Power battery state-of-health estimation method and system based on multi-channel technology

Abstract

The invention belongs to the related technical field of power batteries, and discloses a multichannel technology-based power battery state-of-health estimation method, which comprises the following steps of: acquiring characteristic values of current, voltage and temperature change along with time of each battery in a battery sample under different charge-discharge cycle times; obtaining the battery capacity of the battery under each charge-discharge cycle according to the characteristic value so as to obtain a data set formed by the corresponding relationship between the characteristic valueand the battery capacity; constructing a prediction model and training the prediction model; and inputting the characteristic value of the to-be-predicted battery into the trained prediction model, and obtaining the health state of the to-be-predicted battery in combination with the rated capacity of the to-be-predicted battery. In addition, the invention further provides a system for estimating the health state of the power battery based on the multi-channel technology. The method and the system provided by the invention are simple and convenient to operate and wide in universality.

Description

technical field [0001] The invention belongs to the technical field related to power batteries, and more specifically relates to a method and system for estimating the state of health of power batteries based on multi-channel technology. Background technique [0002] Possible failures and health declines of the battery during application will have adverse effects, so to reduce these adverse effects, it is necessary to accurately estimate and predict the state of health (State of health, SOH) of the battery, because before the failure of the power battery is predicted Generally, it is necessary to estimate the SOH of the power battery, and the SOH of the battery is closely related to the capacity of the battery. During the use of the power battery, the capacity failure problem will inevitably occur, that is, the amount of electricity that can be charged into the battery is getting smaller and smaller. The cause of capacity fading is of vital significance to the study of the s...

AI Technical Summary

Problems solved by technology

This type of method does not need to establish a very precise mathematical model, and has a simple structure. It realizes intelligence by simulating human thinking, but this type of method also has limitations. Fuzzy logic lacks precision because the quantization level cannot be subdivided. Network laws require a large amount of learning methods and data, and it is difficult to find a general learning algorithm

(3) Data-driven related methods. This type of method needs to establish an abstract model with several parameters. The model is like a "black box". As long as the parameters of the "black box" are determined and the input is determined, the output will be obtained. but requires input of a large amount of representative data

Images