基于改進高斯過程回歸的變電站直流蓄電池SOH估算
丁芃，謝昊含，司威，楊茹楠，劉明陽
(國網天津市電力公司濱海供電分公司，天津 300450)
摘 要 ：為了準確估算變電站直流蓄電池的健康狀態(SOH)，輔助直流系統的運行決策，提出了一種基于改進高斯過程回歸的蓄電池SOH估算方法，通過建立變電站蓄電池組在實際不同運行工況下的蓄電池健康特征指標(HF)，對高斯過程回歸算法進行適應性改進，將變電站蓄電池實際歷史運行數據與離線測試數據按比例混合制作訓練集，實現變電站蓄電池HF與SOH之間的映射關系。實驗結果表明，該方法針對于變電站這一特殊場景下的蓄電池具有良好的估算效果，可為直流系統運行維護提供理論依據。
關鍵詞 ： 變電站 ；直流蓄電池 ；蓄電池健康狀態 ；蓄電池運行工況 ；高斯過程回歸 ；訓練集
中圖分類號 ：TM63 ；TM912 文獻標識碼 ：A 文章編號 ：1007-3175(2025)11-0014-07
SOH Estimation for DC Batteries in Substations Based on Improved Gaussian Process Regression
DING Peng, XIE Hao-han, SI Wei, YANG Ru-nan, LIU Ming-yang
（State Grid Tianjin Electric Power Company Binhai Power Supply Branch, Tianjin 300450, China）
Abstract: In order to accurately estimate the state of health (SOH) of DC batteries in substations and assist in the operation decision-making of DC systems, this paper proposes a battery SOH estimation method based on improved Gaussian process regression. By establishing the health of feature (HF) of battery packs in substations under different operating conditions, the Gaussian process regression algorithm is adaptively improved. The actual historical operating data of substation batteries is mixed with offline test data in proportion to create a training set, achieving the mapping relationship between HF and SOH of substation batteries. The experimental results show that this method has good estimation effect on batteries in this special scenario of substations and can provide theoretical basis for the operation and maintenance of DC systems.
Key words: substation; DC battery; state of health of battery; operating condition of battery; Gaussian process regression; training set
參考文獻
[1] 孫冬，許爽 . 梯次利用鋰電池健康狀態預測 [J]. 電工 技術學報，2018，33(9)：2121-2129.
[2] GONG Qingrui, WANG Ping, CHENG Ze.An encoderdecoder model based on deep learning for state of health estimation of lithium-ion battery[J].Journal of Energy Storage，2022，46：103804．
[3] TIAN Jinpeng, XIONG Rui, SHEN Weixiang, et al. State-of-charge estimation of LiFePO4 batteries in electric vehicles:A deep-learning enabled approach[J].Applied Energy，2021，291：116812.
[4] HAN Xuebing, OUYANG Minggao, LU Languang, et al. Simplification of physics-based electrochemical model for lithium ion battery on electric vehicle. Part Ⅱ :Pseudo-twodimensional model simplification and state of charge estimation[J].Journal of Power Sources， 2015，278 ：814-825.
[5] PLETT G L.Extended Kalman filtering for battery management systems of LiPB-based HEV battery packs: Part3. State and parameter estimation[J]. Journal of Power Sources，2004，134(2)：277-292.
[6] WANG Yujie, ZHANG Chenbin, CHEN Zonghai.A method for state-of-charge estimation of LiFePO4 batteries at dynamic currents and temperatures using particle filter[J].Journal of Power Sources，2015，279：306-311.
[7] CHANG Chun, WANG Qiyue, JIANG Jiuchun, et al. Lithium-ion battery state of health estimation using the incremental capacity and wavelet neural networks with genetic algorithm[J]. Journal of Energy Storage，2021，38：102570.
[8] LIU Datong, ZHOU Jianbao, LIAO Haitao, et al.A health indicator extraction and optimization framework for lithium-ion battery degradation modeling and prognostics[J].IEEE Transactions on Systems, Man, and Cybernetics:Systems，2015， 45(6)：915-928.
[9] TIAN Jinpeng, XIONG Rui, SHEN Weixiang.Stateof-health estimation based on differential temperature for lithium ion batteries[J]. IEEE Transactions on Power Electronics，2020， 35(10)：10363-10373. [10] ZHANG Li, LI Kang, DU Dajun, et al.A sparse least squares support vector machine used for SOC estimation of Li-ion Batteries[J].IFACPapersOnLine，2019，52(11)：256-261.
[11] LI Xiaoyu, YUAN Changgui, WANG Zhenpo.Multitime-scale framework for prognostic health condition of lithium battery using modified Gaussian process regression and nonlinear regression[J].Journal of Power Sources，2020， 467：228358.
[12] GOEBEL K, SAHA B, SAXENA A, et al.Prognostics in battery health management[J].IEEE Instrumentation & Measurement Magazine，2008，11(4)：33-40.
[13] HE Jianghe, WEI Zhongbao, BIAN Xiaolei, et al. State-of-health estimation of lithium-ion batteries using incremental capacity analysis based on voltage-capacity model[J].IEEE Transactions on Transportation Electrification， 2020，6(2)：417-426.
[14] XUE Jiankai, SHEN Bo.A novel swarm intelligence optimization approach: Sparrow search algorithm[J]. Systems Science & Control Engineering an Open Access Journal，2020，8(1)：22-34.
[15] CHUNG J, GULCEHRE C, CHO K H, et al.Empirical evaluation of gated recurrent neural networks on sequence modeling[J/OL].(2014-12-11)[2025- 08-14].https//arxiv.org/abs/1412.3555.
