Robust Neural-Network Hybrid Tracking Control of Underwater Vehicles

2008 ◽  
Author(s):  
Wei-Lin Luo ◽  
Zao-Jian Zou ◽  
Lan-Ping Huang
Keyword(s):  
Neural Network ◽  
Autonomous Underwater Vehicle ◽  
Underactuated System ◽  
Tracking Errors ◽  
Actuator Dynamics ◽  
The Neural Network ◽  
Modeling Errors ◽  
Random Disturbances ◽  
On Line ◽  
Bounded Disturbances

A cascade system of an autonomous underwater vehicle is considered. It consists of the nonlinear equation of motion and the equations of actuator dynamics. In the motion equation, unmatched uncertainties are taken into account, including the modeling errors and the bounded disturbances. The modeling errors result from the parameter errors, the ignored high-order modes and unmodelled dynamics. The bounded disturbances refer to environment forces or unknown random disturbances. To obtain accurate manoeuvring of the underactuated system, a hybrid robust controller is proposed by using backstepping Lyapunov functions. A two-layer feedforward neural-network is applied to compensate the modeling errors and the derivatives of desired control inputs, while the H∞ control strategy is used to achieve the L2-gain performance with respect to the bounded disturbances. The on-line tuning algorithms of the neural-network weights are given. The uniformly ultimately bounded stabilities of the tracking errors and the neural-network weights errors are analyzed. Moreover, selection of the gains in controller is recommended by analysis of the upper boundedness of errors. Simulation results have demonstrated the validity of the controller proposed.

scholarly journals Computer image processing and neural network technology for boiler thermal energy diagnosis

2020 ◽  
Vol 24 (5 Part B) ◽  
pp. 3059-3068
Author(s):  
Qinghong Wu
Keyword(s):  
Neural Network ◽  
Image Processing ◽  
Thermal Energy ◽  
Processing System ◽  
Heat Energy ◽  
Image Feature ◽  
The Neural Network ◽  
Computer Image Processing ◽  
On Line ◽  
Parameter Values

The paper uses the flame image processing technology to diagnose the furnace flame combustion achieve the measurement of boiler heat energy. The paper obtains the combustion image of the flame image processing system, and extracts the flame image characteristics of the boiler thermal energy diagnosis, constructs the neural network model of the boiler thermal energy diagnosis, and trains and tests the extracted flame image feature parameter values as the input of the neural network. A rough diagnosis of the boiler?s thermal energy is obtained while predicting the state of combustion. According to the research results, a boiler thermal energy diagnosis system was designed and tested on the boiler of 200 MW unit. The experimental results confirmed the applicability of the system, which can realize on-line monitoring of boiler heat energy and evaluate the combustion situation.

Estimation of Weld Pool Sizes in GMA Welding Process Using Neural Networks

1993 ◽  
Vol 207 (1) ◽  
pp. 15-26 ◽  
Author(s):  
T G Lim ◽  
H S Cho
Keyword(s):  
Neural Network ◽  
Weld Pool ◽  
Gma Welding ◽  
Quality Monitoring ◽  
Design Parameters ◽  
Geometrical Parameters ◽  
The Neural Network ◽  
On Line ◽  
Welding Processes ◽  
Pool Sizes

In gas metal arc (GMA) welding processes, the geometrical shape and size of the weld pool are utilized to assess the integrity of the weld quality. Monitoring of these geometrical parameters for on-line process control as well as for on-line quality evaluation, however, is an extremely difficult problem. The paper describes the design of a neural network estimator to estimate weld pool sizes for on-line use in quality monitoring and control. The neural network estimator is designed to estimate the weld pool sizes from surface temperatures measured at various points on the top surface of the weldment. The main task of the neural network is to realize the mapping characteristics from the point temperatures to the weld pool sizes through training. The chosen design parameters of the neural network estimator, such as the number of hidden layers and the number of nodes in a layer, are based on an estimation error analysis. A series of bead-on-plate welding experiments were performed to assess the performance of the neural network estimator. The experimental results show that the proposed neural network estimator can estimate the weld pool sizes with satisfactory accuracy.

A Study of PID Control System Based on BP Neural Network

2011 ◽  
Vol 328-330 ◽  
pp. 1908-1911
Author(s):  
Wei Liu ◽  
Jian Jun Cai ◽  
Xi Pin Fan
Keyword(s):  
Neural Network ◽  
Control System ◽  
Conjugate Gradient ◽  
Bp Neural Network ◽  
Pid Control ◽  
Pid Controller ◽  
Steepest Descent ◽  
The Neural Network ◽  
On Line ◽  
New Type

To deal with the defects of the steepest descent in slowly converging and easily immerging in partialm in imum,this paper proposes a new type of PID control system based on the BP neural network, which is a combination of the neural network and the PID strategy. It has the merits of both neural network and PID controller. Moreover, Fletcher-Reeves conjugate gradient in controller can make the training of network faster and can eliminate the disadvantages of steepest descent in BP algorithm. The parameters of the neural network PID controller are modified on line by the improved conjugate gradient. The programming steps under MATLAB are finally described. Simulation result shows that the controller is effective.

Neural Network-Based Speed Control of A Two-Mass-Model System

1999 ◽  
Vol 3 (5) ◽  
pp. 427-430 ◽  
Author(s):  
Rached Dhaouadi ◽  
◽  
Khaled Nouri
Keyword(s):  
Neural Network ◽  
Inverse Dynamics ◽  
Mass Model ◽  
Neural Network Learning ◽  
Inverse Control ◽  
Network Learning ◽  
The Neural Network ◽  
Control Scheme ◽  
On Line ◽  
Neural Network Structure

We present an application of artificial neural networks to the problem of controlling the speed of an elastic drive system. We derive a neural network structure to simulate the inverse dynamics of the system, then implement the direct inverse control scheme in a closed loop. The neural network learning is done on-line to adaptively control the speed to follow a stepwise changing reference. The experimental results with a two-mass-model analog board confirm the effectiveness of the proposed neurocontrol scheme.

Neural Network Adaptive Control of Free Floating Space Robot with Actuator Saturation

2014 ◽  
Vol 590 ◽  
pp. 380-385 ◽  
Author(s):  
Guo Liang Zhang ◽  
Ting Lei ◽  
Fan Yang ◽  
Zhuang Cai
Keyword(s):  
Neural Network ◽  
Adaptive Learning ◽  
Control Strategy ◽  
Actuator Saturation ◽  
Space Robot ◽  
Global Approximation ◽  
Neural Network Approach ◽  
The Neural Network ◽  
On Line ◽  
The Stability

This paper proposes an adaptive neural network law for trajectory tracking of a class of free-floating space robot with actuator saturation. Using neural network with global approximation, the control strategy design an on-line real time adaptive learning law to approach the uncertain model and the actuator saturation nonlinearity. The neural network approach errors and outside disturbance can be eliminated by a robust controller.The control strategy need not depend on the model, and can be used under actuator saturation.The control strategy can guarantee the stability of system and the asymptotic convergence of tracking errors based on the Lyapunov’s theory. The simulation results indicate that the proposed strategy can effectively work with actuator saturation.

Optimization of the Neural Network by Using the LabVIEW Instrumentation

2012 ◽  
Vol 463-464 ◽  
pp. 1011-1016 ◽  
Author(s):  
Adrian Olaru ◽  
Serban Olaru ◽  
Dan Paune ◽  
Oprean Aurel
Keyword(s):  
Neural Network ◽  
Transfer Functions ◽  
Error Function ◽  
Virtual Instrumentation ◽  
Closed Loops ◽  
Network Parameters ◽  
The Neural Network ◽  
On Line ◽  
The Mean ◽  
Number Of Iterations

The paper shown one assisted method to construct simple and complex neural network and to simulate on-line them. By on-line simulation of some more important neural simple and complex network is possible to know what will be the influences of all network parameters like the input data, weight, biases matrix, sensitive functions, closed loops and delay of time. There are shown some important neurons type, transfer functions, weights and biases of neurons, and some complex layers with different type of neurons. By using the proper virtual LabVIEW instrumentation in on-line using, were established some influences of the network parameters to the number of iterations before canceled the mean square error to the target. Numerical simulation used the proper teaching law and proper virtual instrumentation. In the optimization step of the research on used the minimization of the error function between the output and the target.

Adaptive Neural Network Compensating Control for Coordinated Motion of Space-Based Robot System With Uncertain Parameters and External Disturbances

2009 ◽  
Author(s):  
Chen Zhiyong ◽  
Chen Li
Keyword(s):  
Neural Network ◽  
System Stability ◽  
Uncertain Parameters ◽  
Coordinated Motion ◽  
Adaptive Neural Network ◽  
Robot System ◽  
External Disturbances ◽  
Neural Network Controller ◽  
The Neural Network ◽  
On Line

The control problem of space-based robot system with uncertain parameters and external disturbances is considered. With Lagrangian formulation and augmentation approach, the dynamic equations of space-based robot system in workspace are derived. Based on the results, an adaptive neural network compensating control scheme for coordinated motion between the base’s attitude and end-effector of space-based robot system is developed. It is based on the inertia-related method, and incorporates a neural network controller to compensate the uncertainties. The closed-loop system stability with the neural network adapted on-line is discussed in detail through the Lyapunov stability approach. Comparing with many adaptive and robust control schemes, the controller proposed does not require one to determine the regression matrix for space robot system and then avoids tedious computations. Numerical simulations are provided to show the effectiveness of the approach.

Research of On-Line Monitoring Technology of Machining Accuracy of CNC Machine Tools

2013 ◽  
Vol 846-847 ◽  
pp. 268-273
Author(s):  
Rong Bo Shi ◽  
Zhi Ping Guo ◽  
Zhi Yong Song
Keyword(s):  
Neural Network ◽  
Machine Tools ◽  
Cnc Machine Tools ◽  
Frequency Domain Method ◽  
Machining Accuracy ◽  
Cnc Machine ◽  
Monitoring Technology ◽  
The Neural Network ◽  
Network Identification ◽  
On Line

This paper analyzes CNC machine tools machining error sources, put forward a kind of on-line monitoring technology of CNC machine tools machining accuracy based on online neural network. Through the establishment of CNC machine tools condition monitoring platform, collection sensor signal of the key components of CNC machine tools, using time domain and frequency domain method of the original signal processing, extract the characteristic related to machining accuracy change, input to the neural network, identification the changes of machining accuracy. The experimental results show that, the on-line monitoring technology based on neural network, can identify the changes of machining accuracy.

scholarly journals ANN Based Inverse Dynamic Model of the 6-PGK Parallel Robot Manipulator

2015 ◽  
Vol 11 (1) ◽  
pp. 90 ◽  
Author(s):  
Liviu Moldovan ◽  
Horațiu-Ștefan Grif ◽  
Adrian Gligor
Keyword(s):  
Neural Network ◽  
Artificial Neural Network ◽  
Robot Manipulator ◽  
Parallel Robot ◽  
Model Estimation ◽  
Inverse Dynamic ◽  
Inverse Dynamic Model ◽  
The Neural Network ◽  
On Line ◽  
Artificial Neural

<p>This paper presents an inverse dynamic model estimation based on an artificial neural network of a complete new parallel robot manipulator prototype 6- PGK with six degrees of freedom, built at Petru Maior University of Tirgu-Mures. The model estimation of the parallel robot manipulator is performed with a feedforward artificial neural network. In the control engineering domain there are control structures that need the direct or inverse model of the process for ensuring the process control at the imposed performances. Usually, the determination of the direct/inverse mathematical model is a difficult or impossible task to be achieved. In these cases different non-parametric or parametric, off-line or on-line identification methods are used. A solution that may support the on-line parametric methods is represented by the feedforward artificial neural networks. By implementing feedforward artificial neural networks as a nonlinear autoregressive model with exogenous inputs, the authors investigate the possibility of choosing the optimum parameters that characterize the neural network so that it approximates as better as possible the model of the 6-PGK prototype robot. Finally an innovative algorithm is developed for obtaining the optimal configuration parameters set of the feedforward artificial neural network. The proposed algorithm helps in setting the optimal parameters of the neural network that offer high opportunities to provide satisfactory identification of the robot model. Experimental results obtained by a structure derived from the proposed solution demonstrate a good approximation related to the studied system, which is characterized by nonlinearities and high complexity.</p>

Sign in / Sign up

Export Citation Format

Share Document