Title :
Learning from adaptive neural control for a class of pure-feedback systems
Author :
Min Wang ; Cong Wang
Author_Institution :
Coll. of Autom., South China Univ. of Technol., Guangzhou, China
Abstract :
This paper studies learning from adaptive neural control (ANC) for a class of pure-feedback nonlinear systems with unknown non-affine terms. The existence of the cascade structure and unknown non-affine terms makes it very difficult to achieve learning using previous methods. To overcome these difficulties, firstly, the implicit function theorem and the mean value theorem are combined to transform the closed-loop system into a semi-affine form during the control design process. Then, we decompose the stable closed-loop system into a series of linear time-varying (LTV) perturbed subsystems with the appropriate state transformation. Using a recursive design, the partial persistent excitation (PE) condition for the radial basis function (RBF) neural network (NN) is satisfied during tracking control to a recurrent reference trajectory. Under the PE condition, accurate approximations of the closed-loop system dynamics are recursively achieved in a local region along recurrent orbits of closed-loop signals. Subsequently, the NN learning control method which effectively utilizes the learned knowledge without re-adapting to the unknown system dynamics is proposed to achieve the closed-loop stability and the improved control performance. Simulation studies are performed to demonstrate the effectiveness of the proposed scheme.
Keywords :
adaptive control; cascade control; closed loop systems; feedback; learning (artificial intelligence); linear systems; neurocontrollers; radial basis function networks; stability; time-varying systems; trajectory control; ANC; LTV perturbed subsystem; NN learning control; RBF neural network; adaptive neural control; cascade structure; closed-loop stability; closed-loop system dynamics; implicit function theorem; linear time-varying system; mean value theorem; nonaffine terms; partial persistent excitation; pure-feedback nonlinear system; radial basis function; recursive design; semiaffine form; tracking control; Approximation methods; Artificial neural networks; Closed loop systems; Convergence; Orbits; Process control; Radial basis function networks;
Conference_Titel :
Control Automation Robotics & Vision (ICARCV), 2012 12th International Conference on
Conference_Location :
Guangzhou
Print_ISBN :
978-1-4673-1871-6
Electronic_ISBN :
978-1-4673-1870-9
DOI :
10.1109/ICARCV.2012.6485137