Scopus İndeksli Yayınlar Koleksiyonu / Scopus Indexed Publications Collection

Permanent URI for this collectionhttps://hdl.handle.net/11147/7148

Browse

Filters

20253

Settings

Start date: 2025Department: search.filters.department.İzmir Institute of Technology. Mechanical Engineering

Search Results

Now showing 1 - 3 of 3
  • Conference Object
    A Comparative Study of Attention-Augmented YOLO Architectures for Defect Detection in Fused Deposition Modelling
    (Institute of Electrical and Electronics Engineers Inc., 2025) Cezayirli, H.; Tetik, H.; Dede, M.I.C.; Phone, W.L.; Alkan, B.
    Additive manufacturing (AM), particularly fused deposition modelling (FDM), facilitates the fabrication of complex geometries with increasing flexibility and efficiency. Ensuring consistent print quality in FDM processes necessitates the development of accurate defect detection mechanisms. Attention-augmented YOLO (You Only Look Once) models have emerged as a promising solution for addressing this challenge. In this study, we systematically benchmark and evaluate the performance of YOLO architectures enhanced with attention mechanisms within the context of FDM 3D printing applications. The models were trained and evaluated using representative defect datasets. The attention-augmented models demonstrate improved detection performance. © 2025 IEEE.
  • Conference Object
    Redundancy resolution options for the twin-it-romans robotic hybrid manufacturing system
    (Springer Science and Business Media B.V., 2025) Gündüz, G.M.; Dede, Mehmet İsmet Can; Kiper, Gökhan; Schmitz, M.; Corves, B.
    The Twinnig Iztech in Robotics Manufacturing System (TWIN-IT-ROMANS) project funded by EU Horizon -Widera-2023-Access-02-01 aims to develop a hybrid manufacturing system that can perform additive and subtractive manufacturing processes and inline quality control using a robotic system. The system will incorporate a 6-degree-of-freedom robot arm and a positioner with 2-degree-of-freedom, which will operate synchronously. This manipulation system is to be designed for performing different manufacturing operations with different degrees-of-freedom requirements. In order to reveal alternative trajectory planning scenarios for this system, this paper presents an initial review of redundancy resolution approaches for kinematically redundant robotic manipulators. First, the four main approaches for redundancy resolution techniques are introduced. Then main studies on energy minimization and stiffness maximization for kinematically redundant robotic manipulators are reviewed. Similar or new approaches are planned to be generated and implemented for the redundant system for hybrid manufacturing. © The Author(s), under exclusive license to Springer Nature Switzerland AG 2025.
  • Article
    Enhancing trajectory-tracking accuracy of high-acceleration parallel robots by predicting compliant displacements
    (Cambridge University Press, 2025) Paksoy, Erkan; Dede, Mehmet Ismet Can; Kiper, Gokhan
    For precision-required robot operations, the robot's positioning accuracy, repeatability, and stiffness characteristics should be considered. If the mechanism has the desired repeatability performance, a kinematic calibration process can enhance the positioning accuracy. However, for robot operations where high accelerations are needed, the compliance characteristics of the mechanism affect the trajectory-tracking accuracy adversely. In this paper, a novel approach is proposed to enhance the trajectory-tracking accuracy of a robot operating at high accelerations by predicting the compliant displacements when there is no physical contact of the robot with its environment. Also, this case study compares the trajectory-tracking characteristics of an over-constrained and a normal-constrained 2degrees-of-freedom (DoF) planar parallel mechanism during high-acceleration operations up to 5 g accelerations. In addition, the influence of the end-effector's center of mass (CoM) position along the normal of the plane is investigated in terms of its effects on the proposed trajectory-enhancing algorithm.