Yazar "Adar, Nurettin Gokhan" seçeneğine göre listele

Listeleniyor 1 - 6 / 6
  • Küçük Resim Yok
    Öğe
    A Fault Detection Robotic Cell Application Based on Deep Learning and Image Processing Hybrid Approach for Quality Control of Automotive Parts
    (Springer Int Publ Ag, 2025) Kir, Hilal; Adar, Nurettin Gokhan; Yazar, Mustafa
    In this study, the development of a robotic cell that combines deep learning and image processing hybrid approach has been addressed in order to increase the accuracy and efficiency of the quality control of automotive parts. In the automotive industry, manual quality control processes performed by operators are susceptible to errors and inaccuracies, leading to the passage of faulty parts and subsequent inefficiencies, wasted time, and increased costs. To overcome these challenges, this study introduces a fault detection robotic cell that combines deep learning and image processing techniques for quality control of automotive parts at Sahinkul Machine Spare Parts Manuf. Ltd. Co.. The robotic cell uses image processing to inspect geometric tolerances, including hole diameter, part geometry and the presence of holes. However, the complex geometry of bolt threads requires the use of the YOLOv5 deep learning algorithm to assess their quality. A dataset consisting of 3500 bolt thread images was collected for training and validation, with 2800 images used for training, 350 for validation, and the remaining 350 for testing purposes. The experimental results show that the fault detection robotic workcell achieves an approximate success rate of 97.4% in inspecting the quality of the selected parts. By combining deep learning and image processing, this study provides a reliable solution to improve the accuracy and efficiency of quality control processes in the automotive industry.
  • Küçük Resim Yok
    Öğe
    Artificial intelligence-based stress prediction in glass fiber reinforced composites
    (Korean Soc Mechanical Engineers, 2025) Ferati, Kajs; Adar, Nurettin Gokhan
    This study addresses the challenge of predicting stress values in glass fibre reinforced epoxy composites under tensile loading using advanced AI methods. Traditional experimental and finite element analysis (FEA) approaches are time consuming and costly. To overcome this, a dataset was generated from FEA simulations covering different lamination sequences and material properties. Three AI models-narrow neural network (NNN), squared exponential Gaussian process regression (GPR) and support vector machine (SVM)-were developed and evaluated. GPR and SVM achieved superior prediction accuracies of 96.83 % and 95.04 %, respectively, outperforming NNN. Experimental validation confirmed these results and demonstrated the robustness of the proposed models. This study provides a cost-effective framework for stress prediction in composites that reduces the reliance on extensive testing and simulation, and advances AI-driven solutions for materials design and analysis.
  • Küçük Resim Yok
    Öğe
    Convolutional Neural Network Based Hand Gesture Recognition in Sophisticated Background for Humanoid Robot Control
    (Zarka Private Univ, 2023) Yildiz, Ali; Adar, Nurettin Gokhan; Mert, Ahmet
    Hand gesture recognition is a preferred way for human-robot interactions. Conventional approaches are generally based on image processing and recognition of hand poses with simple backgrounds. In this paper, we propose deep learning models, and humanoid robot integration for offline and online (real-time) recognition and control using hand gestures. One thousand and two hundred of hand images belonging to four participants are collected to construct the hand gesture database. Five class (forward, backward, right, left and stop) images in six sophisticated backgrounds with different illumination levels are obtained for four participants, and then one participant's images are kept as testing data. A lightweight Convolutional Neural Network (CNN), and transfer learning techniques using VGG16, and Mobilenetv2 are performed on this database to evaluate user independent performance of the hand gesture system. After offline training, real-time implementation is designed using a mobile phone (Wi-Fi and camera), Wi-Fi router, computer with embedded deep learning algorithms, and NAO humanoid robot. Streamed video by the mobile phone is processed and recognized using the proposed deep algorithm in the computer, and then command is transferred to robot via TCP/IP protocol. Thus, the NAO humanoid robot control using hand gesture in RGB and HSV color spaces is evaluated in sophisticated background, and the implementation of the system is presented. In our simulations, 95% and 100% accuracy rates are yielded for the lightweight CNN, and transfer learning, respectively.
  • Küçük Resim Yok
    Öğe
    Detailed Kinematic Analysis and Real-Time Application of the 4-DOF Low Cost Robotic Arm
    (Ieee, 2019) Beyhan, Ayberk; Adar, Nurettin Gokhan
    In this study, real-time position control of the robotic arm has been implemented. For this purpose, an experimental setup was designed and installed for low cost 4-DOF robotic arm. Servo motors are used for the movement of each joint of the robotic arm. Kinematic equations have been obtained for the control of the robot. Inverse kinematic equations have been obtained for the robot to move to the desired position in the Cartesian space. The inverse kinematic equations were used to calculate the angle values required from x-y-z position coordinates. These angles were used to control the motors. The angular position obtained from the encoders of servo motors were obtained by using x-y-z position information in forward kinematic equations. wrist roll angle was defined so that the last link can reach the target at the desired angle. Real-time implementation of the proposed method is carried out using Matlab. The results are given in graphs and tables.
  • Küçük Resim Yok
    Öğe
    Editorial: Vibration-based robot locomotion
    (Frontiers Media Sa, 2024) Reis, Murat; Cocuzza, Silvio; Doria, Alberto; Adar, Nurettin Gokhan
    [Abstract Not Available]
  • Küçük Resim Yok
    Öğe
    Modeling and real-time cartesian impedance control of 3-DOF robotic arm in contact with the surface
    (Sharif Univ Technology, 2024) Beyhan, Ayberk; Adar, Nurettin Gokhan
    Robotic arms have become increasingly popular and widely used in various industrial applications. However, conventional control methods are not capable of adequately controlling a robotic arm in tasks that require contact with a surface. To address this issue, this study proposes a Cartesian impedance control method to control a 3-DOF robotic arm in real-time during contact with a surface. The proposed controller consists of two control loops: an inner loop and an outer loop. The inner loop utilizes a motion control method in the joint space, with the parameters of the controller being calculated through system identification. The outer loop implements Cartesian impedance control in the Cartesian space using a mass-spring-damper model. The coefficients of the Cartesian impedance control were determined based on the over-damped response with real-time applications. By selecting the inner loop in the joint space and the outer loop in the Cartesian space, the control of the robotic arm is guaranteed. The proposed method was tested in real-time, and its performance was compared with the PTD with gravity compensation control in the Cartesian space. The results indicated that the proposed method was able to successfully follow reference trajectories and reduce the contact force. (c) 2024 Sharif University of Technology. All rights reserved.