关键词: 电池峰值功率状态, 麻雀优化算法, 极限学习机, 多约束条件

Abstract:

Accurate estimation of the peak power state [state of power (SOP)] for power batteries is essential for ensuring safe operation and extending the driving range of new energy vehicles. To address the insufficient accuracy of existing SOP estimation methods, this study proposes a joint estimation model—multi-constraint conditions (MCC)-sparrow search algorithm (SSA)-extreme learning machine (ELM)—which integrates MCC with an SSA-optimized ELM for error prediction and correction. Using a single lithium manganese oxide battery as the research subject, a second-order RC equivalent circuit model is established. Online parameter identification is performed with a forgetting factor-based recursive least squares method, and the battery's state of charge (SOC) is dynamically estimated using an adaptive extended Kalman filter algorithm. Furthermore, three-level operational conditions—30 s, 2 min, and 5 min—are defined based on discharge durations to simulate real-world scenarios. A preliminary SOP estimation model under varying durations is developed by comprehensively considering constraints such as SOC, voltage, and maximum allowable discharge current. Subsequently, absolute error datasets between estimated and measured SOP values under MCC are used to train ELM and SSA-ELM error prediction models, enabling dynamic compensation and correction of preliminary estimates. Experimental results demonstrate that the proposed MCC-SSA-ELM model markedly improves SOP estimation accuracy. Compared to the MCC and MCC-ELM models, the average relative errors of the MCC-SSA-ELM model under 30 s, 2 min, and 5 min durations are reduced by 0.382%, 6.215%, and 6.858%, respectively, with final errors consistently controlled within 0.15%. These results demonstrate the effectiveness and engineering applicability of the proposed method.

Key words: SOP, sparrow search algorithm, extreme learning machine, multi-constraint conditions