Comparison of bootstrapped artificial neural networks and quadratic response surfaces for the estimation of the functional failure probability of a thermal-hydraulic passive system

In this work, bootstrapped artificial neural network (ANN) and quadratic response surface (RS) empirical regression models are used as fast-running surrogates of a thermal-hydraulic (T-H) system code to reduce the computational burden associated with estimation of functional failure probability of a T-H passive system. The ANN and quadratic RS models are built on a few data representative of the input/output nonlinear relationships underlying the T-H code. Once built, these models are used for performing, in reasonable computational time, the numerous system response calculations required for failure probability estimation. A bootstrap of the regression models is implemented for quantifying, in terms of confidence intervals, the uncertainties associated with the estimates provided by ANNs and RSs. The alternative empirical models are compared on a case study of an emergency passive decay heat removal system of a gas-cooled fast reactor (GFR).

[1]  Enrico Zio,et al.  Functional failure analysis of a thermal-hydraulic passive system by means of Line Sampling , 2009, Reliab. Eng. Syst. Saf..

[2]  Enrico Zio,et al.  Estimation of the Functional Failure Probability of a Thermal Hydraulic Passive System by Subset Simulation , 2009 .

[3]  Luciano Burgazzi.  State of the art in reliability of thermal-hydraulic passive systems , 2007, Reliab. Eng. Syst. Saf..

[4]  Geoffrey E. Hinton,et al.  Learning internal representations by error propagation , 1986 .

[5]  Jian Deng,et al.  Structural reliability analysis for implicit performance function using radial basis function network , 2006 .

[6]  Halbert White,et al.  Bootstrapping Confidence Intervals for Clinical Input Variable Effects in a Network Trained to Identify the Presence of Acute Myocardial Infarction , 1995, Neural Computation.

[7]  E. Zio,et al.  A study of the bootstrap method for estimating the accuracy of artificial neural networks in predicting nuclear transient processes , 2006, IEEE Transactions on Nuclear Science.

[8]  James L. McClelland,et al.  Parallel distributed processing: explorations in the microstructure of cognition, vol. 1: foundations , 1986 .

[9]  George E. Apostolakis,et al.  Risk-Informed Design Changes in a Passive Decay Heat Removal System , 2008 .

[10]  D. Cacuci,et al.  A Comparative Review of Sensitivity and Uncertainty Analysis of Large-Scale Systems—II: Statistical Methods , 2004 .

[11]  Henri P. Gavin,et al.  High-order limit state functions in the response surface method for structural reliability analysis , 2008 .

[12]  George E. Apostolakis,et al.  The Impact of Uncertainties on the Performance of Passive Systems , 2005 .

[13]  George Cybenko,et al.  Approximation by superpositions of a sigmoidal function , 1989, Math. Control. Signals Syst..

[14]  Gérard Dreyfus,et al.  Towards the Optimal Design of Numerical Experiments , 2008, IEEE Transactions on Neural Networks.

[15]  G. I. Schuëller,et al.  On the treatment of uncertainties in structural mechanics and analysis , 2007 .

[16]  Enrico Zio,et al.  A model based on bootstrapped neural networks for computing the maximum fuel cladding temperature in an Rmbk-1500 nuclear reactor accident , 2008 .

[17]  Vicki L. Sauter,et al.  Implementation and Evaluation , 2011 .

[18]  Jon C. Helton,et al.  Survey of sampling-based methods for uncertainty and sensitivity analysis , 2006, Reliab. Eng. Syst. Saf..

[19]  L. Burgazzi.  Reliability Evaluation of Passive Systems Through Functional Reliability Assessment , 2003 .

[20]  Francesco Saverio D'Auria,et al.  Reliability evaluation of a natural circulation system , 2003 .

[21]  Jon C. Helton,et al.  Alternative representations of epistemic uncertainty , 2004, Reliab. Eng. Syst. Saf..

[22]  Thomas Most,et al.  A comparison of approximate response functions in structural reliability analysis , 2008 .

[23]  M. G. Marietta,et al.  Uncertainty and sensitivity analysis results obtained in the 1992 performance assessment for the waste isolation pilot plant , 1996 .

[24]  Qiusheng Li,et al.  A new artificial neural network-based response surface method for structural reliability analysis , 2008 .

[25]  George E. Apostolakis,et al.  Incorporating reliability analysis into the design of passive cooling systems with an application to a gas-cooled reactor , 2008 .

[26]  Jon C. Helton,et al.  Implementation and evaluation of nonparametric regression procedures for sensitivity analysis of computationally demanding models , 2009, Reliab. Eng. Syst. Saf..

[27]  C. Bassi,et al.  Reliability Assessment of 2400 MWth Gas-Cooled Fast Reactor Natural Circulation Decay Heat Removal in Pressurized Situations , 2008 .

[28]  Olivier Roustant,et al.  Calculations of Sobol indices for the Gaussian process metamodel , 2008, Reliab. Eng. Syst. Saf..

[29]  Jack W. Baker,et al.  Incorporating modeling uncertainties in the assessment of seismic collapse risk of buildings , 2009 .

[30]  Luciano Burgazzi,et al.  Thermal-hydraulic passive system reliability-based design approach , 2007, Reliab. Eng. Syst. Saf..

[31]  George Cybenko,et al.  Approximation by superpositions of a sigmoidal function , 1992, Math. Control. Signals Syst..

[32]  A. Introduction,et al.  AN APPROACH FOR USING PROBABILISTIC RISK ASSESSMENT IN RISK-INFORMED DECISIONS ON PLANT- SPECIFIC CHANGES TO THE LICENSING BASIS , 2009 .

[33]  Jorge E. Hurtado,et al.  Filtered importance sampling with support vector margin: A powerful method for structural reliability analysis , 2007 .

[34]  Susan A. Murphy,et al.  Monographs on statistics and applied probability , 1990 .

[35]  G. Apostolakis.  The concept of probability in safety assessments of technological systems. , 1990, Science.

[36]  B. Iooss,et al.  Global sensitivity analysis for a numerical model of radionuclide migration from the RRC “Kurchatov Institute” radwaste disposal site , 2008 .

[37]  F. D'Auria,et al.  Methodology for the reliability evaluation of a passive system and its integration into a Probabilistic Safety Assessment , 2005 .

[38]  Pedro G. Coelho,et al.  Structural reliability analysis using Monte Carlo simulation and neural networks , 2008, Adv. Eng. Softw..

[39]  A. John Arul,et al.  Functional reliability analysis of Safety Grade Decay Heat Removal System of Indian 500 MWe PFBR , 2008 .

[40]  Ricardo O. Foschi,et al.  Performance-based design and seismic reliability analysis using designed experiments and neural networks , 2004 .

[41]  Christopher M. Bishop,et al.  Neural networks for pattern recognition , 1995 .

[42]  Enrico Zio,et al.  Quantifying uncertainties in the estimation of safety parameters by using bootstrapped artificial neural networks , 2008 .