Lithium ion battery RUL prediction method based on HI and ANN

Abstract

The invention discloses a lithium ion battery RUL prediction method based on HI and ANN, and the method comprises the steps: firstly searching all measured voltages, currents, temperatures and the like in a charging and discharging process, and proposing different feature extraction methods according to different characteristics of data to obtain HI related to the capacity. For abnormal values possibly appearing in the extracted HI, a common average value substitution method and a normalization substitution method are adopted according to the positions of the abnormal values; then, based on the corrected Pearson correlation coefficient between each HI and the capacity, optimal feature selection is carried out, and the HI with the maximum value is selected as the optimal HI; and finally, a neural network is constructed from three aspects of shape features, time dependence features and sequence transformation features of the time sequence HI, so that prediction of the RUL is achieved. The extraction method used in the invention is relatively simple; the subsequent network training and prediction cost is reduced; and the interference of noise on the sequence is reduced, and the prediction precision is improved.

Description

technical field [0001] The invention relates to a lithium-ion battery RUL (remaining service life) prediction method based on HI (health index) and ANN (artificial neural network), belonging to the technical field of lithium-ion battery health management. Background technique [0002] Mobile phones, computers, cars, electric toothbrushes, remote controls, airplanes and other tools can be seen everywhere in people's daily life. Because these tools use batteries as energy sources, batteries have become an indispensable and important part. Lithium-ion batteries have become the representative of modern high-performance and high-energy batteries due to their unique advantages, such as small size, high energy density, wide operating temperature, fast charging rate, safety and environmental protection, and long cycle life. In August 2013, during the test drive of the Model S series electric vehicles launched by Tesla, a Model S90D battery spontaneously ignited, causing the vehicle ...

AI Technical Summary

Problems solved by technology

In August 2013, during the test drive of the Model S series electric vehicles launched by Tesla, a Model S90D battery spontaneously ignited, causing the vehicle to completely burn down.

[0006] Analyzing the above literature, it is not difficult to find that there are some problems in the existing methods: (1) The type of feature extraction is single

The existing literature only extracts a kind of HI, such as equal pressure drop discharge time or entropy value, etc., and directly predicts the capacity or RUL, and does not analyze that there are many factors that affect battery degradation, and there may be other factors. A better HI will better characterize battery degradation

(2) The feature extraction process is complex

(3) The cost of model training and prediction is high

Although some literatures fully consider the factors affecting battery performance degradation such as voltage, current, and temperature, and extract multiple HIs, it is easy to waste a lot of time if many HIs are directly sent to the neural network or other algorithms. Operating costs

Although some literatures take the above problems into consideration, and use the dimensionality reduction method to reduce the dimensionality of HIs to a certain extent before training and predicting, the final input data of the neural network is 15 dimensions, and the number of dimensions is still very high.

If it is used in the long-term RUL prediction of the battery, it will inevitably take a lot of time

Images