Lithium ion battery state-of-charge dynamic assessment and long-acting prediction fusion method

Abstract

The present invention discloses a lithium ion battery state-of-charge dynamic assessment and long-acting prediction fusion method. The method comprises the steps of: employing the expanded Kalman filter method to perform assessment of the lithium ion battery state of charge to obtain a lithium ion battery state of charge SOCKEF; employing an echo state neural network to perform prediction of the lithium ion battery state of charge to obtain a lithium ion battery state of charge SOCESN; and finally performing weighing fusion of the lithium ion battery state of charge SOCKEF and the lithium ionbattery state of charge SOCESN to obtain a final lithium ion battery state of charge SOC. The lithium ion battery state-of-charge dynamic assessment and long-acting prediction fusion method improves the adaptation and the assessment precision of a current battery SOC detection method to overcome the restriction of SOC dynamic assessment of a single method, specifically selects a fusion method based on model and data drive and takes the consideration of SOC detection assessment dynamic timeliness and long-term long-acting prediction demands.

Description

technical field [0001] The invention relates to the technical field of battery state-of-charge evaluation, in particular to a fusion method for dynamic evaluation and long-term prediction of state-of-charge of lithium-ion batteries. Background technique [0002] The power battery is a key component of new energy vehicles, and its health status and management level are related to the efficiency and safe operation of the vehicle. The detection and estimation of battery state of charge (SOC) is the basis of battery thermal management, balance management and safety and reliability management. Accurate SOC estimation can balance the difference between single cells, optimize charge and discharge strategies, prevent overheating and overcharge and overdischarge. Battery state estimation can make full and reasonable use of the battery, prolong the service life of the battery, and provide data basis for the energy management of the vehicle. Therefore, battery state estimation is of g...

AI Technical Summary

Problems solved by technology

[0004] The present invention aims at the problem that the existing battery SOC estimation method relies on fixed model parameters and cannot reproduce and adjust with the actual working conditions of the battery, thereby reducing the detection accuracy and adaptability of the battery state of charge, and provides a lithium-ion battery state of charge dynamic Evaluation and Long-term Prediction Fusion Method

Images