Lithium battery capacity integrated prediction method based on dynamic time-varying weight

Abstract

The invention discloses a lithium battery capacity integrated prediction method based on dynamic time-varying weight. The method comprises the following steps: dividing lithium battery degradation data into a training data set, a verification data set and a test data set; selecting a plurality of primitive algorithms, and training each primitive algorithm by utilizing the training data set; basedon each trained primitive algorithm prediction model, carrying out the prediction in the verification interval, and calculating a prediction relative error; calculating the prediction algorithm weightof each primitive according to the prediction relative error of the verification interval; performing complementary prediction on the prediction relative error in the test interval; calculating a prediction average value of the prediction relative error in the test interval as a time-varying weight induction factor; training each primitive prediction algorithm by using the training data set and the verification data set; employing the trained primitive algorithm for prediction in a test interval; realizing the real-time weight allocation on the basis of V-IOWA; multiplying and summing the prediction result of each primitive algorithm and the corresponding weight of each moment to obtain a final integrated prediction result.

Description

technical field [0001] The invention relates to the technical field of lithium battery capacity prediction, in particular to an integrated prediction method for lithium battery capacity based on dynamic time-varying weights. Background technique [0002] Lithium battery capacity, that is, the maximum amount of electricity that a lithium battery can store in its current performance state, is considered to be an important indicator of the performance of a lithium battery. Affected by various internal and external mechanisms such as ambient temperature, aging, and usage methods, the battery capacity gradually declines with the continuous use of lithium batteries. Therefore, accurate prediction of lithium battery capacity is very important for formulating reasonable lithium battery usage strategy and improving lithium battery life. [0003] Existing lithium battery capacity prediction methods can be divided into model-based methods and data-driven methods. Model-based methods ...

AI Technical Summary

Problems solved by technology

[0027] The technical problem solved by the present invention is that the current single lithium battery capacity prediction method has poor engineering applicability and low prediction accuracy

Images