scholarly journals Neural Learning Control of Flexible Joint Manipulator with Predefined Tracking Performance and Application to Baxter Robot

Complexity ◽  
2017 ◽  
Vol 2017 ◽  
pp. 1-14 ◽  
Author(s):  
Min Wang ◽  
Huiping Ye ◽  
Zhiguang Chen
Keyword(s):  
Neural Control ◽  
Tracking Error ◽  
Small Neighborhood ◽  
Dynamic Surface Control ◽  
Dynamic Surface ◽  
Flexible Joint ◽  
Persistent Excitation ◽  
Neural Learning ◽  
Control Scheme ◽  
Flexible Joint Manipulator

This paper focuses on neural learning from adaptive neural control (ANC) for a class of flexible joint manipulator under the output tracking constraint. To facilitate the design, a new transformed function is introduced to convert the constrained tracking error into unconstrained error variable. Then, a novel adaptive neural dynamic surface control scheme is proposed by combining the neural universal approximation. The proposed control scheme not only decreases the dimension of neural inputs but also reduces the number of neural approximators. Moreover, it can be verified that all the closed-loop signals are uniformly ultimately bounded and the constrained tracking error converges to a small neighborhood around zero in a finite time. Particularly, the reduction of the number of neural input variables simplifies the verification of persistent excitation (PE) condition for neural networks (NNs). Subsequently, the proposed ANC scheme is verified recursively to be capable of acquiring and storing knowledge of unknown system dynamics in constant neural weights. By reusing the stored knowledge, a neural learning controller is developed for better control performance. Simulation results on a single-link flexible joint manipulator and experiment results on Baxter robot are given to illustrate the effectiveness of the proposed scheme.

Robust Adaptive NN Design for Course-Tracking Control of Ship with Input Saturation

2013 ◽  
Vol 712-715 ◽  
pp. 2768-2774 ◽  
Author(s):  
Hong Ying Sun ◽  
Feng Wei Yu
Keyword(s):  
Neural Control ◽  
Tracking Error ◽  
Input Saturation ◽  
Dynamic Surface Control ◽  
Design System ◽  
Dynamic Surface ◽  
Control Scheme ◽  
Robust Adaptive ◽  
The Stability ◽  
Computation Load

In this paper, a novel robust adaptive neural control scheme is proposed for a class of ship course autopilot with input saturation.RBF neural networks (NNs) are used to tackle unknown nonlinear functions,then the robust adaptive NN tracking controller is constructed by combining dynamic surface control (DSC) technique and the minimal-learning-parameters (MLP) algorithm. The stability analysis subject to the effect of input saturation constrains is conducted employing an auxiliary design system. With only one learning parameter and reduced computation load, the proposed algorithm can avoid both problem of “explosion of complexity” in the conventional backstepping method and singularity problem. In addition, the boundedness stability of the closed-loop system is guaranteed and tracking error can be made arbitrary small. The effectiveness of the presented autopilot has been demonstrated in the simulation.

scholarly journals Adaptive Dynamic Surface Control for Generator Excitation Control System

2014 ◽  
Vol 2014 ◽  
pp. 1-11 ◽  
Author(s):  
Zhang Xiu-yu ◽  
Liu Cui-ping ◽  
Wang Jian-guo ◽  
Lin Yan
Keyword(s):  
Neural Network ◽  
Control System ◽  
Tracking Error ◽  
Dynamic Surface Control ◽  
Excitation Control ◽  
Dynamic Surface ◽  
Adaptive Dynamic ◽  
Surface Control ◽  
Control Scheme ◽  
Generator Excitation Control

For the generator excitation control system which is equipped with static var compensator (SVC) and unknown parameters, a novel adaptive dynamic surface control scheme is proposed based on neural network and tracking error transformed function with the following features: (1) the transformation of the excitation generator model to the linear systems is omitted; (2) the prespecified performance of the tracking error can be guaranteed by combining with the tracking error transformed function; (3) the computational burden is greatly reduced by estimating the norm of the weighted vector of neural network instead of the weighted vector itself; therefore, it is more suitable for the real time control; and (4) the explosion of complicity problem inherent in the backstepping control can be eliminated. It is proved that the new scheme can make the system semiglobally uniformly ultimately bounded. Simulation results show the effectiveness of this control scheme.

scholarly journals Spiking-Free HGO-Based Dynamic Surface Control for Flexible Joint Manipulator with Unmeasurable States

2020 ◽  
Author(s):  
Dezhi Kong ◽  
Wendong Wang ◽  
Yikai Shi
Keyword(s):  
High Gain ◽  
Dynamic Surface Control ◽  
Lyapunov Theory ◽  
System Stability ◽  
Dynamic Surface ◽  
Flexible Joint ◽  
Surface Control ◽  
Estimation Of Uncertainties ◽  
Flexible Joint Manipulator ◽  
Manipulator Control

Abstract For the flexible joint manipulator control system (FJMCS) with unmeasurable states, a novel partial states feedback control (PSFC) is proposed. Firstly, the unmeasurable states and the uncertainties are observed by a high-gain observer (HGO) simultaneously. Then, a dynamic surface controller is proposed based on the output of the HGO. The newly proposed controller has several advantages over existing methods. First, the proposed controller not only uses the estimate states to avoid using unmeasurable states, but also uses the estimation of uncertainties to enhance the robustness of FJMCS. Second, a novel spike suppression function (SSF) is developed to avoid the estimation spike problem in the existing HGO-based controllers. The closed-loop system stability is proved by the Lyapunov theory. Simulation results demonstrate the effectiveness of the proposed controller.

Dynamic Surface Neural Control for a Class of Nonlinear Time-Varying Delay Systems Preceded by Unknown Hysteresis

2013 ◽  
Vol 651 ◽  
pp. 937-942 ◽  
Author(s):  
Xiu Yu Zhang ◽  
Cui Ping Liu ◽  
Yan Sun
Keyword(s):  
Neural Control ◽  
Tracking Error ◽  
Dynamic Surface Control ◽  
Delay Systems ◽  
Time Varying ◽  
Dynamic Surface ◽  
Time Varying Delay ◽  
Complexity Problem ◽  
Robust Adaptive ◽  
Varying Delay

In this paper, a new robust adaptive neural dynamic surface control is proposed for a class of time-varying delay nonlinear systems preceded by backlash-like hysteresis. Compared with the present schemes of dealing with time-varying delay and hysteresis input, the main advantages of the proposed scheme are that the prespecified transient and steady state performance of tracking error can be guaranteed for the first time when using DSC to deal with the time-varing delays; the computational burden can be greatly reduced and the explosion of complexity problem inherent in backstepping control can be eliminated. It is proved that the new scheme can guarantee all the closed-loop signals semi-globally uniformly ultimate bounded. Simulation results are presented to demonstrate the validity of the proposed scheme.

Modeling and Dynamic Surface Control of Uncertain Strict-Feedback Nonlinear Systems Using Adaptive Fuzzy Wavelet Network

2018 ◽  
pp. 112-133
Author(s):  
Maryam Shahriari-Kahkeshi
Keyword(s):  
Nonlinear Systems ◽  
Dynamic Surface Control ◽  
Wavelet Network ◽  
Dynamic Surface ◽  
Adaptive Fuzzy ◽  
Surface Control ◽  
Control Scheme ◽  
Adaptive Laws ◽  
Dsc Method ◽  
Strict Feedback

This chapter proposes a new modeling and control scheme for uncertain strict-feedback nonlinear systems based on adaptive fuzzy wavelet network (FWN) and dynamic surface control (DSC) approach. It designs adaptive FWN as a nonlinear-in-parameter approximator to approximate the uncertain dynamics of the system. Then, the proposed control scheme is developed by incorporating the DSC method to the adaptive FWN-based model. Stability analysis of the proposed scheme is provided and adaptive laws are designed to learn all linear and nonlinear parameters of the network. It is proven that all the signals of the closed-loop system are uniformly ultimately bounded and the tracking error can be made arbitrary small. The proposed scheme does not require any prior knowledge about dynamics of the system and offline learning. Furthermore, it eliminates the “explosion of complexity” problems and develops accurate model of the system and simple controller. Simulation results on the numerical example and permanent magnet synchronous motor are provided to show the effectiveness of the proposed scheme.

Sign in / Sign up

Export Citation Format

Share Document