Seminários e Teses

Próximos- Anteriores-
Semana de 05/12 a 11/12
Dissertação de Mestrado
Data-driven ultrasonic non-destructive evaluation of pipes and welds in the context of the oil and gas industry
Guilherme Rezende Bessa Ferreira, PUC-Rio

Data: 06/12/2021 às 14h e 0min
Local: por acesso remoto

Orientador: Helon Ayala e Alan Kubrusly
Área de Concentração: Petróleo e Energia


Ultrasonic non-destructive evaluation (NDE) is of extreme importance inthe oil and gas industry (OGI), especially for assets and structures subjected to conditions that accelerate failure mechanisms. Despite being widely spread, ultrasonic non-destructive methods depend on a specialized workforce, thus being error-prone and time-consuming. In this context, pattern recognition methods, like Machine Learning (ML), fit conveniently to solve the challenges of the task. Hence, this work aims at applying ML techniques to address the interpretation of data acquired through ultrasonic NDE in the context of the OGI. For that purpose, this dissertation involves three case studies. Firstly, Ultrasonic Guided Wave (UGW) signals are used to classify defects present in welded thermoplastic composite joints. Results have shown that, when using features extracted with autoregressive models, the accuracy of the ML model improves by at least 72.5%. Secondly, ultrasonic image data is used to constructo an automatic weld diagnostic system. The proposed framework resulted in a lightweight model capable of performing classification with over 99% accuracy. Finally, simulation data was used to create a deep learning model for estimating the severity of corrosion-like defects in pipelines. R2 results superior to 0.99 were achieved.

Link da defesa:

Meeting ID: 982 1158 9767
Passcode: 259785