为了解决插电式混合动力汽车单一电池低比功率、无法响应暂态功率需求的问题,设计了电池和超级电容并联式复合储能系统。同时针对采用动态规划法优化负载电流分配时缺乏实时性的问题,利用不同驱动工况下动态规划优化的结果构成训练集进行训练,并综合GRU网络以及XGBoost算法,提出了一种Stacking集成学习框架下多模型融合的能量分配策略。仿真结果表明,与仅使用单一电池的储能系统相比,基于Stacking融合模型的实时能量分配系统在UDDS和US06两种循环工况下,电池峰值电流分别降低了48.7%和50.8%,有效削弱了电池的峰值电流,提升了电池的整体性能。
Abstract
In order to solve the problem of low specific power of the single-power battery that unable to respond to transient power demand in plug-in hybrid electric vehicle, a hybrid energy storage system with parallel connection between battery and supercapacitor was designed. To the problem of lack real time when using dynamic programming (DP) method to optimize load current distribution, a training set composed of DP optimization results under different driving conditions data sets was used for training, and a multi-model fusion energy distribute strategy under Stacking integrated learning framework was proposed by integrating GRU network and XGBoost algorithm. The simulation results show that compared with the energy storage system using only a single battery, the real-time energy distribution system based on Stacking fusion model can reduce the peak current by 48.7% and 50.8% under UDDS and US06 cycles, respectively, effectively reduces the peak current of the battery and improves the overall performance of the battery.
关键词
电学计量 /
复合储能系统 /
插电式混合动力汽车 /
动态规划 /
XGBoost /
Stacking融合模型
Key words
electrical measurement /
hybrid energy storage systems /
plug-in hybrid electric vehicle /
dynamic programming /
XGBoost /
Stacking fusion model
{{custom_sec.title}}
{{custom_sec.title}}
{{custom_sec.content}}
参考文献
［1］吴忠强, 胡晓宇, 马博岩, 等. 基于RFF及GWO-PF的锂电池SOC估计［J］. 计量学报, 2022, 43(9): 1200-1207.
WU Z Q, HU X Y, MA B Y, et al. SOC estimation of lithium batteries based on RFF and GWO-PF ［J］. Acta Metrologica Sinica, 2022, 43(9): 1200-1207.
［2］吴忠强, 王国勇, 谢宗奎, 等. 基于WOA-UKF算法的锂电池容量与SOC联合估计［J］. 计量学报, 2022, 43(5): 649-656.
WU Z Q, WANG G Y, XIE Z K, et al. Joint Estimation of the capacity and SOC of lithium battery based on WOA-UKF Algorithm ［J］. Acta Metrologica Sinica, 2022, 43(5): 649-656.
［3］陈燎, 孙登辉, 盘朝奉. 串联式复合电源再生制动系统恒流控制［J］. 中国公路学报, 2019, 32(3): 155-162.
CHEN L, SUN D F, PAN C F. Constant current control of regenerative braking system of tandem-type compound power supply［J］. China Journal of Highway and Transport, 2019, 32(3): 155-162.
［4］陈庆樟, 王正义, 王康, 等. 纯电动车复合电源功率逻辑门限控制策略研究［J］. 重庆交通大学学报(自然科学版), 2019, 38(11): 133-138.
CHEN Q Z, WANG Z Y, WANG K, et al. Power logic threshold control strategy of compound power system for pure electric vehicle［J］. Journal of Chongqing Jiaotong University (Natural Science), 2019, 38(11): 133-138.
［5］DUSMEZ S, KHALIGH A. A supervisory power-splitting approach for a new ultracapacitor-battery vehicle deploying two propulsion machines［J］. IEEE Transactions on Industrial Informatics, 2014, 10(3): 1960-1971.
［6］邓涛, 余浩源, 徐彬. 基于DP算法的复合电源混合动力系统控制优化［J］. 系统仿真学报, 2019, 31(9): 1860-1867.
DENG T, YU H Y, XU B. Control optimization of hybrid system with hybrid power based on DP algorithm［J］. Journal of System Simulation, 2019, 31(9): 1860-1867.
［7］IBRAHIM M, JEMEI S, WIMMER G, et al. Nonlinear autoregressive neural network in an energy management strategy for battery/ultra-capacitor hybrid electrical vehicles［J］. Electric Power Systems Research, 2016, 136: 262-269.
［8］CAO J Y, XIONG R. Reinforcement learning-based real-time energy management for plug-in hybrid electric vehicle with hybrid energy storage system［J］. Energy Procedia, 2017, 142: 1896-1901.
［9］张俊超, 孟丽囡, 孙福明, 等. 基于超级电容器和蓄电池的复合电源研究［J］. 电源技术, 2018, 42(11): 1726-1728.
ZHANG J C, MENG L N, SUN F M, et al. Research on composite power supply based on super capacitor and storage battery［J］. Chinese Journal of Power Sources, 2018, 42(11): 1726-1728.
［10］ZHANG Q, WANG L J, LI G, et al. A real-time energy management control strategy for battery and supercapacitor hybrid energy storage systems of pure electric vehicles［J］. Journal of Energy Storage, 2020, 31: 101721.
［11］CHEN T, GUESTRIN C. XGBoost: A scalable tree boosting system［C］//ACM SIGKDD International Conference on Knowledge Discovery and Data Mining. San Francisco, USA: ACM, 2016: 785-794.
［12］史佳琪, 张建华. 基于多模型融合Stacking集成学习方式的负荷预测方法［J］. 中国电机工程学报, 2019, 39(14): 4032-4042.
SHI J Q, ZHANG J H. Load forecasting based on multi-model by stacking ensemble learning［J］. Proceedings of the CSEE, 2019, 39(14): 4032-4042.
［13］魏书荣, 张鑫, 符杨, 等. 基于GRA-LSTM-Stacking模型的海上双馈风力发电机早期故障预警与诊断［J］. 中国电机工程学报, 2021, 41(7): 2373-2383.
WEI S R, ZHANG X, FU Y, et al. Early fault warning and diagnosis of offshore wind DFIG based on GRA-LSTM-stacking model［J］. Proceedings of the CSEE. 2021, 41(7): 2373-2383.
［14］陈振宇, 刘金波, 李晨, 等. 基于LSTM与XGBoost组合模型的超短期电力负荷预测［J］. 电网技术, 2020, 44(2): 614-620.
CHEN Z Y, LIU J B, LI C, et al. Ultra-Short-term power load forecasting based on combined LSTM-XGBoost model［J］. Power System Technology, 2020, 44(2): 614-620.
［15］HORNG G J, LIN T C, LEE K C, et al. Prediction of prognosis in emergency trauma patients with optimal limit gradient based on grid search optimal parameters［J］. Wireless Personal Communications, 2021, 120(2): 1741-1751.
基金
河北省自然科学基金(F2020203014)
PDF(865 KB)
