Kaddour Najim

Neuro-fuzzy modelling of power plant flue-gas emissions

This paper concerns process modelling using fuzzy neural networks. In distributed logic processors (DLP) the rule base is parameterised. The DLP derivatives required by gradient-based training methods are given, and the recursive prediction error method is used to adjust the model parameters. The power of the approach is illustrated with a modelling example where NOx-emission data from a full-scale fluidised-bed combustion district heating plant are used. The method presented in this paper is general, and can be applied to other complex processes as well.

Forecasting time series with a new architecture for polynomial artificial neural network

Polynomial artificial neural networks (PANN) have been shown to be powerful for forecasting nonlinear time series. The training time is small compared to the time used by other algorithms of artificial neural networks and the capacity to compute relations between the inputs and outputs represented by every term of the polynomial. In this paper a new structure of polynomial is presented that improves the performance of this type of network considering only non-integers exponents. The architecture adaptation uses genetic algorithm (GA) to find the optimal architecture for every example. Some examples of sunspots and chaotic time series are presented.

Multimodal searching technique based on learning automata with continuous input and changing number of actions

This paper describes a multimodal searching technique based on a stochastic automaton. The environment where the automaton operates corresponds to the function to be optimized which is assumed to be unknown function of a single parameter x. The admissible region of x is quantized into N subsets. The environment response is continuous (S-model). The complete set of actions of the automaton is divided into nonempty subsets. The action set is changing from instant to instant and is selected based on a probability distribution. These actions are in turn associated with the discrete values of the parameter x. Convergence and convergence rate results are presented. Simulation results illustrate the performance of this searching technique.

Constrained long-range predictive control based on artificial neural networks

Abstract A long-range predictive control strategy using artificial neural networks ( ANNs) is represented. Both unconstrained and constrained control problems are considered. In this control scheme a recurrent ANN and a multilayer feedforward ANN are used. The recurrent ANN is used as a multi-step ahead predictor. For training this network the backpropagation through the time is used. The control action is provided by the multilayer feedforward ANN which uses the predictions of the output of the process to be controlled. The weights of this ANN are estimated at each control step using a stochastic approximation ( SA) algorithm by minimizing a quadratic control objective which is based on a series of the future predictions and future control actions, and by preventing violations of process constraints. To demonstrate the feasibility and the performance of this control scheme, a continuous biochemical reactor and a fixed bed tubular chemical reactor are chosen as realistic nonlinear case studies. Simulation...

Adaptive predictive control of a grinding circuit

Abstract This paper deals with distributed adaptive generalized predictive control of a grinding circuit. This multivariable system is commonly used in mineral industries for size reduction. It is characterized by time varying dynamics owing to changes in ore properties and operating conditions. The fresh ore feed rate, the water addition rate, the circulating load and the product fineness are respectively selected as control and controlled variables. The parameters of two single input-single output discrete models are identified using a least-squares algorithm, taking into account the requirements for long-term adaptive control. Numerical results have been carried out using a simulator based on phenomenological models derived from mass balance considerations. The adaptive controller is compared to a fixed parameter controller. These results illustrate the self-tuning ability and the continuous adaptivity of the control strategy. They also highlight that adaptive control is particulary suitable for distributed control.

Modelling and learning control of rotary phosphate dryer

The modelling and learning control of a phosphate drying furnace is considered. A mathematical model derived from mass and energy considerations is presented. This model consists of four hyperbolic partial differential equations. The numerical model simulation is performed using the method of characteristics, with the fuel flow and moisture content of the dried phosphate selected as control variables. Despite the external perturbations acting on the drying process, the main control objective is to minimize the fuel consumption and to keep the moisture content of the dried phosphate less than or equal to a certain value, provided that the temperature of the hot air, used as purging gas, equals or exceeds the saturation temperature. This control problem is modelled as the behaviour of a learning automaton in a random environment, subject to mean constraints. Using a reinforcement scheme, the automata update their action probabilities according to the response of the environment, and improve their behaviour ...

GENERALIZED PREDICTIVE CONTROL OF A PULSED LIQUID-LIQUID EXTRACTION COLUMN

This paper deals with the application of a general predictive controller to a pulsed liquid-liquid extraction column. The control purpose is to maintain the column in its optimal behaviour zone in spite or flowrates and physical properties of solvent and solute fluctuations. The complex dynamics of the column is modeled by a low order linear discrete model with time varying parameters which are recursively identified. Based on these estimates, the control policy is adapted on line. The obtained results illustrate the successful application of such an adaptive algorithm.

Open-loop regulation and tracking control based on a genealogical decision tree

The goal of this paper is to design a new control algorithm for open-loop control of complex systems. This control approach is based on a genealogical decision tree for both regulation and tracking control problems. The idea behind this control strategy consists of associating Gaussian distributions to both the norms of the control actions and the tracking errors. This stochastic search model can be interpreted as a simple genetic particle evolution model with a natural birth and death interpretation. It converges on probability. A numerical example dealing with the control of a fluidized bed combustion power plant illustrates the feasibility and the performance of this control algorithm.

Adaptive selection of the optimal order of linear regression models using learning automata

This paper concerns the adaptive selection of the optimal order of linear regression models using a variable-structure stochastic learning automaton. The Alaike criterion is derived for stationary and non-stationary cases, and it is shown that the optimal order minimizes a loss function corresponding to the evaluation of this criterion. The order of the regression model belongs to a finite set. Each order value is associated with an action of the automaton. The Bush-Mosteller reinforcement scheme with normalized automaton input is used to adjust the probability distribution. Simulation results illustrate the feasibility and performance of this model order selection approach

Multivariable learning control of an extractor

Abstract This paper deals with the application of the learning approach to the multivariable control of an extraction pilot plant. This separation process presents a highly nonlinear behaviour and time-varying dynamics. A learning system is composed of three distinct parts. The first part consists of an automation with variable structure whose actions are selected according to a probability distribution associated to the set of actions. An updating scheme (or reinforcement scheme) adapts this probability distribution according to the “good” or “bad” behaviour of the process. The quality of the behaviour is defined on the basis of heuristic rules contained in a performance evaluation unit through information collected in the process (measurements). The pilot plant to be controlled is a pulsed liquid-liquid extraction column. The control strategy involves both the control of the column in its optimal-behaviour zone and the minimization of the solvent flow rate needed to obtain a specific product quality. Previous works have shown that the column could be maintained in its optimal behaviour by means of the regulation of conductivity by action on the pulse frequency. The obtaining of a given product specification can be achieved by the control of the product concentration in the outlet stream by acting on the solvent feed flow rate. Owing to interactions between one variable and another it seems promising to use a two input-two output control scheme. Experimental results are presented which show the feasibility of such an approach for on-line control of a chemical plant.