scholarly journals Position Control of Magnetic Levitation Ball Based on an Improved Adagrad Algorithm and Deep Neural Network Feedforward Compensation Control

2020 ◽  
Vol 2020 ◽  
pp. 1-13
Author(s):  
Zhouxiang Wei ◽  
Zhiwen Huang ◽  
Jianmin Zhu
Keyword(s):  
Neural Network ◽  
Pid Controller ◽  
Deep Neural Network ◽  
Position Control ◽  
Control Structure ◽  
Magnetic Levitation ◽  
Compensation Control ◽  
Static Performance ◽  
Dynamic Inverse ◽  
Trained Network

To control the position of the magnetic levitation ball more accurately, this paper proposes a deep neural network feedforward compensation controller based on an improved Adagrad optimization algorithm. The control structure of the controller consists of a deep neural network identifier, a deep neural network feedforward compensator, and a PID controller. First, the dynamic inverse model of the magnetic levitation ball is established by the deep neural network identifier which is trained online based on the improved Adagrad algorithm, and the trained network parameters are dynamically copied to the deep neural network feedforward compensator. Then, the position control of the magnetic levitation ball system is realized by the output of the feedforward compensator and the PID controller. Simulations and experiments illustrate that the accuracy of the deep network feedforward compensation control based on an improved Adagrad algorithm is higher, and its control system shows good dynamic and static performance and robustness to some extent.

Anti-sway position control of an automated transfer crane based on neural network predictive PID controller

2005 ◽  
Vol 19 (2) ◽  
pp. 505-519 ◽  
Author(s):  
Jin-Ho Suh ◽  
Jin-Woo Lee ◽  
Young-Jin Lee ◽  
Kwon-Soon Lee
Keyword(s):  
Neural Network ◽  
Pid Controller ◽  
Position Control

Tuning of an Adaptive Neural Network Compensator for Position Control of a Pneumatic System

2011 ◽  
Author(s):  
Behrad Dehghan ◽  
Sasan Taghizadeh ◽  
Brian Surgenor
Keyword(s):  
Neural Network ◽  
Pid Controller ◽  
Position Control ◽  
Experimental Results ◽  
Tracking Performance ◽  
Adaptive Neural Network ◽  
Extra Effort ◽  
Adaptive Nature ◽  
Gantry Robot ◽  
Neural Network Compensator

The paper examines the potential of a novel adaptive neural network compensator (ANNC) for the position control of a pneumatic gantry robot. Previousl experimental results were disappointing, with only a 20% improvement in performance when ANNC was employed with a PID controller. The conclusion was that the level of improvement with ANNC did not warrant the extra effort required for implementation. However, when the tests were repeated after the system had been reconfigured, improvements on the order of 45% to 70% were achieved. This paper presents a tuning procedure for ANNC, confirms the adaptive nature and provides results that support the conclusion that ANNC can indeed provide a significant improvement in tracking performance.

scholarly journals Position Control of a Pneumatic Muscle Actuator Using RBF Neural Network Tuned PID Controller

2015 ◽  
Vol 2015 ◽  
pp. 1-16 ◽  
Author(s):  
Jie Zhao ◽  
Jun Zhong ◽  
Jizhuang Fan
Keyword(s):  
Neural Network ◽  
Experimental Data ◽  
Phenomenological Model ◽  
Pid Controller ◽  
Position Control ◽  
Rbf Neural Network ◽  
Pneumatic Muscle ◽  
Highly Nonlinear ◽  
Experimental Apparatus ◽  
Pneumatic Muscle Actuator

Pneumatic Muscle Actuator (PMA) has a broad application prospect in soft robotics. However, PMA has highly nonlinear and hysteretic properties among force, displacement, and pressure, which lead to difficulty in accurate position control. A phenomenological model is developed to portray the hysteretic behavior of PMA. This phenomenological model consists of linear component and hysteretic component force. The latter component is described by Duhem model. An experimental apparatus is built up and sets of experimental data are acquired. Based on the experimental data, parameters of the model are identified. Validation of the model is performed. Then a novel cascade position PID controller is devised for a 1-DOF manipulator actuated by PMA. The outer loop of the controller is to cope with position control whilst the inner loop deals with pressure dynamics within PMA. To enhance the adaptability of the PID algorithm to the high nonlinearities of the manipulator, PID parameters are tuned online using RBF Neural Network. Experiments are performed and comparison between position response of RBF Neural Network based PID controller and that of classic PID controller demonstrates the effectiveness of the novel adaptive controller on the manipulator.

scholarly journals Adaptive Inverse Neural Network Based DC Motor Speed and Position Control Using FPGA

2018 ◽  
Vol 11 (3) ◽  
pp. 71-78
Author(s):  
Aula N. Abd
Keyword(s):  
Neural Network ◽  
Pid Controller ◽  
Position Control ◽  
Back Propagation ◽  
Dc Motor ◽  
Motor Speed ◽  
Back Propagation Algorithm ◽  
Neural Network Controller ◽  
Network Controller ◽  
Field Programmable

In this research two types of controllers are designed in order to control the speed and position of DC motor. The first one is a conventional PID controller and the other is an intelligent Neural Network (NN) controller that generate a control signal DC motor. Due to nonlinear parameters and movable laborers such saturation and change in load a conventional PID controller is not efficient in such application; therefore neural controller is proposed in order to decreasing the effect of these parameter and improve system performance. The proposed intelligent NN controller is adaptive inverse neural network controller designed and implemented on Field Programmable Gate Array (FPGA) board. This NN is trained by Levenberg-Marquardt back propagation algorithm. After implementation on FPGA, the response appear completely the same as simulation response before implementation that mean the controller based on FPGA is very nigh to software designed controller. The controllers designed by both m-file and Simulink in MATLAB R2012a version 7.14.0.

scholarly journals A Formation Flight Method with an Improved Deep Neural Network for Multi-UAV System

2020 ◽  
Vol 38 (2) ◽  
pp. 295-302
Author(s):  
Wenguang Xie ◽  
Kang Wu ◽  
Fang Yan ◽  
Haobin Shi ◽  
Xiaocheng Zhang
Keyword(s):  
Neural Network ◽  
Real Time ◽  
Pid Controller ◽  
Deep Neural Network ◽  
High Dimensional Data ◽  
Formation Flight ◽  
High Dimensional ◽  
Electronic Warfare ◽  
The Real ◽  
Multi Uav

It is crucial to develop an effective controller for the multi-UAV system to contribute to the frontier fields, such as the electronic warfare. To address the dilemma of the cooperative formation with the high dimensional data, a deep neural network(NN) controller is developed in this paper. Firstly, a deep NN model is used to tune parameters of PID controller online. Secondly, this paper introduces an improved deep NN model integrating the momentum to improve the performance of the classical NN model and satisfy the condition for the real time cooperative formation. Lastly, the cooperative formation task is achieved by extending the proposed cooperative controller with an improved NN to the complex multi-UAV system. The simulation result of multi-UAV formation demonstrates the effectiveness of the proposed method, which achieves a faster formation than competitors.

Neural Network Model for Assessing the Physical and Mechanical Properties of a Metal Material Based on Deep Learning

2020 ◽  
pp. 18-28
Author(s):  
Andrei Kliuev ◽  
Roman Klestov ◽  
Valerii Stolbov
Keyword(s):  
Neural Network ◽  
Mechanical Properties ◽  
Deep Neural Network ◽  
Physical And Mechanical Properties ◽  
Training Set ◽  
Test Set ◽  
Algorithmic Stability ◽  
Test Sets ◽  
Trained Network ◽  
Basic Test

The paper investigates the algorithmic stability of learning a deep neural network in problems of recognition of the materials microstructure. It is shown that at 8% of quantitative deviation in the basic test set the algorithm trained network loses stability. This means that with such a quantitative or qualitative deviation in the training or test sets, the results obtained with such trained network can hardly be trusted. Although the results of this study are applicable to the particular case, i.e. problems of recognition of the microstructure using ResNet-152, the authors propose a cheaper method for studying stability based on the analysis of the test, rather than the training set.

Sign in / Sign up

Export Citation Format

Share Document