Research on Neural Network Control Technology for Satellite-Based Laser Communication Tracking Turntable

2014 ◽  
Vol 945-949 ◽  
pp. 2266-2271
Author(s):  
Li Hua Wang ◽  
Xiao Qiang Wu
Keyword(s):  
Neural Network ◽  
Control System ◽  
Pid Controller ◽  
Dynamic Performance ◽  
Mathematic Model ◽  
Network Control ◽  
Learning Ability ◽  
Space Environment ◽  
Laser Communication ◽  
Self Learning

In space laser communication tracking turntable work environment characteristics, we design a neural network PID control system which makes the system’s parameter self-tuning. The control system cans self-tune parameters under the changes of the object’ mathematic model, it solves the problem for the control object’s model changes under the space environment. It also looks for method for optimum control through the function of neural network's self-learning in order to solve the problem of the precision’s decline which arouse from vibration and disturbance. The simulation experiments confirmed the self-learning ability of neural network, and described the neural PID controller dynamic performance is superior to the classical PID controller through the output characteristic curves contrast.

scholarly journals Single-Phase Photovoltaic Grid-Connected Inverter Based on Fuzzy Neural Network

2021 ◽  
Vol 25 (3) ◽  
pp. 310-316
Author(s):  
Shenping Xiao ◽  
Zhouquan Ou ◽  
Junming Peng ◽  
Yang Zhang ◽  
Xiaohu Zhang ◽  
...  
Keyword(s):  
Neural Network ◽  
Pid Controller ◽  
Fuzzy Neural Network ◽  
Single Phase ◽  
Fuzzy Inference ◽  
Learning Ability ◽  
Proportional Integral ◽  
Fuzzy Neural ◽  
Grid Connected Inverter ◽  
Self Learning

Based on a single-phase photovoltaic grid-connected inverter, a control strategy combining traditional proportional–integral–derivative (PID) control and a dynamic optimal control algorithm with a fuzzy neural network was proposed to improve the dynamic characteristics of grid-connected inverter systems effectively. A fuzzy inference rule was established after analyzing the proportional, integral, and differential coefficients of the PID controller. A fuzzy neural network was applied to adjust the parameters of the PID controller automatically. Accordingly, the proposed dynamic optimization algorithm was deduced in theory. The simulation and experimental results showed that the method was effective in making the system more robust to external disruption owing to its excellent steady-state adaptivity and self-learning ability.

Study on Multivariable System Based on PID Neural Network Control

2012 ◽  
Vol 591-593 ◽  
pp. 1490-1495 ◽  
Author(s):  
Huai Lin Shu ◽  
Jin Tian Hu
Keyword(s):  
Neural Network ◽  
Control System ◽  
Transfer Function ◽  
Design Process ◽  
Network Control ◽  
Neural Network Control ◽  
Single Variable ◽  
Multivariable System ◽  
Pid Neural Network ◽  
Self Learning

The multivariable PID neural network (MPIDNN) control system is introduced in this paper. MPIDNN is used to perform both the control and the decouple at the same time and to get better performance. It is difficult to control multivariable system by conventional controller because the strong coupling properties of the system. Generally, the decoupling system should be designed first and the multivariable object would be divided into several single variable objects. Then, several simple controller would achieve the control of those objects. The decoupling system and the controller exist in theory but the design process is very difficult actually because the transfer function of the object is difficult to get. Especially, if the number of the object inputs is not equal to that of the object outputs, which is called unsymmetry object, the conventional decoupling is impossible. A actual example is discussed in the paper in order to prove the function of the MPIDNN, in which an un-symmetry multivariable system which has 3 inputs and 2 outputs is controlled by a MPIDNN and the perfect control property is obtained by self-learning process.

Machining Error Analysis and its Compensation Using Fuzzy Inference in Crankshaft Non-Circular Grinding

2010 ◽  
Vol 44-47 ◽  
pp. 1084-1089 ◽  
Author(s):  
Nan Yan Shen ◽  
Ming Lun Fang ◽  
Jing Li ◽  
Yong Yi He
Keyword(s):  
Control System ◽  
High Efficiency ◽  
Fuzzy Inference ◽  
Mathematic Model ◽  
Numerical Control ◽  
Learning Ability ◽  
Strong Nonlinearity ◽  
Numerical Control System ◽  
Machining Error ◽  
Self Learning

The error sources, including technological system, numerical control system and motion control model, generate a machining error in the radial direction of the crankpin which varies with the rotating angle of the crankshaft journal in crankpin non-circular grinding. This machining error can be reduced in advance through giving the additional impulses as the displacement correction of grinding carriage to numerical control system. However due to the strong nonlinearity of non-circular grinding system, the machining error of crankpin is difficult to be described precisely by a certain mathematic model. In this paper, a compensation method is proposed, which utilizes the measured error after the last grinding circle and the change of error to find the initial compensation value in the next grinding circle by fuzzy reasoning. To increase the self-learning ability of this method, the final compensation value in the next circle is composed of the initial value and the final value in the last circle. The grinding experiments results show that the roundness error can be reduced into the expectation in only a few grinding circles by this method, which demonstrates its high efficiency and applicability.

Research on Pressurizer Pressure Control System Based on BP Neural Network Control of Self-Adjusted PID Parameters

2013 ◽  
Vol 291-294 ◽  
pp. 2416-2423 ◽  
Author(s):  
Guo Duo Zhang ◽  
Xu Hong Yang ◽  
Dong Qing Lu ◽  
Yong Xiao Liu
Keyword(s):  
Neural Network ◽  
Control System ◽  
Bp Neural Network ◽  
Pid Controller ◽  
Nuclear Reactor ◽  
Control Method ◽  
Setting Time ◽  
Pressure Control ◽  
Network Control ◽  
Pressure System

The pressurizer is an important device in nuclear reactor system, and the traditional PID regulator is usually used to control pressure system of pressurizer in modern reactors. However, it is difficult to get precise parameters of traditional PID controller, and the PID control method is relied on the precise mathematical model badly. And the response of PID controller is often shown by the large amount of overshoot and long setting time which are not the desired results. For such a large inertia and complex time-varying control system, the tradition PID controller can not obtain the satisfy control results. A controller based on BP neural network in this paper has a simple structure, and the parameters of PID controller can be tuned on-line by the neural network self-learning characteristics. The computer simulation experiment demonstrates that the BP neural network PID controller performs very well when compared with the tradition PID regulator in minimal overshoot and more quick response.

Application of Single Neuron Adaptive PID Controller in Flow Control System

2014 ◽  
Vol 602-605 ◽  
pp. 1052-1055 ◽  
Author(s):  
Ze Kang ◽  
Cheng Qiang Yin ◽  
Shao Min Teng
Keyword(s):  
Control System ◽  
Flow Control ◽  
Pid Controller ◽  
Single Neuron ◽  
Control Method ◽  
Dynamic Performance ◽  
Oxide Concentration ◽  
Flow Control System ◽  
Self Learning

Oxide concentration at reactor inlet is one of the most important factor effecting the quality of ethylene oxide concentration. A control method with adaptive PID of single neuron is propose using the parameter self-learning with adaptive PID controller of single neuron for the oxide flow control system. The simulation results show that this design scheme has a better dynamic performance than traditional PID scheme to verify the feasibility of this method.

Design of Control System of Eddy Current Retarder Based on BP Neural Network PID Controller

2014 ◽  
Vol 494-495 ◽  
pp. 223-228
Author(s):  
Fu Jin ◽  
Jian Jun Sun ◽  
Hong Bin Yu
Keyword(s):  
Neural Network ◽  
Control System ◽  
Eddy Current ◽  
Bp Neural Network ◽  
Pid Controller ◽  
Learning Algorithm ◽  
Rapid Response ◽  
Learning Ability ◽  
Eddy Current Retarder ◽  
Neural Network Pid

A new kind of algorithm of controller for eddy current retarder is designed in this paper. The eddy current retarder control system with traditional PID controller can't achieve a perfect performance in the rapid response. Back propagation (BP) neural network is one of artificial neural networks which has a good learning ability with a simple and recurrent structure, so it is suitable for controlling complicated eddy current retarder system. This paper introduces the principle, characteristics and learning algorithm of the BP neural network and designs the control system of eddy current retarder based on BP neural network PID controller by combining BP neural network and traditional PID. Making use of MATLAB, simulate this new kind of controller for eddy current retarder in the rapid response. Simulation results show it can improve the dynamic response performance and enhance the static precision compared to the traditional PID controller.

A Novel Hybrid Recurrent Wavelet Neural Network Control for a PMSM Driven Electric Scooter

2013 ◽  
Vol 284-287 ◽  
pp. 2194-2198 ◽  
Author(s):  
Chih Hong Lin ◽  
Chih Peng Lin
Keyword(s):  
Neural Network ◽  
Control System ◽  
Permanent Magnet Synchronous Motor ◽  
Wavelet Neural Network ◽  
Network Control ◽  
Learning Ability ◽  
Electric Scooter ◽  
Supervisor Control ◽  
On Line ◽  
On Line Learning

The electric scooter with nonlinear friction force of the transmission belt made the hybrid recurrent neural network (HRNN) control system with degenerated tracking responses. In order to overcome this problem, a hybrid recurrent wavelet neural network (HRWNN) control system is proposed to control for a permanent magnet synchronous motor (PMSM) driven electric scooter. The HRWNN control system consists of a supervisor control, a RWNN and a compensated control with adaptive law. The on-line parameter training methodology of the RWNN can be derived using adaptation laws and the Lyapunov stability theorem. The RWNN has the on-line learning ability to respond to the system’s nonlinear and time-varying behaviors. To show the effectiveness of the proposed controller, comparative studies with HRNN control system is demonstrated by experimental results.

scholarly journals FlexRay Vehicle Network Predictive Control Based on Neural Network

2018 ◽  
Vol 232 ◽  
pp. 01042 ◽  
Author(s):  
Li Huan ◽  
Li Chao
Keyword(s):  
Neural Network ◽  
Control System ◽  
Network Model ◽  
Predictive Control ◽  
Network Control ◽  
Learning Ability ◽  
Control Input ◽  
Network Control System ◽  
The Neural Network ◽  
Vehicle Network

We propose a design method of FlexRay vehicle network forecasting control based on the neural network to solve the security and reliability of FlexRay network control system, where the control performance and stability of the system are reduced when transmiting data under heavy load, by sampling the working state of the vehicle network at the present time to predict the next-time network state, and adapting to the dynamic load in the vehicular network system by on-line adaptive workload adjustment. The method used the nonlinear neural network model to predict the performance of the future model. The controller calculated the control input and optimized the performance of the next-time network model. The simulation results from the Matlab/Simulink showed that the neural network predictive control had good learning ability and adaptability. It could improve the performance of FlexRay vehicle network control system.

Constant Acceleration Control of Valve-Control-Cylinder System Based on Neural Network

2012 ◽  
Vol 430-432 ◽  
pp. 2041-2045
Author(s):  
Jun Gong Ma ◽  
Xian Yang Shang
Keyword(s):  
Neural Network ◽  
Control System ◽  
Pid Controller ◽  
Mathematic Model ◽  
Neural Element ◽  
Real Time Control ◽  
Time Control ◽  
Set Up ◽  
Valve Control ◽  
Control Cylinder

To solve the serious problem of the nonlinear and Time-varying uncertainty of the valve-control-cylinder system, a control system was designed with neural-proportion-integral-differential (PID) theory. Because of the capacity of neural network, the control system showed adaptive capacity in the system of valve-control-cylinder. In this paper, the basic theory of a single neural element self-adaptive PID controller and a model identifier based on Radial Basis Function were described. The mathematic model of the valve-control-cylinder control system was set up. The simulation results prove that the neural-PID system can regulate the PID parameters dynamically by self-learning so that the system with the neural-PID controller showed quick track performance and capacity against the disturbance. The results also prove the validity and applicability of the system. The algorithm is simple, PID initial parameters are easy to adjust, easy in application of the real-time control the valve-control-cylinder system.

Sign in / Sign up

Export Citation Format

Share Document