Onur Recepoglu

About

Onur Recepoglu is a researcher specializing in non-destructive testing (NDT) and machine learning for industrial pipeline inspection. His work focuses on developing deep learning models to detect and quantify defects in steel pipelines using magnetic flux leakage (MFL) signals collected by semi-autonomous in-line inspection (ILI) robots. His most cited paper, "A Novel Cascaded Deep Learning Model for the Detection and Quantification of Defects in Pipelines via Magnetic Flux Leakage Signals" (2023), has garnered 55 citations, showcasing its impact in the field. In this work, Recepoglu introduces a cascaded deep learning framework that interprets three-axis MFL sensor data, enabling accurate defect characterization. His earlier paper, "Defect Detection and Quantification from Magnetic Flux Leakage Signals Based on Deep Learning" (2022), laid the groundwork for this approach. By combining robotics, sensor technology, and artificial intelligence, Recepoglu’s contributions advance automated pipeline integrity assessment, reducing reliance on manual inspection and improving safety in critical energy infrastructure. His research is particularly valuable for students and engineers working on intelligent NDT systems and industrial automation.

Research Focus

Key Achievements

Top Papers

1. 1
   A Novel Cascaded Deep Learning Model for the Detection and Quantification of Defects in Pipelines via Magnetic Flux Leakage Signals

   55 citations · 2023
2. 2
   Defect Detection and Quantification from Magnetic Flux Leakage Signals Based on Deep Learning

   3 citations · 2022

Key Collaborators

Contact & Links