Scopus İndeksli Yayınlar Koleksiyonu

Permanent URI for this collectionhttps://hdl.handle.net/20.500.12416/8651

Browse

Filters

20252

Settings

Subject: search.filters.subject.Defect DetectionWoS Q: search.filters.wosQuartile.Q2

Search Results

Now showing 1 - 2 of 2
  • Article
    Citation - Scopus: 2
    Damage Detection in Aircraft Engine Borescope Inspection Using Deep Learning
    (Springer Science and Business Media Deutschland GmbH, 2025) Uzun, I.; Tolun, M.R.; Sari, F.; Alpaslan, F.N.
    Aircraft engine inspection is a key pillar of aviation safety as it helps to maintain adequate performance standards to ensure engine airworthiness. In addition, it is also vital for asset value retention. Borescope inspection is currently the most widely used visual inspection method for aircraft engines. However, borescope inspection is a time-consuming, subjective, and complex process that heavily depends on the experience and attention level of the inspector. Moreover, the cost savings of airlines and the maintenance, repair, and overhaul (MRO) centers expose pressure and workload on inspectors. These factors make an automated system to support damage detection during borescope inspection necessary in order to mitigate potential risks. In this paper, we propose a deep learning-based automated damage detection framework that employs aircraft engine borescope inspection images. Faster R-CNN-based deep learning model with Inception v2 feature extractor is utilized for the present architecture. Due to the limited number of images, data augmentation and other overfitting methods are also employed. The framework supports crack, burn, nick, and dent damage types across all modules of turbofan engines. It is trained and validated with moderate to complex borescope images obtained from the field. The framework achieves 92.64% accuracy for crack, 92.05% for nick or dent, and 81.14% for burn damage classes, with an overall 88.61% average accuracy. © The Author(s) 2025.
  • Article
    Citation - WoS: 2
    Citation - Scopus: 1
    Millimeter-Wave Sar Imaging for Sub-Millimeter Defect Detection With Non-Destructive Testing
    (Mdpi, 2025) Yalcinkaya, Bengisu; Aydin, Elif; Kara, Ali
    This paper introduces a high-resolution 77-81 GHz mmWave Synthetic Aperture Radar (SAR) imaging methodology integrating low-cost hardware with modified radar signal characteristics specifically for NDT applications. The system is optimized to detect minimal defects in materials, including low-reflectivity ones. In contrast to the existing studies, by optimizing key system parameters, including frequency slope, sampling interval, and scanning aperture, high-resolution SAR images are achieved with reduced computational complexity and storage requirements. The experiments demonstrate the effectiveness of the system in detecting optically undetectable minimal surface defects down to 0.4 mm, such as bonded adhesive lines on low-reflectivity materials with 2500 measurement points and sub-millimeter features on metallic targets at a distance of 30 cm. The results show that the proposed system achieves comparable or superior image quality to existing high-cost setups while requiring fewer data points and simpler signal processing. Low-cost, low-complexity, and easy-to-build mmWave SAR imaging is constructed for high-resolution SAR imagery of targets with a focus on detecting defects in low-reflectivity materials. This approach has significant potential for practical NDT applications with a unique emphasis on scalability, cost-effectiveness, and enhanced performance on low-reflectivity materials for industries such as manufacturing, civil engineering, and 3D printing.