A New Classifier Network for Ultrasonic NDE Applications based on Ensemble Deep Learning

التفاصيل البيبلوغرافية
العنوان: A New Classifier Network for Ultrasonic NDE Applications based on Ensemble Deep Learning
المؤلفون: Michael Marino, Kushal Virupakshappa, Erdal Oruklu
المصدر: 2019 IEEE International Ultrasonics Symposium (IUS).
بيانات النشر: IEEE, 2019.
سنة النشر: 2019
مصطلحات موضوعية: Artificial neural network, Computer science, business.industry, Deep learning, 05 social sciences, Feature extraction, Detector, Pattern recognition, 010501 environmental sciences, 01 natural sciences, 0502 economics and business, Clutter, Ultrasonic sensor, Artificial intelligence, 050207 economics, business, Classifier (UML), 0105 earth and related environmental sciences
الوصف: This work presents a classifier architecture for Non-Destructive Evaluation (NDE) applications which can robustly detect the presence and location of flaws using an ensemble of deep learning networks. The ensemble draws upon the effective sequential time analysis of Long Short-Term Memory - Neural Networks (LSTM–NN), the function estimation and prediction properties of Wavelet Neural Networks (WNN), and the feature extraction capabilities of Convolution Neural Networks (CNN). Simulation results confirm that the proposed architecture offers highly reliable flaw detection and localization with significant Flaw to Clutter Ratio (FCR) enhancements.
DOI: 10.1109/ultsym.2019.8926229
URL الوصول: https://explore.openaire.eu/search/publication?articleId=doi_________::6670ea8d48bb7f911878e4d89bd7506f
https://doi.org/10.1109/ultsym.2019.8926229
Rights: CLOSED
رقم الانضمام: edsair.doi...........6670ea8d48bb7f911878e4d89bd7506f
قاعدة البيانات: OpenAIRE
الوصف
DOI:10.1109/ultsym.2019.8926229