Yazar "Tansel, I.N." seçeneğine göre listele

Listeleniyor 1 - 2 / 2
  • Küçük Resim Yok
    Öğe
    Evaluation of the health of riveted joints with active and passive structural health monitoring techniques
    (Elsevier B.V., 2015) Demetgül, Mustafa; Senyurek, Volkan Yusuf; Uyandık, R.; Tansel, I.N.; Yazıcıoğlu, Osman
    Many active and passive structural health monitoring (SHM) techniques have been developed for detection of the defects of plates. Generally, riveted joints hold the plates together and their failure may create accidents. In this study, well known active and passive methods were modified for the evaluation of the health of the riveted joints between the plates. The active method generated Lamb waves and monitored their propagation by using lead zirconate titanate (PZT) disks. The signal was analyzed by using the wavelet transformations. The passive method used the Fiber Bragg Grating (FBG) sensors and evaluated the spectral characteristics of the signals by using Fast Fourier Transformation (FFT). The results indicated that the existing methods designed for the evaluation of the health of individual plates may be used for inspection of riveted joints with software modifications. © 2015 Elsevier Ltd. All rights reserved.
  • Küçük Resim Yok
    Öğe
    Fault diagnosis on material handling system using feature selection and data mining techniques
    (Elsevier B.V., 2014) Demetgül, Mustafa; Yıldız, Kazım; Taşkın, S.; Tansel, I.N.; Yazıcıoğlu, Osman
    The material handling systems are one of the key components of the most modern manufacturing systems. The sensory signals of material handling systems are nonlinear and have unique characteristics. It is very difficult to encode and classify these signals by using multipurpose methods. In this study, performances of multiple generic methods were studied for the diagnostic of the pneumatic systems of the material handling systems. Diffusion Map (DM), Local Linear Embedding (LLE) and AutoEncoder (AE) algorithms were used for future extraction. Encoded signals were classified by using the Gustafson-Kessel (GK) and k-medoids algorithms. The accuracy of the estimations was better than 90% when the LLE was used with GK algorithm. © 2014 Elsevier Ltd. All rights reserved.