Publications Internationales

Now showing 1 - 4 of 4

Optimal design of wireless power transfer coils for biomedical implants using machine learning and meta-heuristic algorithms
(Springer Nature, 2024) Bennia, Fatima; Boudouda, Aimad; Nafa, Fares
The classical methods for optimizing wireless power transfer (WPT) systems using mathematical equations or finite element methods can be time-consuming and may only sometimes yield optimal designs. In order to overcome this challenge, this paper introduces a novel approach integrating machine learning techniques with meta-heuristic methods to design and optimize a miniaturized, high-efficiency WPT receiving coil for biomedical applications. The objective is to achieve dimensions below 20 mm, a depth of 30 mm within the tissue, and a frequency of 13.56 MHz. Our approach leverages a neural network (NN) model to predict efficiency based on geometric coil parameters, eliminating the need for complex equations. The NN was trained on a dataset generated via finite element method simulations. We employ two meta-heuristic algorithms, the genetic algorithm and the coyote optimization method, to find optimal parameters that maximize efficiency. Our NN model demonstrates exceptional accuracy, exceeding 97%. Furthermore, the proposed WPT coil design approach enhances transfer efficiency by up to 76%, significantly reducing computation time compared to classical methods. Finally, we validate our results using finite element simulation with Ansys Maxwell 3D.
Real-Time Reduction of rotor position estimation error based on the stator flux Estimation-Combined method for sensorless control of PMSMs drives
(Praise Worthy Prize S.r.l, 2021) Aibeche, Abderrezak; Akroum, Hamza; Boudouda, Aimad; Kidouche, Madjid; Doghmane, Mohamed Zinelabidine
This paper presents the implantation and the performance improvement of real-time reduction of rotor position estimation error based on the stator flux estimation-combined method for sensorless control of PMSMs drives. Wherein, the proposed method is designed based on a simple algorithm for accurate estimation and robust control of quasi-exact stator flux and position/speed of PMSMs. A large-speed range of applications in sensorless control strategies is achieved by using the mathematical model of PMSM motor. The latter presents the main idea of the estimators’ structures design. They are generally composed of voltage and current models (VM and CM). However, the dynamic performances of these methods are influenced in the low and high-speed ranges, and they are sensitive to parameters variations. The estimators’ structures are dominated by the current model at the low-speed range, and by the voltage model at the high-speed range. The technique proposed in this study is the combination of the two preceding models; this provides performances’ improvement in the PMSM dynamics for a large speed variation with compensating estimation errors for the two separate methods (VM and CM). The main objective of this combined method is the drawback reduction for the separate use of VM and CM estimators. The algorithm principle is based on exploiting and combining the two estimators while measuring the stator voltages and the currents, in addition to estimating the rotor position and the speed. Furthermore, the performances of the proposed method have been tested and validated through real-time experiments by using dSPACE ds 1104 DSP board
Robust decoupled adaptive fuzzy sliding mode control for a class of underactuated mechanical systems
(Levrotto and Bella, 2021) Nafa, Fares; Boudouda, Aimad; Smaani, Billel
Nowadays, Underactuated Mechanical Systems (UMS) remain an interesting research field for control laws development. This work deals with the design of an adaptive controller on the basis of Sliding Mode Control (SMC) and the universal approximation property of Fuzzy Systems (FS) for a classe of second order UMS two Degrees of Freedom (DOF). We first design an SMC law to force a coupled sliding urface to be reached in finite time. Second, by considering model uncertainties, fuzzy systems are then introduced to approximate the unknown controller. The adjustable parameters are updated by using gradient descent method. Through the stability analysis for both cases, it is shown that the system converges asymptotically to its equilbrium points in finite time. To demonstrate the validity and the performance of the proposed methods, an appropriate numerical application to an overhead crane systems is presented
Spectral analysis of switch voltage for dual randomized PWM DC-DC converters operating in DCM
(Taylor and Francis, 2021) Boudouda, Aimad; Bouzida, Ahcene; Nafa, Fares
This paper addresses the spectral characteristics of a dual randomised pulse width modulation scheme (RCFM-RPPM) for reducing conducted EMI in the basic DC-DC converters (buck, boost, and buck-boost) operating in discontinuous conduction mode (DCM). It combines two simple schemes, random carrier frequency modulation (RCFM), and a random pulse position (RPPM). First, the modulating principle of the dual randomised PWM is presented. Then, a mathematical model of power spectral density (PSD) that characterises the switch voltage of the three basic DC-DC converters is derived. The mathematical model is validated by simulation of a buck converter operating in DCM. Analytical and simulation results show the effectiveness of PSD spreading of the dual randomised scheme compare to the simple randomised schemes. Moreover, the PSD analysis is confirmed by FFT (Fast Fourier Transform) analysis of the switch voltage. Finally, the effect of randomness levels on the PSD spreading is studied

Publications Internationales

Browse

Filters

Settings

Sort By

Results per page

Search Results