Application of a Deep Learning Technique to the Development of a Fast Accident Scenario Identifier

To obtain more accurate results of probabilistic safety assessment (PSA), it is necessary to reflect more complete dynamics of nuclear power plants. In analyzing these more realistic PSA models, numerous thermal-hydraulic code runs should be performed that typically take from a few minutes to several hours. This paper proposes a fast running model using deep learning techniques to obtain plausible accident scenarios while reducing the resources required to conduct PSA. The developed model is built from a conditional autoencoder, and an analysis of its performance is carried out under both trained and untrained ranges. Taking about one second per scenario, the developed model shows about 0.4% and 1.6% error in the trained and untrained ranges, respectively. As a feasibility study, the aggressive cooldown operation under a small break loss-of-coolant accident in the APR1400 plant was considered. The proposed method can reduce uncertainty in PSA and contribute a key technique to dynamic PSA.

[1]  Carol-Sophie Smidts,et al.  Probabilistic reactor dynamics. II: A Monte Carlo study of a fast reactor transient , 1992 .

[2]  Koray Kavukcuoglu,et al.  Pixel Recurrent Neural Networks , 2016, ICML.

[3]  Michael Yau,et al.  Development of tools for safety analysis of control software in advanced reactors , 1996 .

[4]  Jian Sun,et al.  Delving Deep into Rectifiers: Surpassing Human-Level Performance on ImageNet Classification , 2015, 2015 IEEE International Conference on Computer Vision (ICCV).

[5]  D. Dickey,et al.  Testing for unit roots in autoregressive-moving average models of unknown order , 1984 .

[6]  E. Zio,et al.  Identification of nuclear transients via optimized fuzzy clustering , 2005 .

[7]  Enrico Zio,et al.  An optimized Line Sampling method for the estimation of the failure probability of nuclear passive systems , 2010, Reliab. Eng. Syst. Saf..

[8]  Kwang-Il Ahn,et al.  A new approach for measuring uncertainty importance and distributional sensitivity in probabilistic safety assessment , 1994 .

[9]  Heiga Zen,et al.  WaveNet: A Generative Model for Raw Audio , 2016, SSW.

[10]  Kurt Hornik,et al.  Neural networks and principal component analysis: Learning from examples without local minima , 1989, Neural Networks.

[11]  Lukasz Kaiser,et al.  Attention is All you Need , 2017, NIPS.

[12]  Yoshua Bengio,et al.  Understanding the difficulty of training deep feedforward neural networks , 2010, AISTATS.

[13]  Pascal Vincent,et al.  Stacked Denoising Autoencoders: Learning Useful Representations in a Deep Network with a Local Denoising Criterion , 2010, J. Mach. Learn. Res..

[14]  Enrique Meléndez,et al.  Automatic Generation of Dynamic Event Trees: A Tool for Integrated Safety Assessment (ISA) , 1994 .

[15]  Geoffrey E. Hinton,et al.  Learning representations by back-propagating errors , 1986, Nature.

[16]  Sang-Hoon Han,et al.  MOSAIQUE – A network based software for probabilistic uncertainty analysis of computerized simulation models , 2011 .

[17]  Max Welling,et al.  Auto-Encoding Variational Bayes , 2013, ICLR.

[18]  Paolo F. Fantoni,et al.  Multiple-Failure Signal Validation in Nuclear Power Plants Using Artificial Neural Networks , 1996 .

[19]  M. Kramer.  Nonlinear principal component analysis using autoassociative neural networks , 1991 .

[20]  Borut Mavko,et al.  A dynamic fault tree , 2002, Reliab. Eng. Syst. Saf..

[21]  N. Siu,et al.  Dynamic event trees in accident sequence analysis: application to steam generator tube rupture , 1993 .

[22]  Yves Dutuit,et al.  Dependability modelling and evaluation by using stochastic Petri nets: application to two test cases , 1997 .

[23]  J. Devooght,et al.  Probabilistic Reactor Dynamics —I: The Theory of Continuous Event Trees , 1992 .

[24]  Eduard Hofer,et al.  An approximate epistemic uncertainty analysis approach in the presence of epistemic and aleatory uncertainties , 2002, Reliab. Eng. Syst. Saf..

[25]  Klaus-Robert Müller,et al.  Efficient BackProp , 2012, Neural Networks: Tricks of the Trade.

[26]  John Andrews,et al.  Dependency modelling using fault tree analysis , 1999 .

[27]  Yoshua Bengio,et al.  Generative Adversarial Nets , 2014, NIPS.

[28]  N. O. Siu,et al.  A simulation model for dynamic system availability analysis , 1989 .

[29]  Robert E. Uhrig,et al.  Use of Autoassociative Neural Networks for Signal Validation , 1998, J. Intell. Robotic Syst..

[30]  Jaewhan Kim,et al.  Realistic estimation of human error probability through Monte Carlo thermal-hydraulic simulation , 2020, Reliab. Eng. Syst. Saf..

[31]  Ming-Wei Chang,et al.  BERT: Pre-training of Deep Bidirectional Transformers for Language Understanding , 2019, NAACL.

[32]  Pierre-Etienne Labeau,et al.  DDET and Monte Carlo simulation to solve some dynamic reliability problems , 1998 .

[33]  Alán Aspuru-Guzik,et al.  Automatic Chemical Design Using a Data-Driven Continuous Representation of Molecules , 2016, ACS central science.

[34]  Enrico Zio,et al.  Comparison of bootstrapped artificial neural networks and quadratic response surfaces for the estimation of the functional failure probability of a thermal-hydraulic passive system , 2010, Reliab. Eng. Syst. Saf..

[35]  Richard Hans Robert Hahnloser,et al.  Digital selection and analogue amplification coexist in a cortex-inspired silicon circuit , 2000, Nature.

[36]  M. Ristic,et al.  OPERATING EXPERIENCE WITH NUCLEAR POWER STATIONS IN MEMBER STATES. A Review Prepared in September 1970. , 1970 .

[37]  Xi Chen,et al.  PixelCNN++: Improving the PixelCNN with Discretized Logistic Mixture Likelihood and Other Modifications , 2017, ICLR.