본문 바로가기
KERD
논문KCI 등재

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

Agarwal Vivek|Boring Ronald L.|Gursel Ezgi|Reddy Bhavya|Khojandi Anahita|Madadi Mahboubeh|Coble Jamie Baalis|Yadav Vaibhav
한국원자력학회 (Korean Nuclear Society)|2023.02|Nuclear Engineering and Technology|제55권 제2호|pp. 603-622|DOI 10.1016/j.net.2022.10.032

2

조회

0

다운로드

3

인용

0

참고문헌

키워드

machine learninganomaly detectionnuclear power plantshuman error detection
주제분류원자력공학

초록

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.

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.

참고문헌 (74)

  1. Application of Human Factors in Reducing Human Error in Existing Offshore Facilities, "Jeffrey Thomas", ~, pp.34, United States Department of Transportation - Publication & Papers (2002)
  2. Seongkeun Kang, "Performance shaping factor taxonomy for human reliability analysis on mitigating nuclear power plant accidents caused by extreme external hazards", Annals of Nuclear Energy, 145, pp.107533~ (2020)
  3. 박진균, "Empirical estimation of human error probabilities based on the complexity of proceduralized tasks in an analog environment", Nuclear Engineering and Technology, 54(6), pp.2037~2047 (2022), 한국원자력학회[DOI]
  4. S Dhillon Balbir, "Safety, Reliability, Human Factors, and Human Error in Nuclear Power Plants" (2017), CRC Press
  5. "KONIS (KOrea Hydro & Nuclear Power Company Nuclear Information System)", ~
  6. David Gertman, "The spar-h human reliability analysis method", US Nuclear Regulatory Commission, 230(4), pp.35~ (2005)
  7. 성풍현, "Advanced MMIS Toward Substantial Reduction in Human Errors in NPPs", Nuclear Engineering and Technology, 45(2), pp.125~140 (2013), 한국원자력학회
  8. 차갑문, "A Novel qEEG Measure of Teamwork for Human Error Analysis: An EEG Hyperscanning Study", Nuclear Engineering and Technology, 51(3), pp.683~691 (2019), 한국원자력학회[DOI]
  9. Subtle Process Anomalies Detection Using Machine Learning Methods, "Ahmad Al Rashdan", Idaho National Laboratory, ~, pp.Technical Report INL (2019), EXT-19-55629
  10. 강정성, "Concept of an intelligent operator support system for initial emergency responses in nuclear power plants", Nuclear Engineering and Technology, 54(7), pp.2453~2466 (2022), 한국원자력학회[DOI]
  11. 조원철, "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), pp.709~718 (2019), 한국원자력학회[DOI]
  12. E. Swaton, "Human factors in the operation of nuclear power plants", IAEA Bulletin, 29(4), pp.27~30 (1987)
  13. Gohel Hardik A., "Predictive maintenance architecture development for nuclear infrastructure using machine learning", Nuclear Engineering and Technology, 52(7), pp.1436~1442 (2020), 한국원자력학회[DOI]
  14. Jacques V. Hugo, "A Method to Select Human – System Interfaces for Nuclear Power Plants", Nuclear Engineering and Technology, 48(1), pp.87~97 (2016), 한국원자력학회
  15. Use of Artificial Intelligence to Enhance the Safety of Nuclear Power Plants, "Robert E. Uhrig", Oak Ridge National Laboratory, ~ (1988)
  16. Meenu Sethu, "Using artificial intelligence to mitigate human factor errors in nuclear power plants: a review", 12th Nuclear Plant Instrumentation, Control and Human-Machine Interface Technologies (NPICHMIT 2021), pp.129~141 (2021), ANS
  17. Min-Han Hsieh, "A decision support system for identifying abnormal operating procedures in a nuclear power plant", Nuclear Engineering and Design, 249, pp.413~418 (2012)
  18. 유쾌환, "Smart support system for diagnosing severe accidents in nuclear power plants", Nuclear Engineering and Technology, 50(4), pp.562~569 (2018), 한국원자력학회
  19. Yuyun Zeng, "Machine learning based system performance prediction model for reactor control", Annals of Nuclear Energy, 113, pp.270~278 (2018)
  20. Mario Gomez Fernandez, "Nuclear energy system's behavior and decision making using machine learning", Nuclear Engineering and Design, 324, pp.27~34 (2017)
  21. Varun Chandola, "Anomaly detection: a survey", ACM Computing Surveys (CSUR), 41(3), pp.1~58 (2009)
  22. Nari S. Arunraj, "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, "Semi-supervised anomaly detection algorithms: a comparative summary and future research directions", Knowledge-Based Systems, pp.106878~ (2021)
  24. Prasanta Gogoi, "A survey of outlier detection methods in network anomaly identification", The Computer Journal, 54(4), pp.570~588 (2011)
  25. Ahmad Al Rashdan, "Germain. Methods of data collection in nuclear power plants", Nuclear Technology, 205(8), pp.1062~1074 (2019)
  26. Hermine N. Akouemo, "Probabilistic anomaly detection in natural gas time series data", International Journal of Forecasting, 32(3), pp.948~956 (2016)
  27. Thomas B. Sheridan, "Human Detection and Diagnosis of System Failures", pp.19~35 (1981), Springer
  28. 박주영, "Inter-relationships between performance shaping factors for human reliability analysis of nuclear power plants", Nuclear Engineering and Technology, 52(1), pp.87~100 (2020), 한국원자력학회
  29. Gyunyoung Heo, "A framework for evaluating the effects of maintenance-related human errors in nuclear power plants", Reliability Engineering & System Safety, 95(7), pp.797~805 (2010)
  30. Jaemin Yang, "An accident diagnosis algorithm with untrained accident identification", Transactions of the Korean Nuclear Society Spring Meeting (2019)
  31. 김요찬, "SACADA and HuREX part 2: The use of SACADA and HuREX data to estimate human error probabilities", Nuclear Engineering and Technology, 54(3), pp.896~908 (2022), 한국원자력학회[DOI]
  32. Jinkyun Park, "Calculating nominal human error probabilities from the operation experience of domestic nuclear power plants", Reliability Engineering & System Safety, 170, pp.215~225 (2018)
  33. Wolfgang Preischl, "Human error probabilities from operational experience of German nuclear power plants", Reliability Engineering &System Safety, 109, pp.150~159 (2013)
  34. Markus Goldstein, "A comparative evaluation of unsupervised anomaly detection algorithms for multivariate data", PloS One, 11(4), pp.e0152173~ (2016)
  35. Jianping Ma, "Applications of fault detection and diagnosis methods in nuclear power plants : a review", Progress in Nuclear Energy, 53(3), pp.255~266 (2011)
  36. Luis Martí, "Anomaly detection based on sensor data in petroleum industry applications", Sensors, 15(2), pp.2774~2797 (2015)
  37. Prabhas Hundi, "Comparative studies among machine learning models for performance estimation and health monitoring of thermal power plants", Applied Energy, 265, pp.114775~ (2020)
  38. Ioannou George, "Intelligent techniques for anomaly detection in nuclear reactors", EPJ Web of Conferences, 247, pp.21011~ (2021), EDP Sciences
  39. Xingang Zhao, "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, pp.294~ (2021)
  40. Xin Jin, "Anomaly detection in nuclear power plants via symbolic dynamic filtering", IEEE Transactions on Nuclear Science, 58(1), pp.277~288 (2010)
  41. Minhee Kim, "Rnnbased online anomaly detection in nuclear reactors for highly imbalanced datasets with uncertainty", Nuclear Engineering and Design, 364, pp.110699~ (2020)
  42. Le Zhang, "System-level anomaly detection for nuclear power plants using variational graph auto-encoders", 2021 IEEE International Conference on Sensing, Diagnostics, Prognostics, and Control (SDPC), pp.180~185 (2021), IEEE
  43. Francesco Caliva, "A deep learning approach to anomaly detection in nuclear reactors", 2018International Joint Conference on Neural Networks (IJCNN), pp.1~8 (2018), IEEE
  44. J. Tylee, "On-line failure detection in nuclear power plant instrumentation", IEEE Transactions on Automatic Control, 28(3), pp.406~415 (1983)
  45. Lex Poon, "Unsupervised anomaly detection in data quality control", 2021 IEEE International Conference on Big Data (Big Data), pp.2327~2336 (2021), IEEE
  46. Daiki Nishiura, "Improvement of human error prediction accuracy in single-trial analysis of electroencephalogram", 2021 43rd Annual International Conference of the IEEE Engineering in Medicine & Biology Society (EMBC), pp.6179~6182 (2021), IEEE
  47. Ji Hun Park, "System and component anomaly detection using lstm-vae", 2021 5th International Conference on System Reliability and Safety (ICSRS), pp.131~137 (2021), IEEE
  48. Junyong Bae, "Comparison of multilayer perceptron and long short-term memory for plant parameter trend prediction", Nuclear Technology, 206(7), pp.951~961 (2020)
  49. Jeeyea Ahn, "A Human Error Detection System in Nuclear Power Plant Operations", 11th Nuclear Plant Instrumentation, Control and Human-Machine Interface Technologies (NPICHMIT) (2019), American Nuclear Society
  50. Houssam Zenati, "Efficient gan-based Anomaly Detection", arXiv preprint arXiv:1802.06222, ~ (2018)
  51. Federico Di Mattia, "A Survey on Gans for Anomaly Detection", arXiv preprint arXiv:1906.11632, ~ (2019)
  52. Xuan Xia, "Gan-Based Anomaly Detection: A Review", Neurocomputing (2022)
  53. Ian Goodfellow, "Generative adversarial networks", Communications of the ACM, 63(11), pp.139~144 (2020)
  54. Thomas Schlegl, "Unsupervised anomaly detection with generative adversarial networks to guide marker discovery", International Conference on Information Processing in Medical Imaging, pp.146~157 (2017), Springer
  55. Dan Li, "Mad-gan: Multivariate Anomaly Detection for Time Series Data with Generative Adversarial Networks", ICANN (2019)
  56. Yeji Choi, "Gan-based anomaly detection and localization of multivariate time series data for power plant", 2020 IEEE International Conference on Big Data and Smart Computing (Big-Comp), pp.71~74 (2020), IEEE
  57. Seung Geun Kim, "Development of a generative-adversarial-network-based signal reconstruction method for nuclear power plants", Annals of Nuclear Energy, 142, pp.107410~ (2020)
  58. Xiangyu Li, "Research on anomaly detection method of nuclear power plant operation state based on unsupervised deep generative model", Annals of Nuclear Energy, 167, pp.108785~ (2022)
  59. Anders Brandt, "Noise and Vibration Analysis : Signal Analysis and Experimental Procedures" (2011), John Wiley & Sons
  60. "Engauge digitizer software" (2017)[URL]
  61. Duygu Bayram, "Redundancy-based predictive fault detection on electric motors by stationary wavelet transform", IEEE Transactions on Industry Applications, 53(3), pp.2997~3004 (2016)
  62. Hocine Bendjama, "Application of wavelet transform for fault diagnosis in rotating machinery", International Journal of machine Learning and computing, 2(1), pp.82~87 (2012)
  63. Wahyu Caesarendra, "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), pp.21~ (2017)
  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), pp.218~227 (2014)
  65. Samet Akcay, "Ganomaly: semisupervised anomaly detection via adversarial training", Asian Conference on Computer Vision, pp.622~637 (2018), Springer
  66. Dan Li, "Anomaly Detection with Generative Adversarial Networks for Multivariate Time Series", arXiv preprint arXiv:1809.04758, ~ (2018)
  67. Dan Li, "Madgan:multivariate anomaly detection for time series data with generative adversarial networks", International Conference on Artificial Neural Networks, pp.703~716 (2019), Springer
  68. Ferhat Ozgür Çatak, "Robust ensemble classifier combination based on noise removal with one-class svm", International Conference on Neural Information Processing, pp.10~17 (2015), Springer
  69. Katherine Heller, "One Class Support Vector Machines for Detecting Anomalous Windows Registry Accesses", Columbia Academic Commons (2003)
  70. Shen Yin, "Fault detection based on a robust one class support vector machine", Neurocomputing, 145, pp.263~268 (2014)
  71. S. Sathiya Keerthi, "Asymptotic behaviors of support vector machines with Gaussian kernel", Neural Computation, 15(7), pp.1667~1689 (2003)
  72. Yingchao Xiao, "Parameter selection of Gaussian kernel for one-class svm", IEEE Transactions on Cybernetics, 45(5), pp.941~953 (2014)
  73. Fei Tony Liu, "Isolation forest", 2008 Eighth Ieee International Conference on Data Mining, pp.413~422 (2008), IEEE
  74. Chandresh Kumar Maurya, "Online anomaly detection via class-imbalance learning", 2015 Eighth International Conference on Contemporary Computing (IC3), pp.30~35 (2015), IEEE

관련 논문AI추천

Consistency check algorithm for validation and re-diagnosis to improve the accuracy of abnormality diagnosis in nuclear power plants김근희, 김재민, 신지현, 이승준한국원자력학회 · Nuclear Engineering and Technology2022 · 제54권 제10호Imbalanced data fault diagnosis method for nuclear power plants based on convolutional variational autoencoding Wasserstein generative adversarial network and random forestDu Baigang, Guo Jun, Liu Shiqiao, Sun Xiang, Wang Yulong한국원자력학회 · Nuclear Engineering and Technology2024 · 제56권 제12호Analysis of human errors in nuclear power plant event reportsChen Wenming, Dai Licao, Pang Ensheng, Zhang Meihui한국원자력학회 · Nuclear Engineering and Technology2025 · 제57권 제10호Development of an AI-based remaining trip time prediction system for nuclear power plants나만균, 박지훈, 오상원, 조혜선한국원자력학회 · Nuclear Engineering and Technology2024 · 제56권 제8호Approach to diagnosing multiple abnormal events with single-event training data구서룡, 신지현, 이승준, 조승규한국원자력학회 · Nuclear Engineering and Technology2024 · 제56권 제2호Event diagnosis method for a nuclear power plant using meta-learning김종현, 이대일, 이희재한국원자력학회 · Nuclear Engineering and Technology2024 · 제56권 제6호

이 간행물의 다른 논문 (39건)

Separation and purification of elements from alkaline and carbonate nuclear waste solutionsSafiulina Alfiya M., Kostikova Galina V., Zhilov Valeriy I., Tsivadze Aslan Yu, Boyarintsev Alexander V., Stepanov Sergei I.pp. 391-407Beryllium oxide utilized in nuclear reactors: Part II: A systematic review of the neutron irradiation effectsZhou Xiang-wen, Hou Ming-dong, Liu Bingpp. 408-420Retrieval methodology for similar NPP LCO cases based on domain specific NLP성풍현, 이재희, 이종범, 성노규pp. 421-431Developing an interface strength technique using the laser shock methodSmith James A., Benefiel Bradley C., Scott Clark L.pp. 432-442TinyML Gamma Radiation ClassifierPietrosemoli Ermanno, Zennaro Marco, Altayeb Moezpp. 443-451
원문 보기