Pre-trained network-based transfer learning: A small-sample machine learning approach to nuclear power plant classification problem

Zhong, Xianping; Ban, Heng

doi:10.1016/j.anucene.2022.109201

Pre-trained network-based transfer learning: A small-sample machine learning approach to nuclear power plant classification problem

Journal Article · Thu May 19 00:00:00 EDT 2022 · Annals of Nuclear Energy

DOI:https://doi.org/10.1016/j.anucene.2022.109201· OSTI ID:1976818

Zhong, Xianping ^[1]; Ban, Heng ^[2]

University of Pittsburgh, PA (United States); OSTI
University of Pittsburgh, PA (United States)

Some research topics belonging to classification problems in the nuclear industry, such as fault diagnosis and accident identification, can be solved by feature extraction and subsequent application of statistical machine learning classifiers. Recently, deep neural network-based methods with automatic feature extraction and high accuracy have gained wide attention. They usually require large-scale training data, however, plant fault or accident data are scarce or difficult to obtain. Here this paper proposes a convolutional network (CNN)-based transfer learning method to solve this problem. The network's shallow layer is derived from a pre-trained CNN based on the ImageNet database to automatically extract features, and the deep layer is customized to match the classification problem. Data in non-image formats are converted to image formats and subsequently used to train the network. Case studies of rotating machines fault diagnosis show that the proposed method requires only limited training data to achieve high accuracy.

View Accepted Manuscript (DOE)

Research Organization:: University of Pittsburgh, PA (United States)

Sponsoring Organization:: USDOE Office of Nuclear Energy (NE); University of Pittsburgh

Grant/Contract Number:: NE0008909

OSTI ID:: 1976818

Journal Information:: Annals of Nuclear Energy, Journal Name: Annals of Nuclear Energy Journal Issue: C Vol. 175; ISSN 0306-4549

Publisher:: ElsevierCopyright Statement

Country of Publication:: United States

Language:: English

References (30)

Motor Fault Diagnosis Based on Short-time Fourier Transform and Convolutional Neural Network Wang, Li-Hua; Zhao, Xiao-Ping; Wu, Jia-Xin Chinese Journal of Mechanical Engineering, Vol. 30, Issue 6 https://doi.org/10.1007/s10033-017-0190-5	journal	November 2017
ImageNet Large Scale Visual Recognition Challenge Russakovsky, Olga; Deng, Jia; Su, Hao International Journal of Computer Vision, Vol. 115, Issue 3 https://doi.org/10.1007/s11263-015-0816-y	journal	April 2015
Machine learning for medical diagnosis: history, state of the art and perspective Kononenko, Igor Artificial Intelligence in Medicine, Vol. 23, Issue 1 https://doi.org/10.1016/S0933-3657(01)00077-X	journal	August 2001
Analysis of operator support method based on intelligent dynamic interlock in lead-cooled fast reactor simulator Xu, Peng; Wang, Jianye; Yang, Minghan Annals of Nuclear Energy, Vol. 99 https://doi.org/10.1016/j.anucene.2016.09.006	journal	January 2017
A data-driven adaptive fault diagnosis methodology for nuclear power systems based on NSGAII-CNN He, Chen; Ge, Daochuan; Yang, Minghan Annals of Nuclear Energy, Vol. 159 https://doi.org/10.1016/j.anucene.2021.108326	journal	September 2021
Research on robustness of five typical data-driven fault diagnosis models for nuclear power plants Li, Jiangkuan; Lin, Meng Annals of Nuclear Energy, Vol. 165 https://doi.org/10.1016/j.anucene.2021.108639	journal	January 2022
Deep transfer learning with limited data for machinery fault diagnosis Han, Te; Liu, Chao; Wu, Rui Applied Soft Computing, Vol. 103 https://doi.org/10.1016/j.asoc.2021.107150	journal	May 2021
Intelligent fault diagnosis method of planetary gearboxes based on convolution neural network and discrete wavelet transform Chen, Renxiang; Huang, Xin; Yang, Lixia Computers in Industry, Vol. 106 https://doi.org/10.1016/j.compind.2018.11.003	journal	April 2019
Face recognition: Past, present and future (a review) Taskiran, Murat; Kahraman, Nihan; Erdem, Cigdem Eroglu Digital Signal Processing, Vol. 106 https://doi.org/10.1016/j.dsp.2020.102809	journal	November 2020
Automated latent fingerprint identification system: A review Singla, Nancy; Kaur, Manvjeet; Sofat, Sanjeev Forensic Science International, Vol. 309 https://doi.org/10.1016/j.forsciint.2020.110187	journal	April 2020
Sensors incipient fault detection and isolation of nuclear power plant using extended Kalman filter and Kullback–Leibler divergence Gautam, Suryakant; Tamboli, Prakash K.; Roy, Kallol ISA Transactions, Vol. 92 https://doi.org/10.1016/j.isatra.2019.02.011	journal	September 2019
Rotor fault diagnosis using a convolutional neural network with symmetrized dot pattern images Zhu, Xiaoxun; Hou, Dongnan; Zhou, Pei Measurement, Vol. 138 https://doi.org/10.1016/j.measurement.2019.02.022	journal	May 2019
The engineering simulation system for HTR-PM Sui, Zhe; Sun, Jun; Wei, Chunlin Nuclear Engineering and Design, Vol. 271 https://doi.org/10.1016/j.nucengdes.2013.12.019	journal	May 2014
An adaptive spatiotemporal feature learning approach for fault diagnosis in complex systems Han, Te; Liu, Chao; Wu, Linjiang Mechanical Systems and Signal Processing, Vol. 117 https://doi.org/10.1016/j.ymssp.2018.07.048	journal	February 2019
Weighted domain adaptation networks for machinery fault diagnosis Wei, Dongdong; Han, Te; Chu, Fulei Mechanical Systems and Signal Processing, Vol. 158 https://doi.org/10.1016/j.ymssp.2021.107744	journal	September 2021
A Tutorial on Support Vector Machines for Pattern Recognition Burges, Christopher J. C. Data Mining and Knowledge Discovery, Vol. 2, Issue 2, p. 121-167 https://doi.org/10.1023/A:1009715923555	journal	January 1998
An overview of statistical learning theory Vapnik, V. N. IEEE Transactions on Neural Networks, Vol. 10, Issue 5 https://doi.org/10.1109/72.788640	journal	January 1999
The complex backpropagation algorithm Leung, H.; Haykin, S. IEEE Transactions on Signal Processing, Vol. 39, Issue 9 https://doi.org/10.1109/78.134446	journal	January 1991
Grad-CAM: Visual Explanations from Deep Networks via Gradient-Based Localization Selvaraju, Ramprasaath R.; Cogswell, Michael; Das, Abhishek 2017 IEEE International Conference on Computer Vision (ICCV) https://doi.org/10.1109/ICCV.2017.74	conference	October 2017
Understanding of a convolutional neural network Albawi, Saad; Mohammed, Tareq Abed; Al-Zawi, Saad 2017 International Conference on Engineering and Technology (ICET) https://doi.org/10.1109/ICEngTechnol.2017.8308186	conference	August 2017
A Comprehensive Survey on Transfer Learning Zhuang, Fuzhen; Qi, Zhiyuan; Duan, Keyu Proceedings of the IEEE, Vol. 109, Issue 1 https://doi.org/10.1109/JPROC.2020.3004555	journal	January 2021
A Survey on Transfer Learning Pan, Sinno Jialin; Yang, Qiang IEEE Transactions on Knowledge and Data Engineering, Vol. 22, Issue 10 https://doi.org/10.1109/TKDE.2009.191	journal	October 2010
Overfitting and undercomputing in machine learning Dietterich, Tom ACM Computing Surveys, Vol. 27, Issue 3 https://doi.org/10.1145/212094.212114	journal	September 1995
A survey of transfer learning Weiss, Karl; Khoshgoftaar, Taghi M.; Wang, DingDing Journal of Big Data, Vol. 3, Issue 1 https://doi.org/10.1186/s40537-016-0043-6	journal	May 2016
Development of the On-Line Operator Aid System OASYS Using A Rule-Based Expert System and Fuzzy Logic for Nuclear Power Plants Chang, Soon Heung; Kang, Ki Sig; Choi, Seong Soo Nuclear Technology, Vol. 112, Issue 2 https://doi.org/10.13182/NT95-A35179	journal	November 1995
Short-time Fourier transform and wavelet transform with Fourier-domain processing Yu, F. T. S.; Lu, Guowen Applied Optics, Vol. 33, Issue 23 https://doi.org/10.1364/AO.33.005262	journal	August 1994
Data-Driven Machine Learning for Fault Detection and Diagnosis in Nuclear Power Plants: A Review Hu, Guang; Zhou, Taotao; Liu, Qianfeng Frontiers in Energy Research, Vol. 9 https://doi.org/10.3389/fenrg.2021.663296	journal	May 2021
Boolean Network-Based Sensor Selection with Application to the Fault Diagnosis of a Nuclear Plant Dong, Zhe Energies, Vol. 10, Issue 12 https://doi.org/10.3390/en10122125	journal	December 2017
Deep Learning and Medical Diagnosis: A Review of Literature Bakator, Mihalj; Radosav, Dragica Multimodal Technologies and Interaction, Vol. 2, Issue 3 https://doi.org/10.3390/mti2030047	journal	August 2018
K-nearest neighbor Peterson, Leif Scholarpedia, Vol. 4, Issue 2 https://doi.org/10.4249/scholarpedia.1883	journal	January 2009

Similar Records

Quantum computing based hybrid deep learning for fault diagnosis in electrical power systems

Journal Article · Sat Aug 21 00:00:00 EDT 2021 · Applied Energy · OSTI ID:1981538

Sparse coding of pathology slides compared to transfer learning with deep neural networks

Journal Article · Fri Nov 30 23:00:00 EST 2018 · BMC Bioinformatics · OSTI ID:1626772

Comparing Deep Learning Approaches for Understanding Genotype × Phenotype Interactions in Biomass Sorghum

Journal Article · Mon Jul 04 00:00:00 EDT 2022 · Frontiers in Artificial Intelligence · OSTI ID:1874732

Related Subjects

22 GENERAL STUDIES OF NUCLEAR REACTORS
classification problem
imageNet
nuclear power plant
pre-trained convolutional network
transfer learning

Pre-trained network-based transfer learning: A small-sample machine learning approach to nuclear power plant classification problem

Citation Formats

References (30)

Similar Records

Related Subjects