Affiliation:
1. Faculty of Engineering and Applied Science, Ontario Tech University (UOIT), Oshawa, ON L1G 0C5, Canada
Abstract
In a nuclear power plant (NPP), the used tools are visually inspected to ensure their integrity before and after their use in the nuclear reactor. The manual inspection is usually performed by qualified technicians and takes a large amount of time (weeks up to months). In this work, we propose an automated tool inspection that uses a classification model for anomaly detection. The deep learning model classifies the computed tomography (CT) images as defective (with missing components) or defect-free. Moreover, the proposed algorithm enables incremental learning (IL) using a proposed thresholding technique to ensure a high prediction confidence by continuous online training of the deployed online anomaly detection model. The proposed algorithm is tested with existing state-of-the-art IL methods showing that it helps the model quickly learn the anomaly patterns. In addition, it enhances the classification model confidence while preserving a desired minimal performance.
Subject
Applied Mathematics,Modeling and Simulation,General Computer Science,Theoretical Computer Science
Reference23 articles.
1. Li, S.Z., and Jain, A. (2009). Encyclopedia of Biometrics, Springer.
2. Continual Lifelong Learning with Neural Networks: A Review;Parisi;Neural Netw.,2019
3. Chen, Z., and Liu, B. (2018). Synthesis Lectures on Artificial Intelligence and Machine Learning, Springer.
4. A Continual Learning Survey: Defying Forgetting in Classification Tasks;Delange;IEEE Trans. Pattern Anal. Mach. Intell.,2022
5. Luo, Y., Yin, L., Bai, W., and Mao, K. (2020). An Appraisal of Incremental Learning Methods. Entropy, 22.
Cited by
2 articles.
订阅此论文施引文献
订阅此论文施引文献,注册后可以免费订阅5篇论文的施引文献,订阅后可以查看论文全部施引文献