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

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

2000 ◽  
Author(s):  
Mohammad R. Solemani ◽  
Michel Guillot
Keyword(s):  
Neural Network ◽  
Multilayer Perceptron ◽  
Operating Conditions ◽  
Machining Processes ◽  
Workpiece Material ◽  
Control Scheme ◽  
Organization Capacity ◽  
First Results ◽  
On Line ◽  
Neuro Controller

Abstract 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 feedforward 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.

First results of an on-line adaptive optics system with atmospheric wavefront sensing by an artificial neural network

1992 ◽  
Vol 390 ◽  
pp. L41 ◽  
Author(s):  
M. Lloyd-Hart ◽  
P. Wizinowich ◽  
B. McLeod ◽  
D. Wittman ◽  
D. Colucci ◽  
...  
Keyword(s):  
Neural Network ◽  
Artificial Neural Network ◽  
Adaptive Optics ◽  
Wavefront Sensing ◽  
First Results ◽  
On Line ◽  
Artificial Neural ◽  
Adaptive Optics System

Indirect Neural Network Adaptive Robust Control of Linear Motor Drive System

2002 ◽  
Author(s):  
J. Q. Gong ◽  
Bin Yao
Keyword(s):  
Neural Network ◽  
Robust Control ◽  
Tracking Error ◽  
Linear Motor ◽  
Adaptive Robust Control ◽  
Operating Conditions ◽  
Tracking Performance ◽  
Motor Drive ◽  
Output Tracking ◽  
On Line

In this paper, an indirect neural network adaptive robust control (INNARC) scheme is developed for the precision motion control of linear motor drive systems. The proposed INNARC achieves not only good output tracking performance but also excellent identifications of unknown nonlinear forces in system for secondary purposes such as prognostics and machine health monitoring. Such dual objectives are accomplished through the complete separation of unknown nonlinearity estimation via neural networks and the design of baseline adaptive robust control (ARC) law for output tracking performance. Specifically, recurrent neural network (NN) structure with NN weights tuned on-line is employed to approximate various unknown nonlinear forces of the system having unknown forms to adapt to various operating conditions. The design is actual system dynamics based, which makes the resulting on-line weight tuning law much more robust and accurate than those in the tracking error dynamics based direct NNARC designs in implementation. With a controlled learning process achieved through projection type weights adaptation laws, certain robust control terms are constructed to attenuate the effect of possibly large transient modelling error for a theoretically guaranteed robust output tracking performance in general. Experimental results are obtained to verify the effectiveness of the proposed INNARC strategy. For example, for a typical point-to-point movement, with a measurement resolution level of ±1μm, the output tracking error during the entire execution period is within ±5μm and mainly stays within ±2μm showing excellent output tracking performance. At the same time, the outputs of NNs approximate the unknown forces very well allowing the estimates to be used for secondary purposes such as prognostics.

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–based improved active and reactive power control of wind-driven double fed induction generator under varying operating conditions

2018 ◽  
Vol 42 (5) ◽  
pp. 381-396 ◽  
Author(s):  
Debirupa Hore ◽  
Runumi Sarma
Keyword(s):  
Neural Network ◽  
Artificial Neural Network ◽  
Reactive Power ◽  
Active Power ◽  
Operating Conditions ◽  
Induction Generator ◽  
Active And Reactive Power ◽  
Control Scheme ◽  
Artificial Neural ◽  
Double Fed Induction Generator

Artificial neural network–based power controllers are trained using back propagation algorithm for controlling the active and reactive power of a wind-driven double fed induction generator under varying wind speed conditions and fault conditions. Vector control scheme is used for control of the double fed induction generator. Here stator flux–oriented vector control scheme is implemented for the rotor side converter and grid voltage vector scheme is used for control of grid side converter using tuned proportional–integral active and reactive power controllers, which is later replaced by artificial neural network–based controllers. The artificial neural network controllers are trained using the data obtained from simulation of conventional proportional–integral controllers under varying operating conditions. The intelligent controller makes the generated stator active power to track the reference active power more precisely at specified power factor in both sub-synchronous and super-synchronous modes of operations. Simulation results reveal that the neural network–based controller significantly improves the performance of variable speed wind power generating double fed induction generator under various conditions.

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.

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.

Modeling the S-N Curves of Polyamide PA66 Using a Serial Hybrid Neural Network

2011 ◽  
Vol 133 (3) ◽  
Author(s):  
Jernej Klemenc ◽  
Andrej Wagner ◽  
Matija Fajdiga
Keyword(s):  
Neural Network ◽  
Analytical Model ◽  
Multilayer Perceptron ◽  
Hybrid Approach ◽  
Theoretical Background ◽  
Operating Conditions ◽  
Hybrid Neural Network ◽  
The Core ◽  
Input Parameters ◽  
Material State

The fatigue damage to polymers generally depends on the material properties as well as on the mechanical, thermal, chemical, and other environmental influences. In this article, a methodology for modeling the dependence of the PA66 S-N curves on the material parameters, the material state, and the operating conditions is presented. The core of the presented methodology is a multilayer perceptron neural network combined with an analytical model of the PA66 S-N curve. Such a hybrid approach simultaneously utilizes the good approximation capabilities of the multilayer perceptron and knowledge of the phenomenon under consideration, because the analytical model for the S-N curves was estimated on the basis of the existing experimental data from the literature. The article presents the theoretical background of the applied methodology. The applicability and uncertainty of the presented methodology were assessed for the available data from the literature. The results show that it was possible to approximate the PA66 S-N curves for different input parameters if the space of the input parameters was adequately covered by the corresponding S-N curves.

A New Adaptive Control Scheme Using Dynamic Neural Networks

2008 ◽  
Vol 20 (1) ◽  
pp. 171-177 ◽  
Author(s):  
Khaled Nouri ◽  
◽  
Rached Dhaouadi ◽  
Naceur Benhadj Braiek ◽  
Keyword(s):  
Neural Network ◽  
Adaptive Control ◽  
Inverse Dynamics ◽  
Drive System ◽  
Motor Drive ◽  
Dynamic Neural Networks ◽  
The Neural Network ◽  
Control Scheme ◽  
On Line ◽  
Motor Drive System

A new adaptive neuro-control structure is proposed for the speed control of a nonlinear motor drive system and the compensation of the nonlinearities. A dynamic artificial neural network is used for the on-line adaptive control of the nonlinear motor drive system with high static and Coulomb friction. The neural network is first trained off-line to learn the inverse dynamics of the motor drive system using a layer decoupled extended Kalman filter algorithm. The proposed control scheme is validated experimentally on a dc motor drive system using a standard personal computer. The results obtained confirm the excellent tracking performance and disturbance rejection properties of the system.

Sign in / Sign up

Export Citation Format

Share Document