinations comprise a plurality of design variables related to stress values of the power battery module; calculating the maximum stress value and the battery moduleweight corresponding to the design variable combination according to the neural network approximation model; taking the weight of the battery module as a target, and calculating an optimal design variable combination according to a genetic algorithm. According to the method, a neural network and genetic algorithm combined solving method is adopted, the problem that a traditional method is prone to falling into a local optimal solution is avoided, and the maximum stress value of the power battery pack can be rapidly calculated. The invention further discloses a power battery module maximum stress value calculation method based on the neural network.

Description

technical field [0001] The invention relates to the design and calculation of a power battery module, in particular to the calculation of the maximum stress value of the power battery module and the determination of design variables in the power battery module. Background technique [0002] As an important component of new energy vehicles, the power battery module has always been the goal of research to reduce the weight of the power battery module, make full use of the mechanical properties of the material, and increase the energy density of the module. [0003] At present, the light weight of power modules is mostly verified by physical model verification or computer simulation for strength verification, and each model is gradually verified by using the exhaustive method, so as to select a power battery module model with light weight and strength that meets the requirements . This method of lightweighting through exhaustive methods may fall into the problem of local optim...

AI Technical Summary

Problems solved by technology

This method of lightweighting through exhaustive methods may fall into the problem of local optimal solutions. It is difficult to find a model with the strength that meets the requirements and the smallest weight. Moreover, this method is time-consuming and labor-intensive. Greatly reduces the development speed

Images