Using Deep Learning to Automate the Detection of Flaws in Nuclear Fuel Channel UT Scans
This work addresses the need for faster and more accurate inspections in nuclear reactor safety, though it is incremental as it builds on existing deep learning methods for a specific domain.
The paper tackles the problem of automating flaw detection in nuclear fuel channel ultrasonic testing scans by developing a convolutional neural network model, which successfully identifies at least a portion of each flaw while minimizing false positives as required for the prototype.
Nuclear reactor inspections are critical to ensure the safety and reliability of a nuclear facility's operation. In Canada, Ultrasonic Testing (UT) is used to inspect the health of pressure tubes which are part of Canada's Deuterium Uranium (CANDU) reactor's fuel channels. Currently, analysis of UT scans is performed by manual visualization and measurement to locate, characterize, and disposition flaws. Therefore, there is motivation to develop an automated method that is fast and accurate. In this paper, a proof of concept (PoC) that automates the detection of flaws in nuclear fuel channel UT scans using a convolutional neural network (CNN) is presented. The CNN model was trained after constructing a dataset using historical UT scans and the corresponding inspection results. The requirement for this prototype was to identify the location of at least a portion of each flaw in UT scans while minimizing false positives (FPs). The proposed CNN model achieves this target by automatically identifying at least a portion of each flaw where further manual analysis is performed to identify the width, the length, and the type of the flaw.