燃料电池空气供应系统自适应神经网络滑模控制

doi:10.12068/j.issn.1005-3026.2022.09.008

东北大学学报（自然科学版） ›› 2022, Vol. 43 ›› Issue (9): 1270-1276.DOI: 10.12068/j.issn.1005-3026.2022.09.008

燃料电池空气供应系统自适应神经网络滑模控制

张春雷，李鹤，董茂林，张圣杰

(东北大学机械工程与自动化学院，辽宁沈阳110819)

发布日期:2022-09-16
通讯作者: 张春雷
作者简介:张春雷(1994-)，男，黑龙江佳木斯人，东北大学博士研究生；李鹤(1975-)，男，河南方城人，东北大学教授，博士生导师.
基金资助:
国家自然科学基金资助项目(51675091).

Adaptive Neural Network Sliding Mode Control for the Fuel Cell Air Supply System

ZHANG Chun-lei， LI He， DONG Mao-lin， ZHANG Sheng-jie

School of Mechanical Engineering & Automation， Northeastern University， Shenyang 110819， China.

Published:2022-09-16
Contact: LI He
About author:-
Supported by:
-

摘要/Abstract

摘要： 聚合物电解质膜燃料电池(polymer electrolyte membrane fuel cell， PEMFC)空气供应系统易受参数不确定性和外部干扰的负面影响，难以实现高精度数学建模和鲁棒控制.设计了一种自适应神经网络滑模控制器，用于将PEMFC空气供应系统过氧比调节至其最优参考值，以维持最大系统输出净功率并避免氧饥饿.利用径向基函数神经网络在线逼近系统的未建模动态，而无需对外部干扰与模型参数摄动的界的先验信息.由Lyapunov理论分别推导出神经网络权值和滑模增益的自适应律，以保证闭环系统稳定性.仿真结果表明，所设计的控制器不仅改善了过氧比控制的动态行为，还有效减弱了控制输入的大幅超调和抖振.

关键词: 聚合物电解质膜燃料电池；过氧比；径向基函数神经网络；滑模控制；自适应律

Abstract: The air supply system of polymer electrolyte membrane fuel cell(PEMFC) is vulnerable to the negative impact of parameter uncertainties and external disturbances， and it is difficult to achieve high-precision mathematical modeling and robust control. An adaptive neural network sliding mode controller is designed to adjust the oxygen excess ratio of PEMFC air supply system to its optimal reference value so as to maintain the maximum system output net power and avoid oxygen starvation. The radial basis function(RBF) neural network is employed to approximate the dynamics of the unmodeled system online without prior information of the boundary of external disturbances and model parameter perturbations. To ensure the stability of the closed-loop system， the adaptive laws of neural network weights and sliding mode gains are derived by Lyapunov theory. The numerical simulation results demonstrate that the designed controller not only improves the dynamic behavior of the oxygen excess ratio control， but also effectively alleviates the large overshoot and chattering of the control input.

Key words: polymer electrolyte membrane fuel cell(PEMFC); oxygen excess ratio; radial basis function(RBF)neural network; sliding mode control; adaptive law

中图分类号:

TP29

张春雷，李鹤，董茂林，张圣杰. 燃料电池空气供应系统自适应神经网络滑模控制[J]. 东北大学学报（自然科学版）, 2022, 43(9): 1270-1276.

ZHANG Chun-lei， LI He， DONG Mao-lin， ZHANG Sheng-jie. Adaptive Neural Network Sliding Mode Control for the Fuel Cell Air Supply System[J]. Journal of Northeastern University(Natural Science), 2022, 43(9): 1270-1276.

参考文献

[1]Abbaker A M O，Wang H，Tian Y.Adaptive integral type-terminal sliding mode control for PEMFC air supply system using time delay estimation algorithm［J］.Asian Journal of Control，2022，24(1):217-226.
[2]Deng H，Li Q，Cui Y，et al.Nonlinear controller design based on cascade adaptive sliding mode control for PEM fuel cell air supply systems［J］.International Journal of Hydrogen Energy，2019，44(35):19357-19369.
[3]Ou K，Wang Y X，Li Z Z，et al.Feed forward fuzzy-PID control for air flow regulation of PEM fuel cell system［J］.International Journal of Hydrogen Energy，2015，40(35):11686-11695.
[4]Pukrushpan J T，Stefanopoulou A G，Peng H.Control of fuel cell breathing［J］.IEEE Control Systems，2004，2(24):30-46.
[5]Talj R J，Ortega R，Astolfi A.Passivity and robust PI control of the air supply system of a PEM fuel cell model［J］.Automatica，2011，47(12):2554-2561.
[6]Abdullah M，Idres M.Constrained model predictive control of proton exchange membrane fuel cell［J］.Journal of Mechanical Science and Technology，2014，28(9):3855-3862.
[7]Chen J，Liu Z Y，Wang F，et al.Optimal oxygen excess ratio control for PEM fuel cells［J］.IEEE Transactions on Control Systems Technology，2018，26(5):1711-1721.
[8]Baroud Z，Benmiloud M，Benalia A，et al.Novel hybrid fuzzy-PID control scheme for air supply in PEM fuel-cell-based systems［J］.International Journal of Hydrogen Energy，2017，42(15):10435-10447.
[9]Ahmed S，Wang H P，Tian Y.Model-free control using time delay estimation and fractional-order nonsingular fast terminal sliding mode for uncertain lower-limb exoskeleton［J］.Journal of Vibration and Control，2018，24(22):5273-5290.
[10]Javaid U，Mehmood A，Arshad A，et al.Operational efficiency improvement of PEM fuel cell—a sliding mode based modern control approach［J］.IEEE Access，2020，8:95823-95831.
[11]Naghmeh M，Mehdi R S，Mahmood G.Robust control design for air breathing proton exchange membrane fuel cell system via variable gain second-order sliding mode［J］.Energy Science & Engineering，2018，6(3):126-143.
[12]Kunusch C，Puleston P F，Mayosky M A，et al.Sliding mode strategy for PEM fuel cells stacks breathing control using a super-twisting algorithm［J］.IEEE Transactions on Control Systems Technology，2009，17(1):167-174.
[13]Matraji I，Laghrouche S，Jemei S，et al.Robust control of the PEM fuel cell air-feed system via sub-optimal second order sliding mode［J］.Applied Energy，2013，104:945-957.
[14]Pilloni A，Pisano A，Usai E .Observer-based air excess ratio control of a PEM fuel cell system via high-order sliding mode［J］.IEEE Transactions on Industrial Electronics，2015，62(8):5236-5246.
[15]Wang J，Liu Y，Cao G，et al.Design of RBF adaptive sliding mode controller for a super cavitating vehicle［J］.IEEE Access，2021，9:39873-39883.
[16]Wang Y L，Wang Y F，Chen G.Robust composite adaptive neural network control for air management system of PEM fuel cell based on high-gain observer［J］.Neural Computing and Applications，2020，32(14):10229-10243.
[17]Talj R J，Hissel D，Ortega R，et al.Experimental validation of a PEM fuel cell reduced order model and a moto-compressor higher order sliding mode control［J］.IEEE Transactions on Industrial Electronics，2010，57(6):1906-1913.
[18]Li T，Duan S，Liu J，et al.An improved design of RBF neural network control algorithm based on spintronic memristor crossbar array［J］.Neural Computing & Applications，2016，30:1939-1946.
[19]Wang H，He P，Yu M，et al.Adaptive neural network sliding mode control for steer-by-wire-based vehicle stability control［J］.Journal of Intelligent & Fuzzy Systems，2016，31(2):885-902.
[20]Nasiri A，Nguang S K，Swain A.Adaptive sliding mode control for a class of MIMO nonlinear systems with uncertainties［J］.Journal of the Franklin Institute，2014，351(4):2048-2061.
[21]Qin H D，Yu X，Zhu Z B，et al.An expectation-maximization based single-beacon underwater navigation method with unknown ESV［J］.Neurocomputing，2019，378:295-303.

燃料电池空气供应系统自适应神经网络滑模控制

Adaptive Neural Network Sliding Mode Control for the Fuel Cell Air Supply System

RichHTML

PDF (PC)

可视化

摘要/Abstract

引用本文

使用本文

参考文献

相关文章 15

编辑推荐

Metrics

本文评价

[1]	周炳海，费芊然. 考虑能耗的混流装配线物料配送多目标调度方法[J]. 东北大学学报:自然科学版, 2020, 41(2): 258-264.
[2]	侯延彬，陈炳均，高宪文. 基于GM-ELM的有杆泵抽油井故障诊断[J]. 东北大学学报:自然科学版, 2019, 40(12): 1673-1678.
[3]	高金海，郝丽娜，项超群，祁紫轩. 基于复合ADRC的压电陶瓷驱动器自适应控制[J]. 东北大学学报:自然科学版, 2018, 39(8): 1158-1162.
[4]	刘姝廷，高宪文. 基于KPLS的丙烯爆炸极限非线性预测研究[J]. 东北大学学报:自然科学版, 2017, 38(11): 1521-1524.
[5]	刘永俊，魏阳杰，王义. 基于近邻主特征匹配的微纳米尺度位移测量[J]. 东北大学学报:自然科学版, 2017, 38(2): 195-199.
[6]	李翔宇，高宪文，李琨，侯延彬. 鱼群算法优化组合核函数GPR的油井动液面预测[J]. 东北大学学报:自然科学版, 2017, 38(1): 11-15.
[7]	周炳海，黎明. 考虑多晶圆流的集束型设备群调度方法[J]. 东北大学学报:自然科学版, 2016, 37(5): 697-701.
[8]	周炳海，周淑美，赵猛. 基于析取图考虑物料搬运的Job Shop调度算法[J]. 东北大学学报:自然科学版, 2016, 37(1): 138-142.
[9]	王通，高宪文，刘文芳. 基于改进即时学习算法的动液面软测量建模[J]. 东北大学学报:自然科学版, 2015, 36(7): 918-922.
[10]	刘晓斌，周炳海. OHT搬运系统防阻塞调度策略[J]. 东北大学学报:自然科学版, 2015, 36(2): 176-181.
[11]	李锐，黄敏，张瑞友，王兴伟. 基于弹复性的第四方物流网络设计模型与算法[J]. 东北大学学报:自然科学版, 2014, 35(3): 318-322.
[12]	魏阳杰，吴成东. 微纳米压电陶瓷驱动器的迟滞特性建模[J]. 东北大学学报:自然科学版, 2014, 35(2): 166-169.
[13]	王通，高宪文，蒋子健. 基于黑洞算法的LSSVM的参数优化[J]. 东北大学学报:自然科学版, 2014, 35(2): 170-174.
[14]	李琨，高宪文，仇治学，田中大. 有杆泵抽油系统井下工况诊断的物元分析方法[J]. 东北大学学报(自然科学版), 2013, 34(5): 613-616.
[15]	杨培颖，唐加福，于洋. 低碳型机场接送服务的改进二维扫描算法[J]. 东北大学学报(自然科学版), 2013, 34(4): 478-481.