scholarly journals Neural network‐based non‐linear adaptive controller design for a class of bilinear system

2020 ◽  
Vol 2 (1) ◽  
pp. 1-11
Author(s):  
Samuel Oludare Bamgbose ◽  
Xiangfang Li ◽  
Lijun Qian
Keyword(s):  
Neural Network ◽  
Controller Design ◽  
Bilinear System ◽  
Adaptive Controller ◽  
Non Linear

scholarly journals PD Control Compensation Based on a Cascade Neural Network Applied to a Robot Manipulator

2020 ◽  
Vol 14 ◽  
Author(s):  
Luis Arturo Soriano ◽  
Erik Zamora ◽  
J. M. Vazquez-Nicolas ◽  
Gerardo Hernández ◽  
José Antonio Barraza Madrigal ◽  
...  
Keyword(s):  
Neural Network ◽  
Neural Networks ◽  
Robot Manipulator ◽  
Industrial Robot ◽  
Identification Problem ◽  
Adaptive Controller ◽  
Pd Control ◽  
Non Linear ◽  
Cascade Neural Network ◽  
Integral Gain

A Proportional Integral Derivative (PID) controller is commonly used to carry out tasks like position tracking in the industrial robot manipulator controller; however, over time, the PID integral gain generates degradation within the controller, which then produces reduced stability and bandwidth. A proportional derivative (PD) controller has been proposed to deal with the increase in integral gain but is limited if gravity is not compensated for. In practice, the dynamic system non-linearities frequently are unknown or hard to obtain. Adaptive controllers are online schemes that are used to deal with systems that present non-linear and uncertainties dynamics. Adaptive controller use measured data of system trajectory in order to learn and compensate the uncertainties and external disturbances. However, these techniques can adopt more efficient learning methods in order to improve their performance. In this work, a nominal control law is used to achieve a sub-optimal performance, and a scheme based on a cascade neural network is implemented to act as a non-linear compensation whose task is to improve upon the performance of the nominal controller. The main contributions of this work are neural compensation based on a cascade neural networks and the function to update the weights of neural network used. The algorithm is implemented using radial basis function neural networks and a recompense function that leads longer traces for an identification problem. A two-degree-of-freedom robot manipulator is proposed to validate the proposed scheme and compare it with conventional PD control compensation.

scholarly journals Adaptive backstepping controller design based on neural network for PMSM speed control

2021 ◽  
Vol 12 (3) ◽  
pp. 1940
Author(s):  
E. Sabouni ◽  
B. Merah ◽  
I. K. Bousserhane
Keyword(s):  
Neural Network ◽  
Control Algorithm ◽  
Controller Design ◽  
Classical Method ◽  
Permanent Magnet Synchronous Motor ◽  
Adaptive Controller ◽  
Nonlinear Controller ◽  
Adaptive Backstepping ◽  
Backstepping Controller ◽  
Adaptive Backstepping Controller

<span lang="EN-US">The aim of this research is the speed tracking of the permanent magnet synchronous motor (PMSM) using an intelligent Neural-Network based adapative backstepping control. First, the model of PMSM in the Park synchronous frame is derived. Then, the PMSM speed regulation is investigated using the classical method utilizing the field oriented control theory. Thereafter, a robust nonlinear controller employing an adaptive backstepping strategy is investigated in order to achieve a good performance tracking objective under motor parameters changing and external load torque application. In the final step, a neural network estimator is integrated with the adaptive controller to estimate the motor parameters values and the load disturbance value for enhancing the effectiveness of the adaptive backstepping controller. The robsutness of the presented control algorithm is demonstrated using simulation tests. The obtained results clearly demonstrate that the presented NN-adaptive control algorithm can provide good trackingperformances for the speed trackingin the presence of motor parameter variation and load application.</span>

Neural network adaptive control of nonlinear systems preceded by hysteresis

2020 ◽  
Vol 32 (1) ◽  
pp. 104-112
Author(s):  
Xinlong Zhao ◽  
Qiang Su ◽  
Shengxin Chen ◽  
Yonghong Tan
Keyword(s):  
Neural Network ◽  
Adaptive Control ◽  
Controller Design ◽  
Experimental Tests ◽  
Adaptive Controller ◽  
Auxiliary Variable ◽  
Proposed Model ◽  
And Control ◽  
Novel Model ◽  
Hysteresis Characteristics

Neural network adaptive control is proposed for a class of nonlinear system preceded by hysteresis. A novel model is developed to represent the hysteresis characteristics in explicit form. Furthermore, the auxiliary variable of the proposed model is proved to be bounded, which is essential for controller design. Then, neural network adaptive controller is directly applied to mitigate the influence of the hysteresis without constructing the hysteresis inverse. The updated law and control law of the controllers are derived from Lyapunov stability theorem, so that the boundedness of the close-loop system is guaranteed. Finally, the experimental tests are carried out to validate the effectiveness of the proposed approach.

Sign in / Sign up

Export Citation Format

Share Document