Lithium battery capacity diving turning point identification method based on geometric feature fusion decision

Abstract

The invention relates to a lithium battery capacity diving turning point identification method based on a geometric feature fusion decision, and the method comprises the following steps: 1), obtaining a capacity recession curve of a to-be-identified lithium battery online, and carrying out smooth denoising and biaxial normalization processing to obtain a normalized lithium battery capacity recession curve; 2) connecting a starting point C1 and an ending point C2 on the normalized lithium battery capacity recession curve to form a completely linear aging reference line C1C2; 3) calculating the degree of deviation of points on the normalized lithium battery capacity recession curve from the aging reference line, comparing the maximum deviation value with a capacity diving early warning threshold beta, and judging whether capacity diving occurs or not in real time; and 4) triggering lithium battery capacity diving early warning when capacity diving occurs, and taking the point corresponding to the maximum deviation degree as the identified lithium ion battery capacity diving turning point. Compared with the prior art, the method has the advantages of accurate identification, automatic batch processing and the like.

Description

technical field [0001] The invention relates to the technical field of lithium battery monitoring, in particular to an online warning and turning point identification method for lithium battery capacity diving based on geometric feature fusion decision-making, which is used for online aging of lithium-ion batteries in electric vehicles, hybrid vehicles and energy storage fields Status evaluation and step-by-step utilization. Background technique [0002] The depletion of traditional energy sources and environmental pollution have caused the world to attach great importance to the field of new energy. my country has continuously increased its support for new energy vehicles and introduced a series of policies such as increasing investment in research and development, infrastructure construction, and expanding market size. Among all kinds of new energy batteries, lithium-ion batteries are widely used in many industries and fields including new energy vehicles due to their exce...

AI Technical Summary

Problems solved by technology

[0008] First, manual identification and labeling are greatly affected by subjective factors. Different identification and labeling personnel and identification scales will affect the identification results, which will interfere with the identification and classification of volume diving turning points

[0009] Second, relying on manual discrimination methods requires a lot of labor and time costs, and cannot be operated in batches, which affects the labeling efficiency of samples

[0010] The third is that the offline judgment cannot provide timely warning and treatment for the battery that has capacity diving, thus missing the best replacement opportunity. In severe cases, it may even happen that the lithium battery has thermal runaway before it can be judged in time.

During the use of the battery, because there is no real-time detection mechanism, once the capacity diving point occurs, the early warning cannot be given in time, and the battery will continue to be used until the battery completely fails or fails

This will not only reduce the cascade utilization value of the battery, but even cause serious failure of the battery, resulting in large economic losses

Images