O
Ozhan Gecgel
Researcher at Texas Tech University
Publications - 14
Citations - 97
Ozhan Gecgel is an academic researcher from Texas Tech University. The author has contributed to research in topics: Condition monitoring & Convolutional neural network. The author has an hindex of 4, co-authored 11 publications receiving 50 citations.
Papers
More filters
Journal ArticleDOI
Uncertainty quantification in deep convolutional neural network diagnostics of journal bearings with ovalization fault
Diogo Stuani Alves,Gregory Bregion Daniel,Helio Fiori de Castro,Tiago Henrique Machado,Katia Lucchesi Cavalca,Ozhan Gecgel,João Paulo Dias,Stephen Ekwaro-Osire +7 more
TL;DR: A numerical model was developed to simulate the ovalization fault conditions in order to build training datasets and a deep convolutional neural network algorithm was trained with the generated datasets and used to predict the faults conditions.
Proceedings ArticleDOI
Gearbox Fault Diagnostics Using Deep Learning with Simulated Data
Ozhan Gecgel,Stephen Ekwaro-Osire,João Paulo Dias,Abdul Serwadda,Fisseha M. Alemayehu,Abraham Nispel +5 more
TL;DR: An ML and DL classification performance comparison of several algorithms to diagnose faults in a gearbox based on realistic simulated vibration data revealed the superiority of Convolutional Neural Network compared to other classifiers.
Book ChapterDOI
Machine Learning in Crack Size Estimation of a Spur Gear Pair Using Simulated Vibration Data
Ozhan Gecgel,Stephen Ekwaro-Osire,João Paulo Dias,Abraham Nispel,Fisseha M. Alemayehu,Abdul Serwadda +5 more
TL;DR: A simulation-driven ML framework to estimate the crack size in a gear tooth using simulated vibrations signals is proposed and it was shown that the Decision Tree Classifier (DTC) performed best in the identification of small crack sizes regardless of the random selection of the training subsample.
Journal ArticleDOI
Simulation-Driven Deep Learning Approach for Wear Diagnostics in Hydrodynamic Journal Bearings
Ozhan Gecgel,João Paulo Dias,Stephen Ekwaro-Osire,Diogo Stuani Alves,Tiago Henrique Machado,Gregory Bregion Daniel,Helio Fiori de Castro,Katia Lucchesi Cavalca +7 more
TL;DR: This work develops a framework using a deep learning algorithm to classify wear faults in hydrodynamic journal bearings using simulated vibrations signals and shows that the proposed framework can be a promising tool to wear fault diagnostics in journal bearings.
Journal ArticleDOI
Prognostics and Health Management of Wind Energy Infrastructure Systems
Celalettin Yuce,Ozhan Gecgel,Oğuz Doğan,Shweta Dabetwar,Yasar Yanik,Onur Can Kalay,Esin Karpat,Fatih Karpat,Stephen Ekwaro-Osire +8 more
TL;DR: To address the impact of uncertainty, quality and quantity of data, physics-based machine learning (PBML), and digital twin (DT) in diagnostics and prognostics, four research questions were formulated and the methodology used was Preferred Reporting Items for Systematic Review and Meta-Analysis.