Robust composite adaptive neural network control for air management system of PEM fuel cell based on high-gain observer
- PDF / 3,830,675 Bytes
- 15 Pages / 595.276 x 790.866 pts Page_size
- 35 Downloads / 164 Views
(0123456789().,-volV)(0123456789(). ,- volV)
ORIGINAL ARTICLE
Robust composite adaptive neural network control for air management system of PEM fuel cell based on high-gain observer Yunlong Wang1 • Yongfu Wang1 • Gang Chen2 Received: 6 May 2019 / Accepted: 10 October 2019 Ó Springer-Verlag London Ltd., part of Springer Nature 2019
Abstract Polymer electrolyte membrane (PEM) fuel cell system is usually affected negatively by external disturbance, model uncertainties and unmeasured variables. In this paper, a robust composite adaptive neural network controller using highgain observer is proposed to achieve stable oxygen excess ratio control for PEM fuel cell air management system. First, the derivatives of system output, which are unavailable due to the limited sensors, are estimated via high-gain observer. Then, a neural network is adopted to estimate the unknown system dynamics and the additional robust term is used to attenuate the compound disturbance including unknown external disturbance and neural network approximation error. Finally, a composite adaptive updating laws are constructed by utilizing estimated tracking error and modeling error to improve the tracking performance. In contrast to the existing controllers applied in PEM fuel cell air management system, this controller has a better control performance in the practical application. By means of Lyapunov stability analysis, it is theoretically proved that the system tracking error is uniformly ultimately bounded. The effectiveness and practicability of the proposed controller are validated by hardware-in-loop experiment. Keywords Composite adaptive control Neural network High-gain observer Polymer electrolyte membrane (PEM) fuel cell Abbreviations PEM Polymer electrolyte membrane OER Oxygen excess ratio HIL Hardware-in-loop RBFNN Radial basis function neural network CARBFNN Composite adaptive radial basis function neural network PID Proportion–integral–derivative RMSE Root mean square error SD Standard deviation
& Yongfu Wang [email protected] Yunlong Wang [email protected] Gang Chen [email protected] 1
School of Mechanical Engineering and Automation, Northeastern University, Shenyang 110819, Liaoning, China
2
College of IT and Engineering, Marshall University, Huntington, WV 25755, USA
1 Introduction Nowadays, with the excess energy consumption and the rapid environment deterioration, sustainable and economical energy has attracted considerable attention in public. As one of the new energies, the polymer electrolyte membrane (PEM) fuel cell has received lot of attentions due to its advantages such as high power, low operating temperature and non-pollution. It has been widely applied in various occasions such as laptops, automobiles and power generation [1–4]. However, the problem of shorter life span and inefficiency has remained unsolved. In order to obtain optimal performance, the control of PEM fuel cell air management system has attracted considerable attention in academia and industry. When external workload increase
Data Loading...
