Yazar "Ozcan, Ahmet Remzi" seçeneğine göre listele

Listeleniyor 1 - 4 / 4
  • Küçük Resim Yok
    Öğe
    A new neural network-assisted hybrid chaotic hiking optimization algorithm for optimal design of engineering components
    (Walter De Gruyter Gmbh, 2025) Ozcan, Ahmet Remzi; Mehta, Pranav; Sait, Sadiq M.; Gurses, Dildar; Yildiz, Ali Riza
    In the era of artificial intelligence (AI), optimization and parametric studies of engineering and structural systems have become feasible tasks. AI and ML (machine learning) offer advantages over classical optimization techniques, which often face challenges such as slower convergence, difficulty handling multiobjective functions, and high computational time. Modern AI and ML techniques may not effectively address all critical design engineering problems despite these advancements. Nature-inspired algorithms based on physical phenomena in nature, human behavior, swarm intelligence, and evolutionary principles present a viable alternative for multidisciplinary design optimization challenges. This article explores the optimization of various engineering problems using a newly developed modified hiking optimization algorithm (HOA). The algorithm is inspired by human hiking techniques, such as hill climbing and hiker speed. The advantages of the modified HOA are compared with those of several famous algorithms from the literature, demonstrating superior results in terms of statistical measures.
  • Küçük Resim Yok
    Öğe
    Lightweight design of lattice-embedded brake pedals using artificial intelligence -based optimization
    (Walter De Gruyter Gmbh, 2026) Kurt, Enes; Yildiz, Ali Riza; Inkaya, Tulin; Ozcan, Ahmet Remzi; Gokdag, Istemihan
    The application of lattice structures has become increasingly important in designing complex components due to additive manufacturing (AM) advancements. Various types and design parameters of lattice structures allow weight reduction while maintaining the required strength and improving mechanical properties, with the strength varying based on these parameters. One common approach to calculating this strength is by using software solvers like SimSolid, which employs the meshless analysis solution (MAS). Considering the variety of parameters, the complexity of lattice structures, and the computational difficulties in analysis methods, identifying the optimal lattice structure for a design is highly challenging. To overcome this challenge, artificial neural networks (ANNs) are integrated into the optimization algorithm used in this study. The training data for the ANN are obtained from the analysis results of the designs generated using the design parameters selected by the Latin hypercube sampling (LHS) method. The ANNs integrated non-dominated sorting genetic algorithm II (NSGA-II) optimization algorithm is used to minimize the mass while ensuring the strength of the material by keeping the maximum stress within the permissible limits. The method is applied to the weight reduction of the brake pedal, approximately 26.96 % is achieved while maintaining the required strength under existing conditions.
  • Küçük Resim Yok
    Öğe
    Multi-objective optimization of aluminum foam-filled battery boxes for electric vehicle safety
    (Latin Amer J Solids Structures, 2025) Yay, Ismail; Demirci, Emre; Ozcan, Ahmet Remzi
    In this study, a multi-objective optimization methodology is used to assess the crashworthiness of an aluminum foam-filled battery box designed for passenger cars. Unlike most research focusing on axial crushing, this work investigates the less-explored side pole impact scenario in electric vehicle battery boxes. Finite element simulations are conducted to reduce peak crushing force (PCF) and increase specific energy absorption (SEA) compared to the initial design. Key design variables include aluminum foam densities, wall thickness, and cross-sectional dimensions of battery box components. Four surrogate models are evaluated to approximate the simulation results, and the Non-Dominated Sorting Genetic Algorithm (NSGA-II) is employed to achieve optimal outcomes. The results show that the optimized design significantly improves crashworthiness, achieving a 50.71% increase in SEA and an 11.56% reduction in PCF. Foam density plays a crucial role in controlling deformation behavior under impact conditions. These findings offer a new approach to designing battery boxes with enhanced crashworthiness for electric vehicles.
  • Küçük Resim Yok
    Öğe
    Optimal design of a robot gripper arm using the chaotic animated oat optimizer
    (Walter De Gruyter Gmbh, 2026) Ozcan, Ahmet Remzi; Demirci, Emre; Mehta, Pranav; Yildiz, Ali Riza
    This study presents a modified version of the Animated Oat Algorithm (AOA), enhanced through the integration of chaotic maps, termed the Chaotic Animated Oat Algorithm (CAOA). Inspired by the seed dispersal mechanisms of the oat plant, AOA offers a population-based metaheuristic framework suitable for complex global optimization tasks. The proposed CAOA was evaluated across four real-world engineering optimization problems: pressure vessel design, bolted rim coupling, gear train cost minimization, and robot gripper arm weight reduction. Results demonstrate that CAOA consistently outperforms traditional and state-of-the-art metaheuristics in terms of solution quality, convergence stability, and robustness, affirming its potential for widespread engineering applications.