| 引用本文: | 陆 鹏,付 华,卢万杰,张慧峰,郑翔宇.基于HCOAG算法优化KELM的全钒液流电池SOC估计[J].电力系统保护与控制,2023,51(7):135-145.[点击复制] |
| LU Peng,FU Hua,LU Wanjie,ZHANG Huifeng,ZHENG Xiangyu.State of charge estimation for a vanadium redox flow battery based on a kernel extreme learningmachine optimized by an improved coyote and grey wolf algorithm[J].Power System Protection and Control,2023,51(7):135-145[点击复制] |
|
| 摘要: |
| 针对直流微电网储能系统中全钒液流电池SOC难以精确估计的问题，提出一种基于郊狼算法(coyote optimization algorithm, COA)与灰狼算法(grey wolf optimization, GWO)的混合算法(hybrid COA with gwo, HCOAG)优化核极限学习机(kernel extreme learning machine, KELM)的全钒液流电池SOC估计方法。首先将改进的郊狼算法(improved COA, ICOA)与简化操作的灰狼算法(simplified GWO, SGWO)采用正弦交叉策略融合组成HCOAG算法，利用HCOAG算法对KELM模型的参数进行寻优。然后利用基准函数对HCOAG算法进行测试，并与其他智能算法对比寻优能力。最后通过CEC-VRB-5 kW型号电池进行仿真和实验，验证了该估计方法的准确性与可行性。结果表明，所提HCOAG-KELM方法估计精度优于GWO-KELM、ICOA-KELM、KELM、扩展卡尔曼滤波(extended kalman filter, EKF)和无迹卡尔曼滤波(unscented kalman filter, UKF)算法模型，同时估计误差在2%之内，满足实际需求。 |
| 关键词: 灰狼算法 郊狼算法 核极限学习机 全钒液流电池 荷电状态 |
| DOI：10.19783/j.cnki.pspc.221050 |
| 投稿时间：2022-07-05修订日期：2022-10-07 |
| 基金项目:国家自然科学基金项目资助(51974151)；辽宁省高等学校创新团队项目资助(lt2019007)；辽宁省重点实验室项目资助(ljzs003) |
|
| State of charge estimation for a vanadium redox flow battery based on a kernel extreme learningmachine optimized by an improved coyote and grey wolf algorithm |
| LU Peng1,FU Hua1,LU Wanjie2,ZHANG Huifeng3,ZHENG Xiangyu4 |
| (1.Faculty of Electrical and Control Engineering, Liaoning Technical University, Huludao 125105, China;
2. School of Mechanical Engineering, Liaoning Technical University, Fuxin 123000, China;
3. Shuozhou Power Supply Company of State Grid Shanxi Electric Power Co., Ltd., Shuozhou 036000, China;
4. Guizhou Collect Energy Century Co., Ltd., Qiandongnan 557400, China) |
| Abstract: |
| It is difficult to accurately estimate the state of charge (SOC) of a vanadium redox flow battery in a DC microgrid energy storage system. Thus an SOC estimation method based on hybrid coyote optimization with grey wolf optimization algorithms (HCOAG) to optimize a kernel extreme learning machine (KELM) model is proposed. First, the improved COA (ICOA) and simplified GWO (SGWO) algorithm are fused by a sinusoidal crossing strategy to form an HCOAG algorithm. This is used to optimize the parameters of the KELM model. Then, a benchmark function is used to test the HCOAG algorithm, and the optimization ability of the HCOAG algorithm is compared with other intelligent algorithms. Finally, the accuracy and feasibility of the estimation method are verified by simulation and experiment on a CEC-VRB-5?kW battery. The results show that the estimation accuracy of the proposed HCOAG-KELM method is better than that of the GWO-KELM, ICOA-KELM, KELM, unscented Kalman filter (UKF) and extended Kalman filter (EKF) algorithm models, and the SOC estimation error is within 2%, which can meet actual demand. |
| Key words: grey wolf algorithm coyote algorithm kernel extreme learning machine vanadium redox flow battery state of charge |
