Method for predicting SOH based on HS-MH-MoE model and current, voltage and temperature of battery

Through the multi-layer multi-head sparse hybrid expert model combined with CNN and LSTM, the problem of limited generalization ability of traditional models in battery SOH prediction is solved, improving prediction accuracy and robustness, and achieving more accurate battery health status prediction.

CN119247145APending Publication Date: 2025-01-03NANTONG LE CHUANGXIN ENERGY CO LTD
View PDF 0 Cites 2 Cited by

Patent Information

Application Number
CN202411280086.8
Authority / Receiving Office
CN · China
Patent Type
Applications(China)
Current Assignee / Owner
Filing Date
2024-09-12
Publication Date
2025-01-03

AI Technical Summary

Technical Problem

Traditional machine learning models are difficult to effectively predict battery health status (SOH) when processing complex and heterogeneous battery data. Due to the limited generalization ability of a single model and the ease of overfitting, it leads to low prediction accuracy and efficiency.

Method used

Using multi-layer multi-head sparse hybrid expert model (HS-MH-MoE), combining convolutional neural network (CNN) and long and short-term memory network (LSTM), a more powerful model is built through multi-layer structure and multi-head mechanism. Prediction of battery current, voltage and temperature data.

Benefits of technology

Improve the expression ability and prediction accuracy of the model, reduce the risk of overfitting, improve robustness and generalization ability, better capture the multi-level characteristics and nonlinear relationships of battery data, and enhance the prediction accuracy of battery SOH .

✦ Generated by Eureka AI based on patent content.

Smart Images

  • Figure CN119247145A_ABST
    Figure CN119247145A_ABST
Patent Text Reader

Abstract

The invention discloses a method for predicting SOH based on an HS-MH-MoE model and current, voltage and temperature of a battery. The method comprises the following steps: S1, testing and acquiring current, voltage, temperature and capacity data of the battery; s2, constructing an HS-MH-MoE model, wherein the HS-MH-MoE model comprises a multi-layer multi-head sparse hybrid expert sub-model A two-layer structure is used, each layer comprises three expert sub-models, and each sub-model is a CNN-LSTM model; the CNN automatically learns the spatial correlation of input data, and extracts high-level abstract features; and S3, training and verifying the model. S4, predicting the SOH of the battery: deploying and predicting the model after training; and connecting the three SOH predicted values to a linear regression layer, and outputting a final value. The SOH is predicted based on the CNN-LSTM hybrid expert model HS-MH-MoE and the battery data, the expression ability and prediction precision of the model are improved, the robustness and generalization ability of the model are improved, and the over-fitting risk is reduced.
Need to check novelty before this filing date? Find Prior Art

Citation Information

Cited By

  • Method and system for indirectly predicting state of health of battery based on expansion stress

    CN119936686A

  • Dynamic parameter identification method and device for energy storage BMS

    CN120781046A