Yazar "Yildiz, Ali Riza" seçeneğine göre listele

Listeleniyor 1 - 8 / 8
  • 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
    An investigation of the crash performance of magnesium, aluminum and advanced high strength steels and different cross-sections for vehicle thin walled energy absorbers
    (Carl Hanser Verlag, 2018) Demirci, Emre; Yildiz, Ali Riza
    In this paper, the effect of conventional steel, new generation DP-TRIP steels, AA7108 - AA7003 aluminum alloys, AM60 - AZ31 magnesium alloys and crash-box cross-sections on crash performance of thin-walled energy absorbers are investigated numerically for the lightweight design of vehicle structures. According to finite element analysis results, crash performance parameters such as total energy absorption, specific energy absorption, reaction forces and crush force efficiencies are compared for the above-mentioned materials. The energy absorption capability of steel energy absorbers is better than that of aluminum and magnesium absorbers. On the other hand, the energy absorption capacity per unit mass of energy absorbers made from lightweight materials is higher than that of steel energy absorbers. This advantage of lightweight alloys encourages automobile manufacturers to use them in designing structural vehicle components.
  • Küçük Resim Yok
    Öğe
    Development of Seam Tracking Sensor in ROS Environment
    (Institute of Electrical and Electronics Engineers Inc., 2025) Yildiz, Ali Riza; Adar, Nurettin Gökhan
    Seam tracking sensors are critical for improving the accuracy and adaptability of robotic welding systems. In this study, a vision-based seam tracking sensor was developed and simulated entirely within the Robot Operating System (ROS) and Gazebo environment. A structured light sensor, consisting of a line laser and a camera, was modeled to detect weld seam positions through laser triangulation. Real-time image processing algorithms were implemented to extract seam coordinates, while trajectory planning and motion control modules enabled the Cartesian robot to dynamically adjust its path during operation. The developed system architecture ensured synchronized communication between sensor data acquisition and robot control layers. Simulation results demonstrate that the proposed system achieves accurate and responsive seam tracking under varying seam deviations. The study highlights the potential of simulation-driven development for validating sensor designs and control strategies in a risk-free and cost-effective manner before physical deployment. © 2025 IEEE.
  • Küçük Resim Yok
    Öğe
    Experimental and numerical investigation of crashworthiness performance for optimal automobile structures using response surface methodology and oppositional based learning differential evolution algorithm
    (Walter De Gruyter Gmbh, 2023) Yildirim, Ahmet; Demirci, Emre; Karagoz, Selcuk; Ozcan, Sevket; Yildiz, Ali Riza
    In this study, experimental and numerical crash analyses are carried out to reach an optimum bumper beam and energy absorber design for a passenger car. Design parameters have been created to determine the most crash-efficient bumper beam and energy absorber models. The models that are formed by using Taguchi tables are subjected to crash analysis, and the responses are obtained to find an optimal design. Response surface methodology is used to approximate the structural responses in crash analysis, and the optimum bumper beam and energy absorber models are obtained by the differential evolution algorithm. The optimum model is subjected to crash analysis in the Hyperform software without considering the sheet metal forming effect. Besides, the model is analyzed by incorporating forming history into the crash analysis. As a result of the numerical analysis, a new energy absorber and bumper beam model with the better crash performance and weight reduction are obtained.
  • Küçük Resim Yok
    Öğe
    GBRUN: A Gradient Search-based Binary Runge Kutta Optimizer for Feature Selection
    (Library & Information Center, Nat Dong Hwa Univ, 2024) Dou, Zhi-Chao; Chu, Shu-Chuan; Zhuang, Zhongjie; Yildiz, Ali Riza; Pan, Jeng-Shyang
    Feature selection (FS) is a pre-processing technique for data dimensionality reduction in machine learning and data mining algorithms. FS technique reduces the number of features and improves the model generalization ability. This study presents a Gradient Search-based Binary Runge Kutta Optimizer (GBRUN) for solving the FS problem of high-dimensional. First, the proposed method converts the continuous Runge Kutta optimizer (RUN) into a binary version through S-, V-, and U-shaped transfer functions. Second, a gradient search method is introduced to improve the exploration capability of the algorithm. Five standard performance of the GBRUN algorithm. The experimental results show that GBRUN has better performance than in this manuscript, using the GBRUN algorithm to select algorithms have better performance than other algorithms.
  • 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
    Minimization of release bearing load loss in a clutch system for high-speed rotations using the differential evolution algorithm
    (Walter De Gruyter Gmbh, 2022) Karaduman, Alper; Lekesiz, Huseyin; Yildiz, Ali Riza
    Diaphragm spring is a critical part of a clutch system because it affects the release bearing load characteristics directly and that determines the quality of disengagement. Bearing load provides required clamping for coupling however it may vary significantly during the engagement/disengagement process. A significant drop in bearing load may be experienced especially for high engine velocities for certain bearing displacement due to centrifugal forces occurring on the fingertips of diaphragm springs. The falling in release bearing load is undesirable for comfortable driving and clutch performance. This problem has not been addressed clearly in technical literature. In this study, the diaphragm spring for a C-segment passenger car is optimized using a differential evolutionary algorithm, and an optimized diaphragm was manufactured for testing. The load-bearing characteristics of the optimized diaphragm were compared with those of the currently available diaphragm spring. Loss of bearing load occurring in high-speed rotations was significantly reduced for the optimized diaphragm. Parameters influencing the performance were identified using parameter influence analysis, and a robust disengagement behavior was actualized using the optimization process.
  • 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.