Nuclear Engineering and Technology

Korean Nuclear Society (한국원자력학회)
권호 표지
DOI QR코드

DOI QR Code

Using artificial intelligence to detect human errors in nuclear power plants: A case in operation and maintenance

  • Ezgi Gursel (Department of Industrial and Systems Engineering, University of Tennessee) ;
  • Bhavya Reddy (Department of Computer Science, San Jose State University) ;
  • Anahita Khojandi (Department of Industrial and Systems Engineering, University of Tennessee) ;
  • Mahboubeh Madadi (Department of Marketing and Business Analytics, San Jose State University) ;
  • Jamie Baalis Coble (Department of Nuclear Engineering, University of Tennessee) ;
  • Vivek Agarwal (Idaho National Laboratory) ;
  • Vaibhav Yadav (Idaho National Laboratory) ;
  • Ronald L. Boring (Idaho National Laboratory)
  • Received : 2022.06.17
  • Accepted : 2022.10.23
  • Published : 2023.02.25
Download PDF
⟨ Previous Next ⟩

Abstract

Human error (HE) is an important concern in safety-critical systems such as nuclear power plants (NPPs). HE has played a role in many accidents and outage incidents in NPPs. Despite the increased automation in NPPs, HE remains unavoidable. Hence, the need for HE detection is as important as HE prevention efforts. In NPPs, HE is rather rare. Hence, anomaly detection, a widely used machine learning technique for detecting rare anomalous instances, can be repurposed to detect potential HE. In this study, we develop an unsupervised anomaly detection technique based on generative adversarial networks (GANs) to detect anomalies in manually collected surveillance data in NPPs. More specifically, our GAN is trained to detect mismatches between automatically recorded sensor data and manually collected surveillance data, and hence, identify anomalous instances that can be attributed to HE. We test our GAN on both a real-world dataset and an external dataset obtained from a testbed, and we benchmark our results against state-of-the-art unsupervised anomaly detection algorithms, including one-class support vector machine and isolation forest. Our results show that the proposed GAN provides improved anomaly detection performance. Our study is promising for the future development of artificial intelligence based HE detection systems.

Keywords

Acknowledgement

This work of authorship was prepared as an account of work sponsored by the U.S. Department of Energy, an agency of the U.S. Government, under Grant No. DE-NE0008978 to University of Tennessee-Knoxville. The authors would like to thank the Tennessee Valley Authority (TVA) for providing the research team with real-world NPP data for use in this study. The authors would also like to thank Erica Christine Swift and Stephen Lamar Farlett, representatives of the TVA, for facilitating NPP data access for the authors. Additionally, the authors would like to thank Klaus Blache and the Reliability and Maintainability Center at the University of Tennessee, Knoxville for providing the necessary equipment for testbed data collection, and Darrell Russell for the testbed data curation. Neither the U.S. Government, nor any agency thereof, nor any of their employees makes any warranty, express or implied, or assumes any legal liability or responsibility for the accuracy, completeness, or usefulness of any information, apparatus, product, or process disclosed, or represents that its use would not infringe privately owned rights.

References

  1. Jeffrey Thomas, Clifford C. Baker, Thomas B. Malone, John T. Malone, Christina L. Hard, Ivan C.L. Rezende, Sally Caruana, Mark Witten, Application of Human Factors in Reducing Human Error in Existing Offshore Facilities, 34, United States Department of Transportation - Publication & Papers, 2002. https://digitalcommons.unl.edu/usdot/34. 
  2. Seongkeun Kang, Poong Hyun Seong, Performance shaping factor taxonomy for human reliability analysis on mitigating nuclear power plant accidents caused by extreme external hazards, Annals of Nuclear Energy 145 (2020), 107533. 
  3. Jinkyun Park, Hee Eun Kim, Inseok Jang, Empirical estimation of human error probabilities based on the complexity of proceduralized tasks in an analog environment, Nuclear Engineering and Technology (2021). 
  4. S Dhillon Balbir, Safety, Reliability, Human Factors, and Human Error in Nuclear Power Plants, CRC Press, 2017. 
  5. KONIS (KOrea Hydro & Nuclear Power Company Nuclear Information System). 
  6. David Gertman, Harold Blackman, Julie Marble, James Byers, Curtis Smith, et al., The spar-h human reliability analysis method, US Nuclear Regulatory Commission 230 (4) (2005) 35. 
  7. Seong Poong Hyun, Kang Hyun Gook, Man Gyun Na, Jong Hyun Kim, Gyunyoung Heo, Yoensub Jung, Advanced mmis toward substantial reduction in human errors in npps, Nuclear Engineering and Technology 45 (2) (2013) 125-140.  https://doi.org/10.5516/NET.04.2013.700
  8. Cha Kab-Mun, Lee Hyun-Chul, A novel qeeg measure of teamwork for human error analysis: an eeg hyperscanning study, Nuclear Engineering and Technology 51 (3) (2019) 683-691.  https://doi.org/10.1016/j.net.2018.11.009
  9. Ahmad Al Rashdan, Michael Griffel, Roger Boza, Donna Guillen, Subtle Process Anomalies Detection Using Machine Learning Methods, Idaho National Laboratory, Idaho Falls, ID (USA), 2019. Technical Report INL/EXT-19-55629. 
  10. Jung Sung Kang, Seung Jun Lee, Concept of an intelligent operator support system for initial emergency responses in nuclear power plants, Nuclear Engineering and Technology (2022). 
  11. Won Chul Cho, Tae Ho Ahn, A classification of electrical component failures and their human error types in south Korean npps during last 10 years, Nuclear Engineering and Technology 51 (3) (2019) 709-718.  https://doi.org/10.1016/j.net.2018.12.011
  12. E. Swaton, V. Neboyan, L. Lederman, Human factors in the operation of nuclear power plants, IAEA Bulletin 29 (4) (1987) 27-30. 
  13. Hardik A. Gohel, Himanshu Upadhyay, Leonel Lagos, Kevin Cooper, Andrew Sanzetenea, Predictive maintenance architecture development for nuclear infrastructure using machine learning, Nuclear Engineering and Technology 52 (7) (2020) 1436-1442.  https://doi.org/10.1016/j.net.2019.12.029
  14. Jacques V. Hugo, David I. Gertman, A method to select human-system interfaces for nuclear power plants, Nuclear Engineering and Technology 48 (1) (2016) 87-97.  https://doi.org/10.1016/j.net.2015.10.004
  15. Robert E. Uhrig, Use of Artificial Intelligence to Enhance the Safety of Nuclear Power Plants, Oak Ridge National Laboratory, Oak Ridge, TN (USA), 1988. Technical report. 
  16. Meenu Sethu, Nesar Ahmed Titu, Dingyu Hu, Mahboubeh Madadi, Jamie Coble, Ronald Boring, Klaus Blache, Vivek Agarwal, Vaibhav Yadav, Anahita Khojandi, Using artificial intelligence to mitigate human factor errors in nuclear power plants: a review, in: 12th Nuclear Plant Instrumentation, Control and Human-Machine Interface Technologies (NPICHMIT 2021), ANS, 2021, pp. 129-141. 
  17. Min-Han Hsieh, Sheue-Ling Hwang, Kang-Hong Liu, Sheau- Farn Max Liang, Chang-Fu Chuang, A decision support system for identifying abnormal operating procedures in a nuclear power plant, Nuclear Engineering and Design 249 (2012) 413-418.  https://doi.org/10.1016/j.nucengdes.2012.04.009
  18. Kwae Hwan Yoo, Ju Hyun Back, Man Gyun Na, Seop Hur, Hyeonmin Kim, Smart support system for diagnosing severe accidents in nuclear power plants, Nuclear Engineering and Technology 50 (4) (2018) 562-569.  https://doi.org/10.1016/j.net.2018.03.007
  19. Yuyun Zeng, Jingquan Liu, Kaichao Sun, Lin-wen Hu, Machine learning based system performance prediction model for reactor control, Annals of Nuclear Energy 113 (2018) 270-278.  https://doi.org/10.1016/j.anucene.2017.11.014
  20. Mario Gomez Fernandez, Akira Tokuhiro, Welter Kent, Qiao Wu, Nuclear energy system's behavior and decision making using machine learning, Nuclear Engineering and Design 324 (2017) 27-34.  https://doi.org/10.1016/j.nucengdes.2017.08.020
  21. Varun Chandola, Arindam Banerjee, Vipin Kumar, Anomaly detection: a survey, ACM Computing Surveys (CSUR) 41 (3) (2009) 1-58. 
  22. Nari S. Arunraj, Robert Hable, Michael Fernandes, Karl Leidl, Michael Heigl, Comparison of supervised, semi-supervised and unsupervised learning methods in network intrusion detection system (nids) application, Anwendungen und Konzepte der Wirtschaftsinformatik 6 (2017). 
  23. Villa-Perez Miryam Elizabeth, Miguel A. Alvarez-Carmona, Octavio Loyola-Gonzalez, Miguel Angel Medina-P erez, Juan Carlos Velazco-Rossell, Kim-Kwang Raymond Choo, Semi-supervised anomaly detection algorithms: a comparative summary and future research directions, Knowledge-Based Systems (2021), 106878. 
  24. Prasanta Gogoi, K. Dhruba, Bhattacharyya, Bhogeswar Borah, Jugal, K. Kalita, A survey of outlier detection methods in network anomaly identification, The Computer Journal 54 (4) (2011) 570-588.  https://doi.org/10.1093/comjnl/bxr026
  25. Ahmad Al Rashdan, St Shawn, Germain. Methods of data collection in nuclear power plants, Nuclear Technology 205 (8) (2019) 1062-1074.  https://doi.org/10.1080/00295450.2019.1610637
  26. Hermine N. Akouemo, Richard J. Povinelli, Probabilistic anomaly detection in natural gas time series data, International Journal of Forecasting 32 (3) (2016) 948-956.  https://doi.org/10.1016/j.ijforecast.2015.06.001
  27. Thomas B. Sheridan, Understanding human error and aiding human diagnostic behaviour in nuclear power plants, in: Human Detection and Diagnosis of System Failures, Springer, 1981, pp. 19-35. 
  28. Jooyoung Park, Wondea Jung, Jonghyun Kim, Inter-relationships between performance shaping factors for human reliability analysis of nuclear power plants, Nuclear Engineering and Technology 52 (1) (2020) 87-100.  https://doi.org/10.1016/j.net.2019.07.004
  29. Gyunyoung Heo, Jinkyun Park, A framework for evaluating the effects of maintenance-related human errors in nuclear power plants, Reliability Engineering & System Safety 95 (7) (2010) 797-805.  https://doi.org/10.1016/j.ress.2010.03.001
  30. Jaemin Yang, Jonghyun Kim, An accident diagnosis algorithm with untrained accident identification, in: Transactions of the Korean Nuclear Society Spring Meeting, Jeju, Korea, 2019. 
  31. Yochan Kim, Yung Hsien James Chang, Jinkyun Park, Criscione Lawrence, Sacada and hurex part 2: the use of sacada and hurex data to estimate human error probabilities, Nuclear Engineering and Technology 54 (3) (2022) 896-908.  https://doi.org/10.1016/j.net.2021.09.003
  32. Jinkyun Park, Yochan Kim, Wondea Jung, Calculating nominal human error probabilities from the operation experience of domestic nuclear power plants, Reliability Engineering & System Safety 170 (2018) 215-225.  https://doi.org/10.1016/j.ress.2017.10.011
  33. Wolfgang Preischl, Mario Hellmich, Human error probabilities from operational experience of German nuclear power plants, Reliability Engineering & System Safety 109 (2013) 150-159.  https://doi.org/10.1016/j.ress.2012.08.004
  34. Markus Goldstein, Seiichi Uchida, A comparative evaluation of unsupervised anomaly detection algorithms for multivariate data, PloS One 11 (4) (2016), e0152173. 
  35. Jianping Ma, Jin Jiang, Applications of fault detection and diagnosis methods in nuclear power plants: a review, Progress in Nuclear Energy 53 (3) (2011) 255-266.  https://doi.org/10.1016/j.pnucene.2010.12.001
  36. Luis Marti, Nayat Sanchez-Pi, Jose Manuel Molina, Ana Cristina Bicharra Garcia, Anomaly detection based on sensor data in petroleum industry applications, Sensors 15 (2) (2015) 2774-2797.  https://doi.org/10.3390/s150202774
  37. Prabhas Hundi, Rouzbeh Shahsavari, Comparative studies among machine learning models for performance estimation and health monitoring of thermal power plants, Applied Energy 265 (2020), 114775. 
  38. Ioannou George, Thanos Tagaris, Georgios Alexandridis, Andreas Stafylopatis, Intelligent techniques for anomaly detection in nuclear reactors, in: EPJ Web of Conferences, ume 247, EDP Sciences, 2021, p. 21011. 
  39. Xingang Zhao, Junyung Kim, Kyle Warns, Xinyan Wang, Pradeep Ramuhalli, Sacit Cetiner, Hyun Gook Kang, Michael Golay, Prognostics and health management in nuclear power plants: an updated method-centric review with special focus on data-driven methods, Frontiers in Energy Research 9 (2021) 294. 
  40. Xin Jin, Yin Guo, Soumik Sarkar, Asok Ray, Robert M. Edwards, Anomaly detection in nuclear power plants via symbolic dynamic filtering, IEEE Transactions on Nuclear Science 58 (1) (2010) 277-288.  https://doi.org/10.1109/TNS.2010.2088138
  41. Minhee Kim, Elisa Ou, Po-Ling Loh, Todd Allen, Robert Agasie, Kaibo Liu, Rnnbased online anomaly detection in nuclear reactors for highly imbalanced datasets with uncertainty, Nuclear Engineering and Design 364 (2020), 110699. 
  42. Le Zhang, Wei Cheng, Xue Liu, Xuefeng Chen, Fengtian Chang, Junying Hong, Xiaofei Li, System-level anomaly detection for nuclear power plants using variational graph auto-encoders, in: 2021 IEEE International Conference on Sensing, Diagnostics, Prognostics, and Control (SDPC), IEEE, 2021, pp. 180-185. 
  43. Francesco Caliva, Fabio Sousa De Ribeiro, Antonios Mylonakis, Christophe Demazi'ere, Paolo Vinai, Georgios Leontidis, Stefanos Kollias, A deep learning approach to anomaly detection in nuclear reactors, in: 2018 International Joint Conference on Neural Networks (IJCNN), IEEE, 2018, pp. 1-8. 
  44. J. Tylee, On-line failure detection in nuclear power plant instrumentation, IEEE Transactions on Automatic Control 28 (3) (1983) 406-415.  https://doi.org/10.1109/TAC.1983.1103240
  45. Lex Poon, Siamak Farshidi, Na Li, Zhiming Zhao, Unsupervised anomaly detection in data quality control, in: 2021 IEEE International Conference on Big Data (Big Data), IEEE, 2021, pp. 2327-2336. 
  46. Daiki Nishiura, Isao Nambu, Yoshiko Maruyama, Yasuhiro Wada, Improvement of human error prediction accuracy in single-trial analysis of electroencephalogram, in: 2021 43rd Annual International Conference of the IEEE Engineering in Medicine & Biology Society (EMBC), IEEE, 2021, pp. 6179-6182. 
  47. Ji Hun Park, Hye Seon Jo, Man Gyun Na, System and component anomaly detection using lstm-vae, in: 2021 5th International Conference on System Reliability and Safety (ICSRS), IEEE, 2021, pp. 131-137. 
  48. Junyong Bae, Jeeyea Ahn, Seung Jun Lee, Comparison of multilayer perceptron and long short-term memory for plant parameter trend prediction, Nuclear Technology 206 (7) (2020) 951-961.  https://doi.org/10.1080/00295450.2019.1693215
  49. Jeeyea Ahn, Junyong Bae, Seung Jun Lee, A Human Error Detection System in Nuclear Power Plant Operations. In 11th Nuclear Plant Instrumentation, Control and Human-Machine Interface Technologies (NPICHMIT), American Nuclear Society, 2019. 
  50. Houssam Zenati, Chuan Sheng Foo, Lecouat Bruno, Gaurav Manek, Vijay Ramaseshan Chandrasekhar, Efficient gan-based Anomaly Detection, 2018 arXiv preprint arXiv:1802.06222. 
  51. Federico Di Mattia, Paolo Galeone, Michele De Simoni, Emanuele Ghelfi, A Survey on Gans for Anomaly Detection, 2019 arXiv preprint arXiv: 1906.11632. 
  52. Xuan Xia, Xizhou Pan, Nan Li, He Xing, Ma Lin, Xiaoguang Zhang, Ning Ding, Gan-Based Anomaly Detection: A Review, Neurocomputing, 2022. 
  53. Ian Goodfellow, Jean Pouget-Abadie, Mehdi Mirza, Bing Xu, David Warde-Farley, Sherjil Ozair, Aaron Courville, Yoshua Bengio, Generative adversarial networks, Communications of the ACM 63 (11) (2020) 139-144.  https://doi.org/10.1145/3422622
  54. Thomas Schlegl, Philipp Seebock, Sebastian M. Waldstein, Ursula Schmidt-Erfurth, Georg Langs, Unsupervised anomaly detection with generative adversarial networks to guide marker discovery, in: International Conference on Information Processing in Medical Imaging, Springer, 2017, pp. 146-157. 
  55. Dan Li, Dacheng Chen, Lei Shi, Baihong Jin, Jonathan Goh, See-Kiong Ng, in: Mad-gan: Multivariate Anomaly Detection for Time Series Data with Generative Adversarial Networks, ICANN, 2019. 
  56. Yeji Choi, Hyunki Lim, Heeseung Choi, Ig-Jae Kim, Gan-based anomaly detection and localization of multivariate time series data for power plant, in: 2020 IEEE International Conference on Big Data and Smart Computing (Big-Comp), IEEE, 2020, pp. 71-74. 
  57. Seung Geun Kim, Ho Chae Young, Seong Poong Hyun, Development of a generative-adversarial-network-based signal reconstruction method for nuclear power plants, Annals of Nuclear Energy 142 (2020), 107410. 
  58. Xiangyu Li, Tao Huang, Kun Cheng, Zhifang Qiu, Sichao Tan, Research on anomaly detection method of nuclear power plant operation state based on unsupervised deep generative model, Annals of Nuclear Energy 167 (2022), 108785. 
  59. Anders Brandt, Noise and Vibration Analysis: Signal Analysis and Experimental Procedures, John Wiley & Sons, 2011. 
  60. Mark Mitchell, Baurzhan Muftakhidinov, Winchen Tobias, B. van Schaik, A.K. Wilms, et al., Engauge digitizer software, Webpage (11, 2017). http://markummitchell.github.io/engauge-digitizer. 
  61. Duygu Bayram, Serhat Seker, Redundancy-based predictive fault detection on electric motors by stationary wavelet transform, IEEE Transactions on Industry Applications 53 (3) (2016) 2997-3004.  https://doi.org/10.1109/TIA.2016.2622231
  62. Hocine Bendjama, Salah Bouhouche, Mohamed Seghir Boucherit, Application of wavelet transform for fault diagnosis in rotating machinery, International Journal of machine Learning and computing 2 (1) (2012) 82-87.  https://doi.org/10.7763/IJMLC.2012.V2.93
  63. Wahyu Caesarendra, Tegoeh Tjahjowidodo, A review of feature extraction methods in vibration-based condition monitoring and its application for degradation trend estimation of low-speed slew bearing, Machines 5 (4) (2017) 21. 
  64. Salim Lahmiri, Wavelet low-and high-frequency components as features for predicting stock prices with backpropagation neural networks, Journal of King Saud University-Computer and Information Sciences 26 (2) (2014) 218-227.  https://doi.org/10.1016/j.jksuci.2013.12.001
  65. Samet Akcay, Amir Atapour-Abarghouei, Toby P. Breckon, Ganomaly: semi-supervised anomaly detection via adversarial training, in: Asian Conference on Computer Vision, Springer, 2018, pp. 622-637. 
  66. Dan Li, Dacheng Chen, Jonathan Goh, See-kiong Ng, Anomaly Detection with Generative Adversarial Networks for Multivariate Time Series, 2018 arXiv preprint arXiv:1809.04758. 
  67. Dan Li, Dacheng Chen, Baihong Jin, Lei Shi, Jonathan Goh, See-Kiong Ng, Madgan: multivariate anomaly detection for time series data with generative adversarial networks, in: International Conference on Artificial Neural Networks, Springer, 2019, pp. 703-716. 
  68. Ferhat Ozgur Catak, Robust ensemble classifier combination based on noise removal with one-class svm, in: International Conference on Neural Information Processing, Springer, 2015, pp. 10-17. 
  69. Katherine Heller, Krysta Svore, Angelos D. Keromytis, Salvatore Stolfo, One Class Support Vector Machines for Detecting Anomalous Windows Registry Accesses, Columbia Academic Commons, 2003, https://doi.org/10.7916/D85M6CFF. 
  70. Shen Yin, Xiangping Zhu, Jing Chen, Fault detection based on a robust one class support vector machine, Neurocomputing 145 (2014) 263-268.  https://doi.org/10.1016/j.neucom.2014.05.035
  71. S. Sathiya Keerthi, Chih-Jen Lin, Asymptotic behaviors of support vector machines with Gaussian kernel, Neural Computation 15 (7) (2003) 1667-1689.  https://doi.org/10.1162/089976603321891855
  72. Yingchao Xiao, Huangang Wang, Wenli Xu, Parameter selection of Gaussian kernel for one-class svm, IEEE Transactions on Cybernetics 45 (5) (2014) 941-953.  https://doi.org/10.1109/TCYB.2014.2340433
  73. Fei Tony Liu, Kai Ming Ting, Zhi-Hua Zhou, Isolation forest, in: 2008 Eighth Ieee International Conference on Data Mining, IEEE, 2008, pp. 413-422. 
  74. Chandresh Kumar Maurya, Durga Toshniwal, Gopalan Vijendran Venkoparao, Online anomaly detection via class-imbalance learning, in: 2015 Eighth International Conference on Contemporary Computing (IC3), IEEE, 2015, pp. 30-35.