Lithium battery capacity estimation method based on convolutional neural network

Abstract

The invention provides a lithium battery capacity estimation method based on a convolutional neural network. The lithium battery capacity estimation method comprises the following steps: constructing a battery parameter data set, performing a charge-discharge cycle experiment on batteries of the same specification, preprocessing data acquired in the step 1, and constructing input data of the neural network; constructing a convolutional neural network to carry out adaptive modification, ensuring the feature extraction capability and convergence capability of the network, and carrying out hyper-parameter optimization; obtaining an estimation model; and taking charging voltage and charging current data of the last charging process of the battery, processing the charging voltage and charging current data in the step 2, and inputting the data into the step 4 for calculation to obtain a capacity estimation value of the battery. The method provided by the invention has the advantage of transfer learning, effectively reduces the experimental test requirements of algorithm development, and shortens the development time. The research work lays a foundation for research and development of intelligent battery management.

Description

technical field [0001] The invention relates to a method for estimating the capacity of a lithium battery based on a convolutional neural network, and belongs to the technical fields of cascade utilization of batteries and neural network algorithms. Background technique [0002] The improvement of environmental awareness and the development of new energy have led to the rapid popularization of electric vehicles, the mass production and use of lithium batteries, and the increase in waste batteries. How to recycle and reuse waste batteries has become a popular research trend under the current environmental protection theme. Due to the high requirements of lithium batteries for vehicles, after the battery is decommissioned, its capacity and performance can still be used in other places. The performance of each single battery has a great impact on the performance of the battery as a whole. If the parameter performance is inconsistent, it will not only affect the efficiency of t...

AI Technical Summary

Problems solved by technology

However, there are relatively few studies on the extraction method of health characteristic parameters for waste power batteries.

[0004] Affected by various factors such as battery specifications, models, and usage conditions, decommissioned power batteries often lack consistency

The inconsistency of power batteries in terms of capacity, internal resistance, and voltage has become a major problem preventing cascade utilization

Images