MOHAMED DJEMEL - Academia.edu (original) (raw)

Papers by MOHAMED DJEMEL

Pruning approaches for selection of neural networks structure

ABSTRACT Topology design of artificial neural networks (ANNs) is a complex problem. This paper pr... more ABSTRACT Topology design of artificial neural networks (ANNs) is a complex problem. This paper presents a study of some approaches which derived from a pruning technique (OBS). In the first step, we explicit the corresponding algorithms used to determine the adequate number of neurons and weights for neural structure. In the second step, a comparative study of the presented strategies is also investigated according to numerical simulation example.

Statistical and incremental methods for neural models selection

International Journal of Artificial Intelligence and Soft Computing, 2014

ABSTRACT This work presents two methods of selection of neural models for identification of dynam... more ABSTRACT This work presents two methods of selection of neural models for identification of dynamic systems. Initially, a strategy of selection based on statistical tests, which relates to training and generalisation performances of a neural model is analysed. In the second time, a new constructive approach of neural model selection, which the training begins with minimal structure and then incrementally adds new hidden units and/or layers, is described. The simulation and the application of these methods for selection of neural models are also considered.

arXiv (Cornell University), Dec 23, 2015

In this paper, a novel adaptive tuning method of PID neural network (PIDNN) controller for nonlin... more In this paper, a novel adaptive tuning method of PID neural network (PIDNN) controller for nonlinear process is proposed. The method utilizes an improved gradient descent method to adjust PIDNN parameters where the margin stability will be employed to get high tracking performance and robustness with regard to external load disturbance and parameter variation. Simulation results show the effectiveness of the proposed algorithm compared with other well-known learning methods.

Fuzzy predictive control based on Takagi-Sugeno model for nonlinear systems

... National school of engineering of Sfax, PB 1173, 3083 Sfax, Tunisia. dalhoumilatifa@hotmail. ... more ... National school of engineering of Sfax, PB 1173, 3083 Sfax, Tunisia. dalhoumilatifa@hotmail. com Mohamed.Djemel@enis.rnu.tn Mohamed. Chtourou@enis.rnu.tn ... and u(k -nB) is B;'n then yr(k) = -a,ry(kl) -azry(k-2) -... a" ry(k-nA) A +blru(k -1) +bZru(k-2) + ... b" ru(k-nB) (22) A ...

Design and comparison of quadratic boost and double cascade boost converters with boost converter

Basically, the output voltage in renewable energy sources is improved using the boost converter, ... more Basically, the output voltage in renewable energy sources is improved using the boost converter, which is the key part in a photovoltaic chain. In this converter, the switching frequency is limited; hence the output voltage is reduced. To overcome this problem, two topologies are proposed; the quadratic boost converter results by combining the components of two boost converters by using single switch and the double cascade boost results from the association of two identic elementary boost converters connected in tandem. In this proposed paper a comparison of the efficiency of the two proposed converters topologies with boost converter is discussed.

International Journal of Control Automation and Systems, Dec 23, 2016

This paper deals with the control of nonlinear systems using multimodel approach. The main idea o... more This paper deals with the control of nonlinear systems using multimodel approach. The main idea of this work consists on the association of the gap metric and the stability margin tools to reduce the number of models constituting the multimodel bank. In fact, the self-organisation map (SOM) algorithm is used, firstly, to develop a preliminary multimodel bank. Then, the gap metric and the stability margin are computed to determine the redundancy of the initial multimodel bank. So, the multimodel controller is elaborated based on the reduced model bank. Simulations confirm the method for selecting the appropriate number of local models which should be used in the controller design.

Observer based adaptive neuro-sliding mode control for MIMO nonlinear systems

International Journal of Control Automation and Systems, Apr 1, 2010

In this paper, a stable adaptive neural sliding mode controller is developed for a class of multi... more In this paper, a stable adaptive neural sliding mode controller is developed for a class of multivariable uncertain nonlinear systems. For these systems not all state variables are available for measurements. By designing a state observer, adaptive neural systems, which are used to model unknown functions, can be constructed using the state estimations. Based on Lyapunov stability theorem, the proposed

Sur les méthodes de réduction de modèles linéaires : application à la machine synchrone

Journal de physique, May 1, 1996

This paper deals with the reduction of a high-order linear system. To this end, four methods are ... more This paper deals with the reduction of a high-order linear system. To this end, four methods are presented. The first one consists of selecting eigenvalues of a high-order system which will be retained in the aggregated low-order model. This method is based on the determination of the time moments. The second method, called balanced matrix, estimates the degree of the

Zenodo (CERN European Organization for Nuclear Research), Aug 26, 2016

Choosing the training algorithm and determining the architecture of artificial neural networks ar... more Choosing the training algorithm and determining the architecture of artificial neural networks are very important issues with large application. There are no general methods which permit the estimation of the adequate neural networks size. In order to achieve this goal, a pruning algorithm based on the relevancy index of hidden neurons outputs is developed in this paper. The relevancy index depends on the output amplitude of each hidden neuron and estimates his contribution on the learning process. This method is validated with an academic example and it is tested on a wind turbine modeling problem. Compared with two modified versions of Optimal Brain Surgeon (OBS) algorithm, the developed approach gives interesting results.

Indirect Adaptive Neuro-Sliding Mode Control for SISO Nonlinear Systems with State Observer

I-Manager's Journal on Future Engineering and Technology, Jul 15, 2007

International Journal of Computer Applications, 2016

In this paper, three neural control strategies are addressed to a class of single input-single ou... more In this paper, three neural control strategies are addressed to a class of single input-single output (SISO) discrete-time nonlinear systems affected by parametric variations. According to the control scheme, in a first step, a direct neural model (DNM) is developed to emulate the behavior of the system, then an inverse neural model (INM) is synthesized using specialized learning technique and cascaded to the system as a controller. The sliding mode backpropagation algorithm (SM-BP), which presents in a previous study robustness and high speed learning, is adopted for the training of the neural models. However, in the presence of strong parametric variations, the synthesized (INM) shows limitations to present satisfactory tracking performances. In fact, in order to improve the control results, two neural control strategies such as hybrid control and neuro-sliding mode control are proposed in this work. A simulation example is treated to show the effectiveness of the proposed control strategies

Two fuzzy internal model control methods for nonlinear uncertain systems

International Journal of Intelligent Computing and Cybernetics, Jun 12, 2017

Purpose The purpose of this paper is to use the internal model control to deal with nonlinear sta... more Purpose The purpose of this paper is to use the internal model control to deal with nonlinear stable systems affected by parametric uncertainties. Design/methodology/approach The dynamics of a considered system are approximated by a Takagi-Sugeno fuzzy model. The parameters of the fuzzy rules premises are determined manually. However, the parameters of the fuzzy rules conclusions are updated using the descent gradient method under inequality constraints in order to ensure the stability of each local model. In fact, without making these constraints the training algorithm can procure one or several unstable local models even if the desired accuracy in the training step is achieved. The considered robust control approach is the internal model. It is synthesized based on the Takagi-Sugeno fuzzy model. Two control strategies are considered. The first one is based on the parallel distribution compensation principle. It consists in associating an internal model control for each local model. However, for the second strategy, the control law is computed based on the global Takagi-Sugeno fuzzy model. Findings According to the simulation results, the stability of all local models is obtained and the proposed fuzzy internal model control approaches ensure robustness against parametric uncertainties. Originality/value This paper introduces a method for the identification of fuzzy model parameters ensuring the stability of all local models. Using the resulting fuzzy model, two fuzzy internal model control designs are presented.

Analysis of a Quadratic Boost Converter using Sliding Mode Controller

Static converters are the most important part in a photovoltaic chain. These converters assure th... more Static converters are the most important part in a photovoltaic chain. These converters assure the adaptation between the photovoltaic panel and the receiver. Generally, DC-DC converters are used to boost up a low level of DC voltage to a higher DC voltage level. Among the different DC-DC converters, the quadratic boost converter is an interesting topology. In this paper a DC-DC quadratic boost converter is modelled and controlled using sliding mode strategy. Dynamic equations describing the converter are derived and the sliding mode controller is designed. The proposed controller has a two loop control. The inner loop involves a sliding mode control for the input current. The outer loop engages a proportional integral compensator. This compensator is used for producing the current reference value taking the output voltage error as an input. The simulator SABER is used. The simulation results are presented to illustrate the proposed approach.

Design of optimal fuzzy logic controller with genetic algorithms

... REGIM) University of Sfa, ENIS, BP. W, 3038, Sfa, Tunisia. Phone: (21 6-4) 2 74.088, Fax. (2 ... more ... REGIM) University of Sfa, ENIS, BP. W, 3038, Sfa, Tunisia. Phone: (21 6-4) 2 74.088, Fax. (2 I6-4) 2 75.595. Emails: Chokri.Rekik @, enis.rnu.tn, Mohamed.DJEMEL @, enis.rnu.tn, Nabil.Derbel@,ieee.orn. Adel.alimi@,ieee.orz ...

International Journal of Automation and Computing, Apr 19, 2017

This work deals with robust inverse neural control strategy for a class of single-input single-ou... more This work deals with robust inverse neural control strategy for a class of single-input single-output (SISO) discrete-time nonlinear system affected by parametric uncertainties. According to the control scheme, in the first step, a direct neural model (DNM) is used to learn the behavior of the system, then, an inverse neural model (INM) is synthesized using a specialized learning technique and cascaded to the uncertain system as a controller. In previous works, the neural models are trained classically by backpropagation (BP) algorithm. In this work, the sliding mode-backpropagation (SM-BP) algorithm, presenting some important properties such as robustness and speedy learning, is investigated. Moreover, four combinations using classical BP and SM-BP are tested to determine the best configuration for the robust control of uncertain nonlinear systems. Two simulation examples are treated to illustrate the effectiveness of the proposed control strategy.

Neural network adaptive control scheme for nonlinear systems with Lyapunov approach and sliding mode

International Journal of Intelligent Computing and Cybernetics, Aug 24, 2010

ABSTRACT Purpose – The purpose of this paper is to present an adaptive neuro-sliding mode control... more ABSTRACT Purpose – The purpose of this paper is to present an adaptive neuro-sliding mode control scheme for uncertain nonlinear systems with Lyapunov approach. Design/methodology/approach – The paper focuses on neural network (NN) adaptive control for nonlinear systems in the presence of parametric uncertainties. The plant model structure is represented by a NNs system. The essential idea of the online parametric estimation of the plant model is based on a comparison of the measured state with the estimated one. The proposed adaptive neural controller takes advantages of both the sliding mode control and proportional integral (PI) control. The chattering phenomenon is attenuated and robust performances are ensured. Based on Lyapunov stability theorem, the proposed adaptive neural control system can guarantee the stability of the whole closed-loop system and obtain good-tracking performances. Adaptive laws are proposed to adjust the free parameters of the neural models. Findings – Simulation results show that the adaptive neuro-sliding mode control approach works satisfactorily for nonlinear systems in the presence of parametric uncertainties. Originality/value – The proposed adaptive neuro-sliding mode control approach is a mixture of classical neural controller with a supervisory controller. The PI controller is used to attenuate the chattering phenomena. Based on the Lyapunov stability theorem, it is rigorously proved that the stability of the whole closed-loop system is ensured and the tracking performance is achieved.

Robust sliding mode control for nonlinear uncertain discrete-time systems

This paper deals with robust sliding mode control for nonlinear uncertain discrete-time systems. ... more This paper deals with robust sliding mode control for nonlinear uncertain discrete-time systems. The dynamics of a such system are approximated by a model including two parts: the first one is a linear uncertain expression and the second part is a nonlinear static term assimilated to an additive perturbation. Then, a robust sliding mode control is synthesized basing on this model. Finally, two simulation examples are presented to show the validity of the proposed control design.

On the neuro-genetic approach for determining optimal control of a rotary crane

The aim of this paper considers the determination of optimal control trajectories of a complex pr... more The aim of this paper considers the determination of optimal control trajectories of a complex process. The proposed method is based on the decomposition of the system into interconnected subsystems. We consider the cases where subsystems are linear in terms of their state and control vectors. For this reason, a neural network is identified which compute local gains. Genetic algorithms

Decomposition and hierarchical control for discrete complex systems by fuzzy logic controllers

This paper proposes a method to compute sub-optimal control strategies of discrete time large-sca... more This paper proposes a method to compute sub-optimal control strategies of discrete time large-scale non-linear systems by fuzzy logic controllers. The method is based on the principle of decomposition of the global system into inter-connected subsystems. We consider that the non-linearities are located in the interconnections terms. Then, a mixed method of coordination procedure between different subsystems is formulated. So,

Robust pole assignment for the control of uncertain nonlinear discrete-time systems

This paper concerns a robust pole assignment for the control of uncertain discrete-time nonlinear... more This paper concerns a robust pole assignment for the control of uncertain discrete-time nonlinear systems. A composed model of two parts is used to describe the dynamic of the considered system. The first part is linear affected by bounded uncertainties. It is obtained by the nominal system linearization around some operating points. The second part is nonlinear. A robust pole assignment called `pole colouring' is employed for the system control. It is synthesized basing only on the linear uncertain part of the model. Finally, two simulation examples are presented to illustrate the effectiveness of the proposed design method.