Adaptive Control of Vehicle Yaw Rate with Active Steering System and Extreme Learning Machine - A Pilot Study

2018 ◽  
pp. 1-11
Author(s):  
Pak Kin Wong ◽  
Wei Huang ◽  
Ka In Wong ◽  
Chi Man Vong
Keyword(s):  
Adaptive Control ◽  
Pilot Study ◽  
Extreme Learning Machine ◽  
Steering System ◽  
Yaw Rate ◽  
Active Steering ◽  
Learning Machine ◽  
Active Steering System

Torque Neutrality for Active Steering Systems

2012 ◽  
Vol 134 (5) ◽  
Author(s):  
Jonas Müller
Keyword(s):  
Transfer Functions ◽  
Steering System ◽  
Experimental Results ◽  
System Model ◽  
Steering Wheel ◽  
Control Law ◽  
Feed Forward Control ◽  
Power Steering ◽  
Active Steering ◽  
Active Steering System

This paper outlines a method for using an active steering system with two electrical actuators (one power-steering actuator and one superposition actuator) in order to manipulate the steering rack position without torque feedback to the steering wheel. To this effect, the power-steering actuator is used to implement a feed-forward control in order to compensate for the inertial effect introduced by the angle superposition. A rudimentary steering system model is used to derive the relevant transfer functions and assemble the control law for the superposition actuator. Experimental results of a research project at the BMW Group are included.

scholarly journals Adaptive Control Using Fully Online Sequential-Extreme Learning Machine and a Case Study on Engine Air-Fuel Ratio Regulation

2014 ◽  
Vol 2014 ◽  
pp. 1-11 ◽  
Author(s):  
Pak Kin Wong ◽  
Chi Man Vong ◽  
Xiang Hui Gao ◽  
Ka In Wong
Keyword(s):  
Adaptive Control ◽  
Extreme Learning Machine ◽  
Neural Control ◽  
Stochastic Gradient Descent ◽  
Initial Training ◽  
Node Number ◽  
Control Applications ◽  
Engine Model ◽  
Fuel Ratio ◽  
Learning Machine

Most adaptive neural control schemes are based on stochastic gradient-descent backpropagation (SGBP), which suffers from local minima problem. Although the recently proposed regularized online sequential-extreme learning machine (ReOS-ELM) can overcome this issue, it requires a batch of representative initial training data to construct a base model before online learning. The initial data is usually difficult to collect in adaptive control applications. Therefore, this paper proposes an improved version of ReOS-ELM, entitled fully online sequential-extreme learning machine (FOS-ELM). While retaining the advantages of ReOS-ELM, FOS-ELM discards the initial training phase, and hence becomes suitable for adaptive control applications. To demonstrate its effectiveness, FOS-ELM was applied to the adaptive control of engine air-fuel ratio based on a simulated engine model. Besides, controller parameters were also analyzed, in which it is found that large hidden node number with small regularization parameter leads to the best performance. A comparison among FOS-ELM and SGBP was also conducted. The result indicates that FOS-ELM achieves better tracking and convergence performance than SGBP, since FOS-ELM tends to learn the unknown engine model globally whereas SGBP tends to “forget” what it has learnt. This implies that FOS-ELM is more preferable for adaptive control applications.

scholarly journals RIDE COMFORT SIMULATION OF A VEHICLE EQUIPPED WITH SEMI-ACTIVE STEERING SYSTEM

2015 ◽  
Vol 11 ◽  
pp. 2495-2503
Author(s):  
M. Maharun ◽  
◽  
M.B. Baharom ◽  
M.S. Mohd ◽  
◽  
...  
Keyword(s):  
Ride Comfort ◽  
Steering System ◽  
Active Steering ◽  
Active Steering System

Fuzzy and Sliding Mode Variable Structure Control of Vehicle Active Steering System

2020 ◽  
Vol 13 ◽  
Author(s):  
Ganging Qi ◽  
Xiaobinc Fan ◽  
Zixiang Zhao
Keyword(s):  
Fuzzy Control ◽  
Sliding Mode Control ◽  
Sliding Mode ◽  
Steering System ◽  
Control Effect ◽  
Automobile Safety ◽  
Mode Control ◽  
Active Steering ◽  
Simulation Results ◽  
Active Steering System

Background: All the time, the safety of vehicle has been valued by all the world's parties, whether it is now or in the future, the automobile safety issue is the hotspot and focus of the research by experts and scholars both at home and abroad. The continuous increase of car ownership brings convenience to people's life and it also poses a threat to people's life and property security. Objective: Vehicle active safety system is the. hotspot of current research and development, which plays an important role in automobile safety. Through the analysis of patents and references, understand the development of an active steering system.In order to improve the development efficiency of active steering system, the paper proposes a feedback control method of front wheel angle. Methods: Based on yaw velocity and center of mass side angle, the Active Front Steering (AFS)model is established respectively by fuzzy control and sliding mode control under the establishment of seven degrees of freedom vehicle dynamics model and Dug off tire model. Results: The simulation results show that both the control algorithm of sliding mode control and fuzzy control can improve the handling stability of vehicle steering on high adhesion coefficient road surface. On the low adhesion coefficient road, the control effect of slide mode control is more ideal while fuzzy control caused larger oversteer. Conclusion: The simulation results show that the control effect of sliding mode is superior to fuzzy control.

Sign in / Sign up

Export Citation Format

Share Document