Publications Scientifiques

Permanent URI for this communityhttps://dspace.univ-boumerdes.dz/handle/123456789/10

Browse

Subject: search.filters.subject.Meta-heuristic algorithms

Search Results

Now showing 1 - 3 of 3
  • No Thumbnail Available
    Item
    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.
  • No Thumbnail Available
    Item
    An enhanced battery model using a hybrid genetic algorithm and particle swarm optimization
    (Springer Nature, 2023) Mammeri, Elhachemi; Ahriche, Aimad; Necaibia, Ammar; Bouraiou, Ahmed; Mekhilef, Saad; Dabou, Rachid; Ziane, Abderrezzaq
    Batteries are widely used for energy storage in stand-alone PV systems. However, both PV modules and batteries exhibit nonlinear behavior. Therefore, battery modeling is an essential step toward appropriate battery control and overall PV system management. Empirical models remain reliable for lead-acid batteries, especially the Copetti model, which describes many inner and outer battery phenomena, including temperature dependency. However, the parameters of the Copetti model require further adjustment to increase its ability to accurately represent battery behavior. Recently, metaheuristic algorithms have been employed for parameter identification, especially hybrid algorithms that combine the advantages of two or more algorithms. This paper proposes an enhanced battery model based on the Copetti model. The parameter identification of the enhanced model has been carried out using a novel hybrid PSO-GA algorithm (HPGA). The hybrid algorithm combines GA and PSO in a cascade configuration, with GA as the master algorithm. The HPGA algorithm has been compared with other algorithms, namely GA, PSO, ABC, COA, and a hybrid GWO-COA, to reveal its advantages and disadvantages. The NRMSE is used to evaluate algorithms in terms of tracking speed and efficiency. HPGA shows an improvement in tracking efficiency compared to GA and PSO. The proposed model is validated on several charging-discharging data and exhibits a 15% lower mean error compared to the Copetti model with original parameters. Additionally, the proposed model demonstrates a lower mean error of 0.16% compared to other models in the literature with a 0.36% mean error at least.
  • No Thumbnail Available
    Item
    Hybrid soft computational approaches for modeling the maximum ultimate bond strength between the corroded steel reinforcement and surrounding concrete
    (Springer, 2020) Ben Seghier, Mohamed El Amine; Ouaer, Hocine; Ghriga, Mohammed Abdelfetah; Nait Amar, Menad; Duc-Kien, Thai
    The capacity efficiency of load carrying with the accurate serviceability performances of reinforced concrete (RC) structure is an important aspect, which is mainly dependent on the values of the ultimate bond strength between the corroded steel reinforcements and the surrounding concrete. Therefore, the precise determination of the ultimate bond strength degradation is of paramount importance for maintaining the safety levels of RC structures affected by corrosion. In this regard, hybrid intelligence and machine learning techniques are proposed to build a new framework to predict the ultimate bond strength in between the corroded steel reinforcements and the surrounding concrete. The proposed computational techniques include the multilayer perceptron (MLP), the radial basis function neural network and the genetic expression programming methods. In addition to that, the Levenberg–Marquardt (LM) deterministic approach and two meta-heuristic optimization approaches, namely the artificial bee colony algorithm and the particle swarm optimization algorithm, are employed in order to guarantee an optimum selection of the hyper-parameters of the proposed techniques. The latter were implemented based on an experimental published database consisted of 218 experimental tests, which cover various factors related to the ultimate bond strength, such as compressive strength of the concrete, concrete cover, the type steel, steel bar diameter, length of the bond and the level of corrosion. Based on their performance evaluation through several statistical assessment tools, the proposed models were shown to predict the ultimate bond strength accurately; outperforming the existing hybrid artificial intelligence models developed based on the same collected database. More precisely, the MLP-LM model was, by far, the best model with a determination coefficient (R2) as high as 0.97 and 0.96 for the training and the overall data, respectively.