结合区间负荷预测与无模型预测控制的氢能船舶能量管理策略

doi:10.19595/j.cnki.1000-6753.tces.260288

摘要
图/表
参考文献
相关文章 (11)

全文: PDF (2311 KB)
输出: BibTeX | EndNote (RIS)

摘要

合理的能量管理策略可有效提高氢能船舶运行的综合效益,降低经济成本。本文提出了一个结合区间负荷预测(interval load forecasting, ILF)与无模型预测控制(model-free predictive control, MFPC)的氢能船舶能量管理策略(energy management strategy, EMS),即ILF-MFPC。首先提出了一个考虑负荷趋势的自适应指数平滑模型用于氢能船舶ILF,可有效应对系统运行状态数据与航道水位气象数据的非线性特征学习。随后,将模型给出的ILF上下限序列作为MFPC的扰动输入向量,协同控制输入向量与输出向量共同构造汉克尔优化矩阵,进行氢能船舶能量分配的滚动优化计算。最后将所提出的ILF-MFPC策略用于一艘实际的氢动力船舶负荷的能量管理。算例结果表明,ILF-MFPC比案例船舶原本的功率追随策略综合成本降低接近15%,并且优于多个先进的优化方法,与理论的全局最优仅相差3%左右。

	服务

	把本文推荐给朋友
	加入我的书架
	加入引用管理器
	E-mail Alert
	RSS
	作者相关文章
	刘星斗
	邹亮
	贾荣照
	马良旺
	王亚伟

关键词 ：能量管理策略, 区间负荷预测, 无模型预测控制, 自适应指数平滑法, 氢能船舶

Abstract：

Hydrogen-powered vessels represent a promising zero-emission solution for maritime decarbonization. However, their power system operation is significantly challenged by uncertain and fluctuating loads, which hinder the stable and optimal energy management required for efficiency and reliability.
This paper presents an energy management strategy (EMS) combining interval load forecasting (ILF) and model-free predictive control (MFPC), namely ILF-MFPC, for hydrogen-powered vessels. First, an adaptive exponential smoothing model (AESM) is developed for hydrogen-powered vessel ILF, which effectively handles the nonlinear features of system operation data, water level, and meteorological data. The upper and lower bounds of the obtained ILF are then taken as disturbance input sequences, which are jointly used with control input and output vectors to construct the Hankel optimization matrix for the rolling optimization calculation of energy allocation.
Subsequently, the proposed ILF-MFPC strategy is applied to a real hydrogen-powered ship. The comprehensive cost of the ship is reduced by nearly 15% compared with the power-following strategy, and it outperforms several advanced optimization methods, with only about 3% difference from the theoretical global optimum.
The proposed strategy is validated under different working conditions. Compared with rule-based methods, the ILF-MFPC strategy effectively reduces hydrogen consumption and battery degradation. Specifically, under low-fluctuation conditions, the equivalent hydrogen consumption and fuel cell degradation costs are significantly lower than those of other strategies. Under high-fluctuation conditions, it still maintains optimal performance. The influence of the confidence interval and weight parameter on the performance of the proposed strategy is further analyzed. The results show that a reasonable confidence interval and weight parameter can balance hydrogen consumption and battery degradation, achieving optimal comprehensive cost.
The proposed ILF-MFPC strategy has good real-time performance and engineering practicability, providing a new solution for energy management of hydrogen-powered vessels.

Key words： Energy management strategy Interval load forecasting Model-free predictive control Adaptive exponential smoothing method Hydrogen powered vessels

收稿日期: 2026-02-27

PACS:

TK91

基金资助:

国家重点研发计划资助项目（2022YFB4300703）

通讯作者: 邹亮男,1983年生,教授,博士生导师,研究方向为新能源发电与智能微电网、先进电工理论与装备等。E-mail：zouliang@sdu.edu.cn

作者简介: 刘星斗男,1996年生,博士研究生,研究方向为低/零碳船舶电力系统负荷预测与能量管理。E-mail：202320713@mail.sdu.edu.cn

引用本文:

刘星斗, 邹亮, 贾荣照, 马良旺, 王亚伟. 结合区间负荷预测与无模型预测控制的氢能船舶能量管理策略[J]. 电工技术学报, 0, (): 288-. Liu Xingdou, Zou Liang, Jia Rongzhao, Ma Liangwang, Wang Yawei. Hydrogen Ship Energy Management Strategy Combining Interval Load Forecasting and Model Free Predictive Control. Transactions of China Electrotechnical Society, 0, (): 288-.

链接本文:

https://dgjsxb.ces-transaction.com/CN/10.19595/j.cnki.1000-6753.tces.260288 https://dgjsxb.ces-transaction.com/CN/Y0/V/I/288

[1] International Hydrogen Council.Global Hydrogen Guide report[R].International Hydrogen Council, 2025.
[2] 蒙军,任洲洋,王皓.氢能交互下的多区域电氢综合能源系统可靠性提升策略[J].电工技术学报,2024, 39(16): 5011-5027.
MENG Jun, REN Zhouyang, WANG Hao.Reliability Improvement Strategy for Multi-Regional Electro-Hydrogen Integrated Energy Systems Under Hydrogen-Energy Interaction[J].Transactions of China Electrotechnical Society, 2024, 39(16): 5011-5027.
[3] 肖能齐,徐翔,周瑞平.船舶柴电混合动力系统能量管理控制策略[J].哈尔滨工程大学学报,2020, 41(1): 153-160.
XIAO Nengqi, XU Xiang, ZHOU Ruiping.Energy management and control strategy of ship diesel-electric hybrid power system[J].Journal of Harbin Engineering University, 2020, 41(1): 153-160.
[4] XIAO F,LI C,FAN Y,YANG G,TANG X.State of charge estimation for lithium-ion battery based on Gaussian process regression with deep recurrent kernel[J].International Journal of Electrical Power & Energy Systems,2021,124:106369.
[5] LEE N,JEONG G,AHN H.Improvement of fuel economy using fuzzy logic-based power distribution control strategy for a FCHEV[C].International Conference on Computational Intelligence and Security,2006:891-894.
[6] 薛琼,马洋洋,裴冯来.氢燃料电池汽车动力系统建模与能量管理策略[J].汽车与新动力,2025, 8(5): 26-33.
XUE Qiong, MA Yangyang, PEI Fenglai.Modeling and energy management strategy of hydrogen fuel cell vehicle powertrain[J].Automobile and New Powertrain, 2025, 8(5): 26-33.
[7] SONG T,FU L,ZHONG L,FAN Y,SHANG Q.HP3O algorithm-based all electric ship energy management strategy integrating demand-side adjustment[J].Energy,2024,295:130968.
[8] 陈杰,陆宇鑫,王雪钰,等.燃料电池/ 锂电池混合供电系统的分散式鲁棒滑模复合控制[J].中国电机工程学报,2025, 45(7): 2447-2460.
CHEN Jie, LU Yuxin, WANG Xueyu, et al.Decentralized Robust Sliding Mode Composite Control for the Fuel Cell/Lithium Battery Hybrid Power Supply System[J].Proceedings of the CSEE, 2025, 45(7): 2447-2460.
[9] 丁琦欣,赵波,陈哲,等.基于多时间尺度特征提取的微网电氢混合储能协同优化配置[J].中国电机工程学报,2024, https://link.cnki.net/urlid/11.2107.TM.20241114.2052.025.
DING Qixin, ZHAO Bo, CHEN Zhe, et al.Collaborative Configuration Optimization of Microgrid Electric-Hydrogen Hybrid Energy Storage Based on Multi-Time Scale Feature Extraction[J].Proceedings of the CSEE, 2024, https://link.cnki.net/urlid/11.2107.TM.20241114.2052.025.
[10] ZHU J Y, CHEN L, WANG X F, YU L.Bi-level optimal sizing and energy management of hybrid electric propulsion systems[J].Applied Energy, 2020, 260: 114134.
[11] 全睿,刘大志,管鑫,章国光,全琎.融合动态规划与模型预测控制的燃料电池无人机能量管理策略[J/OL].电工技术学报,2026, https://doi.org/10.19595/j.cnki.1000-6753.tces.251126.
QUAN Rui, LIU Dazhi, GUAN Xin, ZHANG Guoguang, QUAN Jin. Energy Management Strategy for Fuel Cell UAVs Integrating Dynamic Programming and Model Predictive Control[J/OL].Transactions of China Electrotechnical Society, 2026, https://doi.org/10.19595/j.cnki.1000-6753.tces.251126.
[12] SI Yupeng, WANG Rongjie, ZHANG Shiqi, et al.Configuration optimization and energy management of hybrid energy system for marine using quantum computing[J].Energy, 2022, 253: 124131.
[13] KANELLOS F D.Optimal Power Management With GHG Emissions Limitation in All-Electric Ship Power Systems Comprising Energy Storage Systems[J].IEEE Transactions on Power Systems, 2014, 29(1): 330-339.
[14] LIANG X, WANG P, ZHANG X T, et al.Multi-objective robust energy management for environment powered unmanned surface vehicles[J].Ocean Engineering, 2022, 247: 110624.
[15] FU Z, LI Z, SI P, et al.A Hierarchical Energy Management Strategy for Fuel Cell/Battery/ Supercapacitor Hybrid Electric Vehicles[J].International Journal of Hydrogen Energy, 2019, 44(39): 22146-22159.
[16] Gao Huizhong, Wang Zhijie, Yin Shaoping, et al.Adaptive real-time optimal energy management strategy based on equivalent factors optimization for hybrid fuel cell system[J].International Journal of Hydrogen Energy, 2021, 46: 4329-4338.
[17] ZHANG Y, XUE Q, GAO D, et al.Two-level model predictive control energy management strategy for hybrid power ships with hybrid energy storage system[J].Journal of Energy Storage, 2022, 52.
[18] 吴俊杰,胡可.基于人工神经网络 - 模型预测控制的海上风储系统调频控制策略[J].电气技术,2025, 26(12):24-28.
WU Junjie, HU Ke.Frequency Control Strategy for Offshore Wind-Storage Systems Based on Artificial Neural Network-Model Predictive Control[J].Electrical Engineering, 2025, 26(12): 24-28.
[19] 柯水清,杨祥国,李昕,等.基于MPC-HHO 的船载复合储能系统规划与运行策略协同优化方法[J].中国舰船研究,2025, 20(4): 233-245.
KE Shuiqing, YANG Xiangguo, LI Xin, et al.Collaborative optimization for planning and operation strategy of shipboard hybrid energy storage systems based on MPC-HHO[J].Chinese Journal of Ship Research, 2025, 20(4): 233-245.
[20] 梁天驰,袁裕鹏,童亮.基于支持向量机与模型预测控制的混合动力船舶能量管理策略[J].交通信息与安全,2024, 42(4): 125-135.
LIANG Tianchi, YUAN Yupeng, TONG Liang.Energy Management Strategy for Hybrid Power Ships Based on Support Vector Machine and Model Predictive Control[J].Journal of Transportation Information and Safety, 2024, 42(4): 125-135.
[21] 刘璐,李奇,尹良震,等.基于PFDL 的阴极开放式 PEMFC 系统无模型自适应预测控制[J].中国电机工程学报,2019, 39(16): 4827-4837.
LIU Lu, LI Qi, YIN Liangzhen, et al.Model-free Adaptive Predictive Control of Open-cathode PEMFC System Based on PFDL[J].Proceedings of the CSEE, 2019, 39(16): 4827-4837.
[22] LIU Xingdou, ZOU Liang, HAN Zhiyun, MA Liangwang, JIANG Jundao, WANG Yawei, WANG Rui.An energy management strategy for hydrogen-powered electric vessels based on data-enabled predictive control model combined with probabilistic load forecasting[J].Energy, 2026, 344: 140063.
[23] 魏尧,付俊荣,王高林,汪凤翔.基于陷波抗停滞的永磁同步电机无模型预测电流滑模控制[J].电工技术学报,2026, 41(2):475-486.
WEI Yao, FU Junrong, WANG Gaolin, WANG Fengxiang.Model-Free Predictive Current Sliding Mode Control for Permanent Magnet Synchronous Motors Based on Notch Filter Anti-Stalling[J].Transactions of China Electrotechnical Society, 2026, 41(2): 475-486.
[24] 韩国强,韩颖,贾政,朱惠敏,于东升.基于超局部模型的开关磁阻电机无模型预测电流控制方法[J].电工技术学报,2025, 40(18): 5931-5944.
HAN Guoqiang, HAN Ying, JIA Zheng, ZHU Huimin, YU Dongsheng.Model-Free Predictive Current Control Method for Switched Reluctance Motors Based on Ultra-Local Model[J].Transactions of China Electrotechnical Society, 2025, 40(18): 5931-5944.
[25] 芮涛,冯壮壮,胡存刚,孙晓磊,陆格野.基于自适应超局部的并网逆变器三矢量无模型预测电流控制策略[J].电工技术学报,2025, 40(19):6257-6265.
RUI Tao, FENG Zhuangzhuang, HU Cungang, SUN Xiaolei, LU Geye.Three-Vector Model-Free Predictive Current Control Strategy for Grid-Connected Inverters Based on Adaptive Ultra-Local Model[J].Transactions of China Electrotechnical Society, 2025, 40(19): 6257-6265.
[26] 刘星斗,邹亮,韩智云,马良旺,王睿.基于构造混合约束损失函数的 Informer-PINN 氢动力船舶超短期多步负荷预测框架[J/OL].电工技术学报,2026, https://doi.org/10.19595/j.cnki.1000-6753.tces.251906.
LIU Xingdou, ZOU Liang, HAN Zhiyun, MA Liangwang, WANG Rui. An Ultra-Short-Term Multi-Step Load Prediction Framework for Hydrogen-Powered Ships Based on Informer-PINN with Hybrid Constraint Loss Function[J/OL].Transactions of China Electrotechnical Society, 2026, https://doi.org/10.19595/j.cnki.1000-6753.tces.251906.
[27] 杨淇,陈景文,华志广,李祥隆,赵冬冬,兰天一,窦满峰.基于集成型极限学习机的氢燃料电池寿命预测[J].电工技术学报,2025, 40(3):964-974.
YANG Qi, CHEN Jingwen, HUA Zhiguang, LI Xianglong, ZHAO Dongdong, LAN Tianyi, DOU Manfeng.Lifetime Prediction of Hydrogen Fuel Cells Based on Ensemble Extreme Learning Machine[J].Transactions of China Electrotechnical Society, 2025, 40(3): 964-974.
[28] GIOVANNIELLO M A, Wu X Y.Hybrid lithium-ion battery and hydrogen energy storage systems for a wind-supplied microgrid[J].Applied Energy, 2023, 345: 121311.
[29] 李奇, 赵淑丹, 蒲雨辰, 等. 考虑电氢耦合的混合储能微电网容量配置优化[J].电工技术学报, 2021, 36(3): 486-495.
LI Qi, ZHAO Shudan, PU Yuchen, et al.Capacity configuration optimization of hybrid energy storage microgrid considering electricity-hydrogen coupling[J].Transactions of China Electrotechnical Society, 2021, 36(3): 486-495.
[30] 谈浩澜, 王天宏, 李奇, 等. 市域动车组多模块并联氢燃料电池/锂电池混合发电系统能量管理优化控制方法研究[J].电机与控制学报, 2025, 29(6).
TAN Haolan, WANG Tianhong, LI Qi, et al.Research on energy management optimization control method for multi-module parallel hydrogen fuel cell/lithium battery hybrid power generation system of urban EMU[J].Electric Machines & Control, 2025, 29(6).
[31] GUO X, LICHTENDAHL Jr K C, GRUSHKA Cockayne Y. Bayesian ensembles of exponentially smoothed life-cycle forecasts[J].Manufacturing & Service Operations Management, 2025, 27(1): 230-248.
[32] CHEN B, HE G, HU L, et al.Energy management of electric vehicles based on improved long short term memory network and data-enabled predictive control[J].Applied Energy, 2025, 384: 125456.
[33] José L.R.N. Cunha, Cláudio M.N.A. Pereira. A hybrid model based on STL with simple exponential smoothing and ARMA for wind forecast in a Brazilian nuclear power plant site[J].Nuclear Engineering and Design, 2024, 421: 113026.
[34] 方娜,陈浩,邓心,肖威.基于VMD-ARIMA-DBN 的短期电力负荷预测[J].电力系统及其自动化学报,2023, 35(6): 59-65.
FANG Na, CHEN Hao, DENG Xin, XIAO Wei.Short-term power load forecasting based on VMD-ARIMA-DBN[J].Proceedings of the CSU-EPSA, 2023, 35(6): 59-65.
[35] Flávio Araújo Lim-Apo, Fabricio Oliveira, Silvio Hamacher. Decision tree enhancer (DTE): Improving decision trees with optimization[J].Knowledge-Based Systems, 2026, 339: 115597.
[36] 高锋阳,苏红宇,查鹏堂,强雅昕,刘嘉.基于工况预测和动力源寿命衰减协同的燃料电池有轨电车能量管理策略[J].电工技术学报,2025, 40(13):4316-4329.
GAO Fengyang, SU Hongyu, ZHA Pengtang, QIANG Yaxin, LIU Jia.Energy Management Strategy for Fuel Cell Trams Based on Operating Condition Prediction and Power Source Life Degradation Synergy[J].Transactions of China Electrotechnical Society, 2025, 40(13): 4316-4329.
[37] HOU S Y, CHEN H, LIU X, CUI J H, ZHAO J, GAO J W.Hierarchical model predictive control for energy management and lifespan protection in fuel cell electric vehicles[J].Energy, 2025, 319: 134968.
[38] LIN X Y, HUANG H, XU X H, et al.Dynamic programming solutions extracted SOC-trajectory online learning generation algorithm based approximate global optimization control strategy for a fuel cell hybrid electric vehicle[J].Energy, 2024, 295: 130728.