Extreme-learning-machine-based FNTSM control strategy for electronic throttle
- PDF / 992,334 Bytes
- 12 Pages / 595.276 x 790.866 pts Page_size
- 95 Downloads / 219 Views
(0123456789().,-volV)(0123456789(). ,- volV)
EXTREME LEARNING MACHINE AND DEEP LEARNING NETWORKS
Extreme-learning-machine-based FNTSM control strategy for electronic throttle Youhao Hu1 • Hai Wang2 Xiaozheng Jin1
•
Zhenwei Cao3 • Jinchuan Zheng3 • Zhaowu Ping1 • Long Chen4
•
Received: 30 November 2018 / Accepted: 14 August 2019 Ó Springer-Verlag London Ltd., part of Springer Nature 2019
Abstract A novel extreme-learning-machine-based robust control scheme for automotive electronic throttle systems with uncertain dynamics is presented in this paper. It is shown that the well-known extreme learning machine (ELM) is used to estimate the upper bound of the lumped uncertainty while a fast nonsingular terminal sliding mode feedback controller is designed to achieve global stability and finite-time convergence for the closed-loop system. Although the ELM used in this paper has the same structure as the one in the conventional least-square-based ELM used for pattern classifications, i.e., the input weights are randomly chosen, the ELM adopted in the closed-loop control system is designed to achieve global control purpose. The output weights of the ELM will be adaptively adjusted in Lyapunov sense from the perspective of global stability of the closed-loop system, rather than local optimization in conventional ELM. The proposed control can thus not only realize the finite-time error convergence but also needs no prior knowledge of lumped uncertainty. Simulation results are demonstrated to verify the excellent tracking performance of the proposed control in comparison with other existing control methods. Keywords Electronic throttle Extreme learning machine Fast nonsingular terminal sliding mode Lumped uncertainty bound
1 Introduction The electronic throttle (ET) is a DC motor-driven valve regulating air flow into the intake manifold of spark-ignition combustion engine. It is different from the traditional mechanical throttle system that the ET is directly connected to the accelerator with a mechanical device and exhibits considerable merits in terms of safety and practicability. (1) The engine efficiency can be further improved due to the appropriate reduction in the fuel consumption. (2) By the & Hai Wang [email protected] 1
School of Electrical and Automation Engineering, Hefei University of Technology, Hefei 230009, China
2
College of Science, Health, Engineering ad Education, Murdoch University, Perth WA 6150, Australia
3
School of Software and Electrical Engineering, Swinburne University of Technology, Melbourne VIC3122, Australia
4
School of Electronics and Information, Hangzhou Dianzi University, Hangzhou 310018, China
virtue of drive-by-wire, the control stability and tracking accuracy as well as drivability can be simultaneously enhanced for practical implementation. The primary goal of the ET system is to enable the throttle plate to exactly track the reference position generated by the pedal. However, the synthesis of a satisfactory ET system is a challenging work due to various kinds
Data Loading...
