An accident diagnosis algorithm using long short-term memory

Abstract Accident diagnosis is one of the complex tasks for nuclear power plant (NPP) operators. In abnormal or emergency situations, the diagnostic activity of the NPP states is burdensome though necessary. Numerous computer-based methods and operator support systems have been suggested to address this problem. Among them, the recurrent neural network (RNN) has performed well at analyzing time series data. This study proposes an algorithm for accident diagnosis using long short-term memory (LSTM), which is a kind of RNN, which improves the limitation for time reflection. The algorithm consists of preprocessing, the LSTM network, and postprocessing. In the LSTM-based algorithm, preprocessed input variables are calculated to output the accident diagnosis results. The outputs are also postprocessed using softmax to determine the ranking of accident diagnosis results with probabilities. This algorithm was trained using a compact nuclear simulator for several accidents: a loss of coolant accident, a steam generator tube rupture, and a main steam line break. The trained algorithm was also tested to demonstrate the feasibility of diagnosing NPP accidents.

[1]  Kazuhiko Kudo,et al.  On-line neuro-expert monitoring system for Borssele Nuclear Power Plant , 2003 .

[2]  Kazuhiko Kudo,et al.  The Development of Anomaly Diagnosis Method Using Neuro-Expert for PWR Monitoring System , 2006 .

[3]  Mark J. Embrechts,et al.  Hybrid identification of nuclear power plant transients with artificial neural networks , 2004, IEEE Transactions on Industrial Electronics.

[4]  D. Woods.  Coping with complexity: the psychology of human behaviour in complex systems , 1988 .

[5]  Charles Elkan,et al.  Learning to Diagnose with LSTM Recurrent Neural Networks , 2015, ICLR.

[6]  David Meister,et al.  Cognitive behavior of nuclear reactor operators , 1995 .

[7]  Geoffrey Zweig,et al.  Joint Language and Translation Modeling with Recurrent Neural Networks , 2013, EMNLP.

[8]  Jasper Snoek,et al.  Practical Bayesian Optimization of Machine Learning Algorithms , 2012, NIPS.

[9]  Poong Hyun Seong,et al.  A dynamic neural network based accident diagnosis advisory system for nuclear power plants , 2005 .

[10]  Feng Jia,et al.  An Intelligent Fault Diagnosis Method Using Unsupervised Feature Learning Towards Mechanical Big Data , 2016, IEEE Transactions on Industrial Electronics.

[11]  James A. Reggia,et al.  A generalized LSTM-like training algorithm for second-order recurrent neural networks , 2012, Neural Networks.

[12]  J. Vohradský.  Neural network model of gene expression , 2001, FASEB journal : official publication of the Federation of American Societies for Experimental Biology.

[13]  P. F. Fantoni,et al.  A pattern recognition-artificial neural networks based model for signal validation in nuclear power plants , 1996 .

[14]  Shri Kant.  Machine Learning and Pattern Recognition , 2010 .

[15]  Marcus Liwicki,et al.  A novel approach to on-line handwriting recognition based on bidirectional long short-term memory networks , 2007 .

[16]  Samy Bengio,et al.  Show and tell: A neural image caption generator , 2014, 2015 IEEE Conference on Computer Vision and Pattern Recognition (CVPR).

[17]  Gopika Vinod,et al.  Application of artificial neural networks to nuclear power plant transient diagnosis , 2007, Reliab. Eng. Syst. Saf..

[18]  Pierre Baldi,et al.  Improving the prediction of protein secondary structure in three and eight classes using recurrent neural networks and profiles , 2002, Proteins.

[19]  Khalil Moshkbar-Bakhshayesh,et al.  Transient identification in nuclear power plants: A review , 2013 .

[20]  J. K. Vaurio.  Safety-related decision making at a nuclear power plant , 1998 .

[21]  Yong-kuo Liu,et al.  Knowledge base operator support system for nuclear power plant fault diagnosis , 2018 .

[22]  Kee-Choon Kwon,et al.  Accident identification in nuclear power plants using hidden Markov models , 1999 .

[23]  Tom Kontogiannis,et al.  Stress and operator decision making in coping with emergencies , 1996, Int. J. Hum. Comput. Stud..

[24]  Quoc V. Le,et al.  Sequence to Sequence Learning with Neural Networks , 2014, NIPS.

[25]  Wondea Jung,et al.  A study on the systematic framework to develop effective diagnosis procedures of nuclear power plants , 2004, Reliab. Eng. Syst. Saf..

[26]  Fei-Fei Li,et al.  Deep visual-semantic alignments for generating image descriptions , 2015, CVPR.

[27]  Mauro Vitor de Oliveira,et al.  HSI for monitoring the critical safety functions status tree of a NPP , 2013 .

[28]  Tao Zhang,et al.  Bearing fault diagnosis method based on stacked autoencoder and softmax regression , 2015, 2015 34th Chinese Control Conference (CCC).

[29]  Yoshua Bengio,et al.  Random Search for Hyper-Parameter Optimization , 2012, J. Mach. Learn. Res..

[30]  Robert E. Uhrig,et al.  COMPUTATIONAL INTELLIGENCE IN NUCLEAR ENGINEERING , 2005 .

[31]  Poong Hyun Seong,et al.  A dynamic neural network aggregation model for transient diagnosis in nuclear power plants , 2007 .

[32]  Jürgen Schmidhuber,et al.  Long Short-Term Memory , 1997, Neural Computation.

[33]  Emine Ayaz,et al.  Elman's recurrent neural network applications to condition monitoring in nuclear power plant and rotating machinery , 2003 .