Superheater Steam Temperature Control Based on the Expanded-Structure Neural Network Inverse Models

2012 ◽  
Vol 443-444 ◽  
pp. 401-407 ◽  
Author(s):  
Liang Yu Ma ◽  
Zhen Xing Shi ◽  
Kwang Y. Lee
Keyword(s):  
Neural Network ◽  
Process Models ◽  
Steam Temperature ◽  
Operating Characteristics ◽  
Control Effect ◽  
Inverse Dynamic ◽  
Inverse Models ◽  
Control Scheme ◽  
Detailed Simulation ◽  
On Line

In order to improve the control effect of the Superheater Steam Temperature (SST) for a 300MW boiler unit, this paper presents an inverse compensation control scheme based on the expanded-structure neural network inverse models. The input and output variables of the expanded–structure neural network Inverse Dynamic Process Models （IDPMs） for the superheater system are determined from understanding of the boiler operating characteristics. Then, two neural network (NN) inverse controllers are designed with the IDPMs as on-line output compensators for the original cascade PID controllers in order to improve the control effect. Detailed simulation tests are carried out on the full-scope simulator of the given 300MW power unit. It is shown by tests that the control effects of the NN-compensated control on the SST are significantly improved compared with the case of the original cascade PID control scheme.

scholarly journals Improving the Performance of Process Controllers Using a New Clustered Neural Network

2011 ◽  
Vol 1 ◽  
pp. 273-277
Author(s):  
M. Reza Soleymani Yazdi ◽  
Michel Guillot
Keyword(s):  
Neural Network ◽  
Multilayer Perceptron ◽  
Operating Conditions ◽  
Machining Processes ◽  
Workpiece Material ◽  
Control Scheme ◽  
Organization Capacity ◽  
First Results ◽  
On Line ◽  
Neuro Controller

This paper presents first a newly developed clustered neural network, which incorporates self-organization capacity into the well-known common multilayer perceptron (MLP) architecture. With this addition, it is possible to reduce significantly overall memory degradation of the neuro-controller during on-line training. In the second part of the paper, this clustered multilayer perceptron (CMLP) network is applied and compared to the MLP through modeling and simulations of machining processes. Simulation results presented using machining data demonstrate that the CMLP possesses more powerful modeling capacity than the standard MLP, offers better adaptability to new operating conditions, and finally performs more reliably. During on-line training with machining data about 65% degradation of previously learned information can be observed in the MLP as opposed to only 11% for the CMLP. Finally, an adaptive control scheme intended for on-line optimization of the machining processes is presented. This scheme uses a feed forward CMLP inverse neuro-controller which learns off-line and on-line the relationships between process inputs and output under simulated perturbations (i.e., tool wear and non-homogeneous workpiece material properties). The first results using the CMLP inverse neuro-controller are promising

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.

Superheated Steam Temperature Control Based on Improved Recurrent Neural Network and Simplified PSO Algorithm

2011 ◽  
Vol 128-129 ◽  
pp. 1065-1069 ◽  
Author(s):  
Liang Yu Ma ◽  
Yin Ping Ge ◽  
Xing Cao
Keyword(s):  
Neural Network ◽  
Temperature Control ◽  
Recurrent Neural Network ◽  
Power Plants ◽  
Superheated Steam ◽  
Steam Temperature ◽  
Superheated Steam Temperature ◽  
Control Scheme ◽  
Wide Range ◽  
Optimization Control

Coal-fired power plants are facing a rapid developing tide toward supercritical and ultra-supercritical boiler units with higher parameters and bigger capacity. Due to the large inertia, large time delay and nonlinear characteristics of a boiler’s superheater system, the widely-used conventional cascade PID control scheme is often difficult to obtain satisfactory steam temperature control effect under wide-range operating condition. In this paper, a predictive optimization control method based on improved mixed-structure recurrent neural network model and a simpler Particle Swarm Optimization (sPSO) algorithm is presented for superheated steam temperature control. Control simulation tests on the full-scope simulator of a 600 MW supercritical power unit showed that the proposed predictive optimization control scheme can greatly improve the superheated steam temperature control quality with good application prospect.

Research on Fuzzy Adaptive Control of Multi-Cylinder Synchronous Hydraulic System

2013 ◽  
Vol 456 ◽  
pp. 244-247
Author(s):  
Guo Hua Zhao
Keyword(s):  
Adaptive Control ◽  
Hydraulic System ◽  
Rolling Process ◽  
Pi Control ◽  
Control Effect ◽  
Fuzzy Adaptive Control ◽  
Control Scheme ◽  
Hydraulic Servo ◽  
On Line ◽  
Fuzzy Adaptive

In large continuous rolling process, that the roller can be accurately control have an important impact on production. In allusion to the characteristics of variable and nonlinear of hydraulic servo system parameters for controlling roller position, fuzzy PI control and adjusting the parameters in on-line are used, in order to realize the three cylinder synchronous control. The research results indicate: for system with external force disturbance, the fuzzy adaptive control has a strong anti-interference ability, and improve the robustness of the control system of multi-cylinder synchronization, as a result, to obtain the satisfactory control effect. To be carried out simulation with Matlab, the results show that the fuzzy PI control scheme is a high precision, efficient and feasible method, and can obtain the satisfactory results.

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>

Intelligent Control of Uncertain PMSM Based on Stable and Adaptive Discrete-Time Neural Network Compensators

2021 ◽  
Vol 54 (4) ◽  
pp. 575-589
Author(s):  
Aziz El Janati El Idrissi ◽  
Mohsin Beniysa ◽  
Adel Bouajaj ◽  
Mohammed Réda Britel
Keyword(s):  
Neural Network ◽  
Intelligent Control ◽  
High Speed ◽  
Closed Loop ◽  
Permanent Magnet Synchronous Motor ◽  
Closed Loop System ◽  
Adaptive Neural Network ◽  
Control Scheme ◽  
On Line ◽  
Classical Vector

In this paper, stable and adaptive neural network compensators are proposed to control the uncertain permanent magnet synchronous motor (PMSM). Firstly, the overall uncertainties caused by mathematical modelling, parameters variation during operation and external load torque disturbances are modelled. Secondly, a new motion control scheme, where (d-q) current loops are dotted by two on-line tuning neural network compensators (NNCs), is used to compensate these uncertainties. As a result, the speed control loop is processed easily by proportional integral (PI) controller. Stability of the closed-loop system is also designed according to the Lyapunov stability. Compared to classical vector control, the simulations of PMSM system at different speeds including nominal, low and high speed, with and without uncertainties, show the effectiveness of the proposed control scheme.

scholarly journals Optimization of electrochemical parameters in microbial fuel cell system based on Fuzzy-PID and CMAC neural network

2019 ◽  
Vol 9 (2) ◽  
pp. 135-142 ◽  
Author(s):  
Chengcai Fu ◽  
Fengying Ma
Keyword(s):  
Neural Network ◽  
Optimal Control ◽  
Microbial Fuel Cells ◽  
Pid Controller ◽  
Cerebellar Model Articulation Controller ◽  
Fuzzy Pid ◽  
Control Effect ◽  
Cmac Neural Network ◽  
Electrochemical Parameters ◽  
Control Scheme

Due to the extensive application prospects on wastewater treatment and new energy development, microbial fuel cells (MFCs) have gained more and more attention by many scholars all over the world. The bioelectrochemical reaction in MFC system is highly complex, serious nonlinear and time-delay dynamic process, in which the optimal control of electrochemical parameters is still a considerable challenge. A new optimal control scheme for MFC system which combines proportional integral derivative (PID) controller with parameters fuzzy optional algorithm and cerebellar model articulation controller (CMAC) neural network was proposed. The simulation results demonstrate that the proposed control scheme has rapider response, better control effect and stronger anti-interference ability than Fuzzy PID controller by taking constant voltage output of MFC under the different load disturbances as example.

Based on the BP Neural Network-PID Series Control Boiler Main-Steam Temperature System Research

2011 ◽  
Vol 354-355 ◽  
pp. 968-973 ◽  
Author(s):  
Wen Zhu ◽  
Jian Ping Sun
Keyword(s):  
Neural Network ◽  
Control Strategy ◽  
Bp Neural Network ◽  
Pid Controller ◽  
Cascade Control ◽  
Steam Temperature ◽  
Control Effect ◽  
Real Time System ◽  
Main Steam ◽  
Neural Network Pid

Due to the boiler main-steam temperature system exists more serious characteristics,such as much capacitive,nonlinear,time-varying and lag, so adopt cascade control strategy. This paper design a control algorithm which is based on BP neural network, it can accelerate the regulating time, and combined with the conventional PID controller, constitute the BP neural network - PID cascade control strategy. This control strategy not only contain the BP neural network control in real time system strong anti-interference ability characteristic, but also fully utilize the PID controller response speed characteristic. The simulation results show that based on the BP neural network - PID series control boiler main-steam temperature system can achieve satisfactory control effect.

Sign in / Sign up

Export Citation Format

Share Document