Using Deep Learning to Automate the Detection of Flaws in Nuclear Fuel Channel UT Scans

by   Issam Hammad, et al.

Nuclear reactor inspections are critical to ensure the safety and reliability of plants operation. Inspections occur during planned outages and include the inspection of the reactor's fuel channels. In Canada, Ultrasonic Testing (UT) is used to inspect the health of fuel channels in Canada's Deuterium Uranium (CANDU) reactors. Currently, analysis of the UT scans is performed by manual visualization and measurement to locate, characterize, and disposition flaws. Therefore, there is a 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. This industry research was conducted at Alithya Digital Technology Corporation in Pickering, Ontario, Canada. The CNN model was trained after constructing a dataset using historical UT scans and the corresponding inspection results. This data was obtained from a large nuclear power generation company in Ontario. The requirement for this prototype was to identify the location of at least a portion of each flaw in fuel channel scans while minimizing false positives (FPs). This allows for automatic detection of the location of each flaw where further manual analysis is performed to identify the extent and the type of the flaw. Based on the defined requirement, the proposed model was able to achieve 100 with minor chatter and a 100 scans with severe chatter using 18 UT full test scans.


page 2

page 3

page 4

page 7


Automated detection of pitting and stress corrosion cracks in used nuclear fuel dry storage canisters using residual neural networks

Nondestructive evaluation methods play an important role in ensuring com...

Detecting Glaucoma Using 3D Convolutional Neural Network of Raw SD-OCT Optic Nerve Scans

We propose developing and validating a three-dimensional (3D) deep learn...

Effort-free Automated Skeletal Abnormality Detection of Rat Fetuses on Whole-body Micro-CT Scans

Machine Learning-based fast and quantitative automated screening plays a...

Multi-Resolution 3D Convolutional Neural Networks for Automatic Coronary Centerline Extraction in Cardiac CT Angiography Scans

We propose a deep learning-based automatic coronary artery tree centerli...

Taguchi based Design of Sequential Convolution Neural Network for Classification of Defective Fasteners

Fasteners play a critical role in securing various parts of machinery. D...

Attaining human-level performance for anatomical landmark detection in 3D CT data

We present an efficient neural network approach for locating anatomical ...

Please sign up or login with your details

Forgot password? Click here to reset