A Computer Program for Evaluating the Alpha Factor Model Parameters Using the Bayesian Operation
|
|
- Ethelbert Gordon
- 5 years ago
- Views:
Transcription
1 Computer Program for Evaluating the lpha actor odel Parameters Using the Bayesian Operation Baehyeuk Kwon a, oosung Jae a*, and Dong Wook Jerng b a Department of Nuclear Engineering, Hanyang University 17 Haengdang-Dong, Sungdong-u, Seoul, Korea b Department of Energy Systems Engineering, Chung-ng University 84 Heukseok-Ro, Dongjak-u, Seoul, Korea *Correspondence: jae@hanyang.ac.kr bstract: The assessment of common cause failure (CC) is necessary for reducing the uncertainty during the process of probabilistic safety assessment. basic unavailability assessment method is an approach for the quantitative analysis of CC modeling using Bayesian probability, in which the estimation of parameters is more accurate by combining the failure information from system, component and cause level. This study describes the CC evaluation program which has been developed for assessing the α-factor common cause failure parameters. Examples are presented to demonstrate the calculation process and necessary databases are presented. s a result, the posterior s for α-factors model parameter are obtained using the conjugate family s as well as general s for conducting a numerical estimation. Due to the fact that CC is one of the significant factors to affect both core damage frequency and large early release frequency, the appropriate evaluation for the relevant parameters is essential, though there are rare the CC data. In the previous study, the ultiple reek etter model () had been used for modeling the common cause failures in the OPR 1000 reactors. In the future modeling for the reactors, the α-factors approach might be employed for simulating the common cause failures as well as it will be quantified using the computer program developed by the C# language. The main operation to quantify the α-factors parameters is Bayesian which combines the prior and the likelihood function to produce the posterior. It is expected that this program might contribute to enhancing the quality of probabilistic safety assessment and to reducing common cause failure uncertainty. Keywords: common cause failure, ultiple reek etter model, α-factors model, Bayesian, parameter uncertainty, data analysis 1. INTRODUCTION Since the quantitative analysis about the Common Cause ailure (CC) was first attempted in WSH-1004 [1], the various quantitative CC have been suggested. These for the CC analysis were synthetically analyzed in NURE/CR-4780 [2-3] and have been mostly used in the probability safety assessment (PS). The Common Cause ailure events occur when one or more components fail simultaneously or around same time due to a common cause. Due to the fact that CC is one of the significant factors to affect Core Damage requency and arge Early Release requency, systematic and accurate evaluation of the CC parameter is essential. However, it is practically impossible to perform CC analysis accurately with the lack of CC data just for one Nuclear Power Plant because CC is rare event. To address this problem, NURE/CR-5485 [4] reported the various CC parameter estimation methods based on the Bayesian method, which can reduce the CC parameter uncertainty using CC data not only of the reference Nuclear Power Plants but also of other NPPs. Up to now, PS in Korea has performed the CC analysis using beta factor model or ultiple reek etter () model and mainly used the CC parameter data provided by USNRC. The CC parameter data provided by USNRC, however, is currently the CC parameter data of lpha-actor odel (). Thus, the CC parameters used for the CC analysis in Korea have used parameters converted form parameters to parameter. In this case, the PS researchers have not performed the Bayesian updating for reducing uncertainty of the parameters due to the Probabilistic Safety ssessment and anagement PS 12, June 2014, Honolulu, Hawaii
2 fact that conversions of these CC parameters cannot know the parameters. or this reason, therefore the parameter has been used popularly to perform PS for Korean plants. In this study, therefore, the Bayesian-based CC parameters estimation program using α-factors parameter data has been developed for evaluating the CC parameters and applied for the system of the reference plant to obtain the uncertainty data of the parameters in model. The calculation algorithm of this program using the Bayesian method has been developed and programmed by the C# language in this study. 2. ETHODOOY 2.1. CC parametric The Bayesian-based CC parameters estimation program developed in this study consists of various CC. ultiple reek etter () model and lpha-actor odel () as shown in table 1 are important in this study. The estimation approaches of each parameter of the CC model are different. However, these CC have same value when parameters of the model and model can be converted to parameter of Basic Parameter odel (BP) following the conversion formulas described in table 2. Depending on the reason of these, the developed program in this study uses the relation of and. CC Table 1. Parameters of the CC model CC parameter Non-Staggered testing (NS) Staggered testing (S) ( 1,,,,..., 0) m 1 Probabilistic Safety ssessment and anagement PS 12, June 2014, Honolulu, Hawaii
3 CC Table 2. CC conversion parameters to Basic Parameter odel CC parameter Non-Staggered testing (NS) Staggered testing (S) ( 1,,,,..., 0) m CC ultiplier The conversion formulas in Table 2, however, cannot be practically used due to fact that the total failure probability of each component (Q t ) is unavailable generally. Due to the fact that the CC events rarely occur, the values of Q t and Q 1 are almost the same as shown in Eq. (1). Therefore, for calculation of the failure probability involving k specific components (Q k ), the CC multiplier ( k ) is first calculated. Q k is converted to the approximated equations to be practically used as shown in Eq. (2). In these equations, k and Q 1 are CC multiplier and single failure probability, respectively. The program developed in this study was designed to easily calculate CC multipliers for both and as shown in Table 3. (2) (1) Probabilistic Safety ssessment and anagement PS 12, June 2014, Honolulu, Hawaii
4 CC Table 3. CC ultipliers ormula CC parameter Non-Staggered testing (NS) Staggered testing (S) ( 1,,,,..., 0) m Bayes Theory Up to now there has been no detail guidance for estimating the CC parameters using the Bayesian method in an uncertainty analysis. In this study the Bayesian method has been introduced and applied for reducing the uncertainty of the common cause failures. The basic equation of the Bayesian theory [5-6] is described as follows. (3) Where, ( / E) is posterior of given evidence E, ( ) 0 is of prior to the evidence, and E ( / ) is likelihood function or the probability of the evidence E for the given. Table 4. Conjugate family s of Bayes operation ikelihood Conjugate prior Posterior Binomial Distribution Beta Beta ulti-nominal Dirichlet Dirichlet The likelihood function for common cause failure parameters depends on the common cause failure and has the corresponding conjugate as shown in Table 4. The posterior is proportional to the product of prior and the likelihood function as shown in Eq. 4. By applying the normalization factors into denominator, the Bayesian data analysis for the common cause failure parameters can be performed to result in determining the posterior as shown in Eq. (2). Bayesian analysis can be used as an efficient data analysis method among moments method, the curve fitting method, maximum likelihood method and Bayes method. (4) Probabilistic Safety ssessment and anagement PS 12, June 2014, Honolulu, Hawaii
5 2.4. Parameter s The C# program named COCP (Common Cause ailure Parameter Estimation for PS), has been developed and applied to obtain the common cause failure parameters. The parameters of the common cause failure can be obtained using the Beta conjugate family as sown in Table 4. The Bayesian approach results are shown in Table 5. It involves the systematic approach about how to combine the prior and the likelihood function to produce the posterior. Thus, the developed program, COCP, can not only estimate the CC parameter but also perform the Bayesian updating of the CC parameters of the important systems in the reference nuclear power plants. CC Table 5. Distribution of the CC parameter CC parameter Beta (a, b) Non-Staggered (NS) testing Staggered (S) Testing Beta (a, b) 3. RESUTS 3.1. Computer Program, COCP To evaluate the parameter s and the common cause failure uncertainty, a computer program named COCP (Common Cause ailure Parameter Estimation for PS), has been developed using the C# language. igure 1 shows the main screen of the program developed in this study. This program might contribute to evaluating easily the common cause failure analysis related to the ultiple reek etter model and lpha-actor odel. The developed program involves the Common Cause Component roup (CCC = m) which may be applied from a value of 2 to 8. The output data of the user-selected CC parameters offered in this program provides prior, likelihood and posterior for the parameters of the ultiple reek etter model and lpha-actor odel as shown in igure 2. Each provides the confidence interval such as 5 %, 50 %, and 95 %, mean values for the Beta (a, b). The COCP computer program consists of four functions which are Input module, Conversion module, Run module and Help module as shown in table 6. The Input module can deal with USNRC lpha-actor odel CC parameters [7] in which users can select the appropriate CC parameters considering the relevant system, failure mode, type of component, and system size. The Conversion Probabilistic Safety ssessment and anagement PS 12, June 2014, Honolulu, Hawaii
6 function module can convert from parameters to parameters easily. The common cause failure multiplier function supplies the function to calculate the multiplying values for the CC parameters selected by the analyzing user. The Bayesian analysis function module supplies the function to perform the Bayesian-updating for the CC parameter when the user allocates the actual number of the CC events in likelihood menu of the computer program. Table 6 : ain functions used in the computer program, COCP ain function Input data Conversion Bayesian analysis Description Connect database Selection of NRC CC data (2007) to conversion (CC parameter) to conversion (CC parameter) Bayesian analysis of / parameter / multiplier calculation igure 1. ain screen of the program (a) parameter output frame (b) parameter output frame igure 2. Parameter Output obtained from the program 3.2 Execution of the computer program Probabilistic Safety ssessment and anagement PS 12, June 2014, Honolulu, Hawaii
7 The common cause failure parameters have been evaluated using the program, COCP developed in this study under the particular assumed conditions. or demonstrating the program execution process, the prior data of the auxiliary feedwater system, motor driven pump, and fail to start for CCC=3 are utilized. The USNRC CC parameter estimations used in this study are shown in Table 7 while the likelihood data are shown in the Table 8. To execute the developed program, the parameters data of the CC have been calculated individually using the model and model and they are compared each other. Table 9 shows the Bayesian updating results showing that the calculated CC multiplier values are exactly identical regardless of the model types depending on the conditions. It is shown that the program, COCP might evaluate the parameter s of the model and model properly without any problems. Table 7. Prior data CCC ail mode α-factors lpha 1 lpha 2 lpha 3 Parameter of a 1.89E E E+00 beta b 8.16E E E+02 m=3 ail to 5% 9.33E E E-03 Start Percentiles 50% 9.60E E E-02 95% 9.79E E E-02 ean 9.59E E E-02 Table 8. ikelihood data CCC ail mode α-factors lpha 1 lpha 2 lpha 3 Parameter of a 5.00E E E+00 beta b 7.00E E E+01 m=3 ail to 5% 7.99.E E E-03 Start Percentiles 50% 8.82.E E E-02 95% 9.40.E E E-02 ean 8.77.E E E-02 Table 9. Posterior data and CC multiplier CC CC Non- Staggered CCC m=3 CCC m=3 Staggered m=3 ail mode ail to Start ail mode ail to Start ail to Start CC parameters lpha 1 lpha 2 lpha 3 Parameter of beta a 2.39.E E E+00 b 1.52.E E E+02 5% 9.14.E E E-02 Percentiles 50% 9.41.E E E-02 95% 9.63.E E E-02 ean 9.40.E E E-02 CC multiplier NS 8.86E E E-02 S 9.40E E E-02 CC parameters β γ Parameter of beta a 1.00.E E-01 b 1.31.E E-01 5% 1.67.E E-01 Percentiles 50% 1.32.E E-01 95% 3.63.E E+01 ean 2.39.E E+01 CC multiplier NS 8.86E E E-02 Parameter of beta a 3.74.E E-01 b 5.85.E E-01 5% 8.59.E E-01 Percentiles 50% 5.97.E E-01 95% 1.52.E E+00 ean 2.39.E E+00 CC multiplier S 9.40E E E-02 Probabilistic Safety ssessment and anagement PS 12, June 2014, Honolulu, Hawaii
8 4. CONCUSION The common cause failures in nuclear power plants are one of the significant factors to affect both the values of Core Damage requency and arge Early Release requency. Several investigators have made many efforts to attempt to reduce the common cause failure uncertainty. In this study a methodology using the Bayesian operation has been developed and applied for reducing the uncertainty of the common cause failures. The Bayesian-based CC parameters estimation program called COCP has also been developed for evaluating the common cause failures parameters. It is shown that the COCP program can obtain the parameter s for various common cause failure for both the non-staggered and the staggered tests. It is also shown that this program might contribute to assessing the safety measures such as core damage frequency and large early release frequency. It is expected that the developed program might contribute to supplying the efficient risk assessment procedures by evaluating the uncertainty of the relevant common cause failures parameters of the analyzing systems. cknowledgement This work was supported by the KHNP Central Research Institute s Project and partly by Korea Radiation Safety oundation (rant Code: SB110). References [1] U.S. NRC (Nuclear Regulatory Commission), Reactor Safety Study: n ssessment of ccident Risks in U.S. commercial Nuclear Power Plant, WSH-1400, NURE , [2] osleh and K. N. leming, Pickard, owe, and arrick,., U.S. NRC, Procedure for Treating Common Cause ailures in Safety and Reliability Studies, Procedural ramework and Examples, NURE/CR-4780 Vol 1, [3] osleh and K. N. leming, Pickard, owe and arrick,., U.S. NRC, Procedure for Treating Common Cause ailures in Safety and Reliability Studies, nalytical Background and Techniques, NURE/CR-4780 Vol 2, [4] osleh,., INEE, uidelines on odelling Common-Cause ailures in Probabilistic Risk ssessment, NURE/CR-5485, [5] lfredo H-S. ng, Wilson H. Tang, Probability Concepts in Engineering Planning and Design, Volume I-Basic Principles, pp , [6] Peter. ee, Bayesian Statistics n Introduction, Third Edition, pp , [7] U.S.NRC (Nuclear Regulatory Commission), 2008, CC Parameter Estimations, 2007 Update. Probabilistic Safety ssessment and anagement PS 12, June 2014, Honolulu, Hawaii
Estimation of reliability parameters from Experimental data (Parte 2) Prof. Enrico Zio
Estimation of reliability parameters from Experimental data (Parte 2) This lecture Life test (t 1,t 2,...,t n ) Estimate θ of f T t θ For example: λ of f T (t)= λe - λt Classical approach (frequentist
More informationASSESSMENT OF DYNAMIC PRA TECHNIQUES WITH INDUSTRY- AVERAGE COMPONENT PERFORMANCE DATA
ASSESSMENT OF DYNAMIC PRA TECHNIQUES WITH INDUSTRY- AVERAGE COMPONENT PERFORMANCE DATA Vaibhav Yadav*, Vivek Agarwal, Andrei V. Gribok, and Curtis L. Smith Idaho National Laboratory 2525 Fremont Avenue,
More informationCommon Cause Failures: Extended Alpha Factor method and its Implementation
Common Cause Failures: Extended Alpha Factor method and its Implementation Alexandra Sitdikova Reactor Engineering Division, Jožef Stefan Institute Jamova 39, SI-1000 Ljubljana, Slovenia Institute of Physics
More informationA General Cause Based Methodology for Analysis of Common Cause and Dependent Failures in System Risk and Reliability Assessments
A General Cause Based Methodology for Analysis of Common Cause and Dependent Failures in System Risk and Reliability Assessments Andrew O Connor a*, Ali Mosleh b a1 Center for Risk and Reliability, University
More informationPresentation of Common Cause Failures in Fault Tree Structure of Krško PSA: An Historical Overview
International Conference Nuclear Energy for New Europe 2003 Portorož, Slovenia, September 8-11, 2003 http://www.drustvo-js.si/port2003 Presentation of Common Cause Failures in Fault Tree Structure of Krško
More informationTreatment of Expert Opinion Diversity in Bayesian Belief Network Model for Nuclear Digital I&C Safety Software Reliability Assessment
Treatment of Expert Opinion Diversity in Bayesian Belief Network Model for Nuclear Digital I&C Safety Software Reliability Assessment 20 International Topical Meeting on Probabilistic Safety Assessment
More informationTime Dependent Analysis with Common Cause Failure Events in RiskSpectrum
Time Dependent Analysis with Common Cause Failure Events in RiskSpectrum Pavel Krcal a,b and Ola Bäckström a a Lloyd's Register Consulting, Stockholm, Sweden b Uppsala University, Uppsala, Sweden Abstract:
More informationA BAYESIAN SOLUTION TO INCOMPLETENESS
A BAYESIAN SOLUTION TO INCOMPLETENESS IN PROBABILISTIC RISK ASSESSMENT 14th International Probabilistic Safety Assessment & Management Conference PSAM-14 September 17-21, 2018 Los Angeles, United States
More informationHow to predict the probability of a major nuclear accident after Fukushima Da
How to predict the probability of a major nuclear accident after Fukushima Dai-ichi? CERNA Mines ParisTech March 14, 2012 1 2 Frequentist approach Bayesian approach Issues 3 Allowing safety progress Dealing
More informationParametric Models. Dr. Shuang LIANG. School of Software Engineering TongJi University Fall, 2012
Parametric Models Dr. Shuang LIANG School of Software Engineering TongJi University Fall, 2012 Today s Topics Maximum Likelihood Estimation Bayesian Density Estimation Today s Topics Maximum Likelihood
More informationIssues in Dependency Modeling in Multi- Unit Seismic PRA
Issues in Dependency Modeling in Multi- Unit Seismic PRA 1 Taotao Zhou Mohammad Modarres Enrique López Droguett Center for Risk and Reliability University of Maryland, College Park Presented at the PSA-2017,
More informationSequential Importance Sampling for Rare Event Estimation with Computer Experiments
Sequential Importance Sampling for Rare Event Estimation with Computer Experiments Brian Williams and Rick Picard LA-UR-12-22467 Statistical Sciences Group, Los Alamos National Laboratory Abstract Importance
More informationState Nuclear Power Technology Research & Development Center, Beijing, China
Passive system Evaluation by using integral thermal-hydraulic test facility in passive NPP(nuclear power plant) PSA(probabilistic safety assessment) process Ruichang Zhao a, Huajian Chang a, Yang Xiang
More informationCounterintuitive results from Bayesian belief network software reliability model
This document is downloaded from the Digital Open Access Repository of VTT Title Counterintuitive results from Bayesian belief network software reliability model Author(s) Tyrväinen, Tero Citation Research
More informationRisk Analysis Framework for Severe Accident Mitigation Strategy in Nordic BWR: An Approach to Communication and Decision Making
International Topical Meeting on Probabilistic Safety Assessment And Analysis, PSA 2017, September 24-28, 2017. Pittsburgh, PA. Risk Analysis Framework for Severe Accident Mitigation Strategy in Nordic
More informationCS 361: Probability & Statistics
March 14, 2018 CS 361: Probability & Statistics Inference The prior From Bayes rule, we know that we can express our function of interest as Likelihood Prior Posterior The right hand side contains the
More informationFault Tree Modeling for Redundant Multi-Functional Digital Systems
International Journal of Perforability Engineering, Vol. 3, No. 3, July, 2007, pp. 329-336 RAMS Consultants Printed in India Fault Tree Modeling for Redundant Multi-Functional Digital Systes HYUN GOOK
More informationBayesian inference. Fredrik Ronquist and Peter Beerli. October 3, 2007
Bayesian inference Fredrik Ronquist and Peter Beerli October 3, 2007 1 Introduction The last few decades has seen a growing interest in Bayesian inference, an alternative approach to statistical inference.
More informationSHAKING TABLE TEST OF STEEL FRAME STRUCTURES SUBJECTED TO NEAR-FAULT GROUND MOTIONS
3 th World Conference on Earthquake Engineering Vancouver, B.C., Canada August -6, 24 Paper No. 354 SHAKING TABLE TEST OF STEEL FRAME STRUCTURES SUBJECTED TO NEAR-FAULT GROUND MOTIONS In-Kil Choi, Young-Sun
More informationBasic notions of probability theory
Basic notions of probability theory Contents o Boolean Logic o Definitions of probability o Probability laws Objectives of This Lecture What do we intend for probability in the context of RAM and risk
More informationA MULTI-STATE PHYSICS MODELING FOR ESTIMATING THE SIZE- AND LOCATION-DEPENDENT LOSS OF COOLANT ACCIDENT INITIATING EVENT PROBABILITY
MULTI-STTE PHYSICS MODELING FOR ESTIMTING THE SIZE- ND LOCTION-DEPENDENT LOSS OF COOLNT CCIDENT INITITING EVENT PROBBILITY Francesco Di Maio 1, Davide Colli 1, Enrico Zio 1,2, Liu Tao 3, Jiejuan Tong 3
More informationA New Reliability Allocation Method Based on FTA and AHP for Nuclear Power Plant!
A New Reliability Allocation Method Based on FTA and AHP for Nuclear Power Plant! Presented by Rongxiang Hu Contributed by FDS Team Institute of Nuclear Energy Safety Technology (INEST) Chinese Academy
More informationSeminar on Case Studies in Operations Research (Mat )
Seminar on Case Studies in Operations Research (Mat-2.4177) Evidential Uncertainties in Reliability Assessment - Study of Non-Destructive Testing of Final Disposal Canisters VTT, Posiva Backlund, Ville-Pekka
More informationBayesian Technique for Reducing Uncertainty in Fatigue Failure Model
9IDM- Bayesian Technique or Reducing Uncertainty in Fatigue Failure Model Sriram Pattabhiraman and Nam H. Kim University o Florida, Gainesville, FL, 36 Copyright 8 SAE International ABSTRACT In this paper,
More informationBayes theorem and its application to nuclear power plant safety
Bayes theorem and its application to nuclear power plant safety MATSUOKA Takeshi 1, 1 Collage of Nuclear Science and Technology, Harbin Engineering University No145-1, Nantong Street, Nangang District,
More informationUncertainty of the Level 2 PSA for NPP Paks. Gábor Lajtha, VEIKI Institute for Electric Power Research, Budapest, Hungary
Uncertainty of the Level 2 PSA for NPP Paks Gábor Lajtha, VEIKI Institute for Electric Power Research, Budapest, Hungary Attila Bareith, Előd Holló, Zoltán Karsa, Péter Siklóssy, Zsolt Téchy VEIKI Institute
More informationApportioning Transient Combustible Fire Frequency via Areal Factors: More Complicated Than It May Seem
Apportioning Transient Combustible Fire Frequency via Areal Factors: More Complicated Than It May Seem Raymond H.V. Gallucci, Ph.D., P.E. U.S. Nuclear Regulatory Commission (USNRC), MS O-10C15, Washington,
More informationReview of Errors of Containment Integrated Leak Rate Test for Nuclear Power Plants
Review of Errors of Containment Integrated Leak Rate Test for Nuclear Power Plants Manwoong Kim*, Ar Ryum Kim, Dong-Ju Jang, Ku-Young Chung Korea Institute of Nuclear Safety, 62 Gwahak-ro, Yuseong-gu,
More informationBayesian Models in Machine Learning
Bayesian Models in Machine Learning Lukáš Burget Escuela de Ciencias Informáticas 2017 Buenos Aires, July 24-29 2017 Frequentist vs. Bayesian Frequentist point of view: Probability is the frequency of
More informationBayesian statistics. DS GA 1002 Statistical and Mathematical Models. Carlos Fernandez-Granda
Bayesian statistics DS GA 1002 Statistical and Mathematical Models http://www.cims.nyu.edu/~cfgranda/pages/dsga1002_fall15 Carlos Fernandez-Granda Frequentist vs Bayesian statistics In frequentist statistics
More informationThe Effects of Activation Energy and Reference Temperature on the Qualified Life of Safety-related Equipment
, pp.1-5 http://dx.doi.org/10.14257/astl.2016.140.01 The Effects of Activation Energy and Reference Temperature on the Qualified Life of Safety-related Equipment Sungwan Park 1, Sunchul Jung 1 and Kyungheum
More informationDevelopment of Multi-Unit Dependency Evaluation Model Using Markov Process and Monte Carlo Method
Development of Multi-Unit Dependency Evaluation Model Using Markov Process and Monte Carlo Method Sunghyon Jang, and Akira Yamaguchi Department of Nuclear Engineering and Management, The University of
More informationPSA Quantification. Analysis of Results. Workshop Information IAEA Workshop
IAEA Training Course on Safety Assessment of NPPs to Assist Decision Making PSA Quantification. Analysis of Results Lecturer Lesson Lesson IV IV 3_7.3 3_7.3 Workshop Information IAEA Workshop City, XX
More informationUnobservable Parameter. Observed Random Sample. Calculate Posterior. Choosing Prior. Conjugate prior. population proportion, p prior:
Pi Priors Unobservable Parameter population proportion, p prior: π ( p) Conjugate prior π ( p) ~ Beta( a, b) same PDF family exponential family only Posterior π ( p y) ~ Beta( a + y, b + n y) Observed
More informationApplied Bayesian Statistics STAT 388/488
STAT 388/488 Dr. Earvin Balderama Department of Mathematics & Statistics Loyola University Chicago August 29, 207 Course Info STAT 388/488 http://math.luc.edu/~ebalderama/bayes 2 A motivating example (See
More informationBasics of Uncertainty Analysis
Basics of Uncertainty Analysis Chapter Six Basics of Uncertainty Analysis 6.1 Introduction As shown in Fig. 6.1, analysis models are used to predict the performances or behaviors of a product under design.
More informationAn Integrated Approach for Characterization of Uncertainty in Complex Best Estimate Safety Assessment
An Integrated Approach for Characterization of Uncertainty in Complex Best Estimate Safety Assessment Presented By Mohammad Modarres Professor of Nuclear Engineering Department of Mechanical Engineering
More informationParametric Techniques Lecture 3
Parametric Techniques Lecture 3 Jason Corso SUNY at Buffalo 22 January 2009 J. Corso (SUNY at Buffalo) Parametric Techniques Lecture 3 22 January 2009 1 / 39 Introduction In Lecture 2, we learned how to
More informationSeismic Issues for California's Nuclear Power Plants. Norman Abrahamson University of California, Berkeley
Seismic Issues for California's Nuclear Power Plants Norman Abrahamson University of California, Berkeley From UCERF 2 Seismic Setting for California s Nuclear Power Plants Major Offshore Strike-Slip Faults
More informationConstrained Noninformative Priors
~ INEL-94/0074 Constrained Noninformative Priors. Corwin L. Atwood c Published October 1994 Idaho National Engineering Laboratory Idaho Falls, Idaho 83415 L Prepared for the U.S. Nuclear Regulatory Commission
More informationBayesian Inference. p(y)
Bayesian Inference There are different ways to interpret a probability statement in a real world setting. Frequentist interpretations of probability apply to situations that can be repeated many times,
More informationHow Fukushima-Daiichi core meltdown changed the probability of nuclear acci
How Fukushima-Daiichi core meltdown changed the probability of nuclear accidents? CERNA Mines ParisTech Paris, March 22, 2013 Motivation Motivations 1 Two weeks after Fukushima Daiichi an article in a
More informationQuantitative evaluation of Dependability
Quantitative evaluation of Dependability 1 Quantitative evaluation of Dependability Faults are the cause of errors and failures. Does the arrival time of faults fit a probability distribution? If so, what
More informationQuantitative Reliability Analysis
Quantitative Reliability Analysis Moosung Jae May 4, 2015 System Reliability Analysis System reliability analysis is conducted in terms of probabilities The probabilities of events can be modelled as logical
More informationParametric Techniques
Parametric Techniques Jason J. Corso SUNY at Buffalo J. Corso (SUNY at Buffalo) Parametric Techniques 1 / 39 Introduction When covering Bayesian Decision Theory, we assumed the full probabilistic structure
More informationComputational Cognitive Science
Computational Cognitive Science Lecture 9: Bayesian Estimation Chris Lucas (Slides adapted from Frank Keller s) School of Informatics University of Edinburgh clucas2@inf.ed.ac.uk 17 October, 2017 1 / 28
More informationEstimating binomial proportions
Estimating binomial proportions Roberto Rossi University of Edinburgh Business School Edinburgh, U Problem description Consider the problem of estimating the parameter p of a random variable which follows
More informationUse of Simulation in Structural Reliability
Structures 008: Crossing Borders 008 ASCE Use of Simulation in Structural Reliability Author: abio Biondini, Department of Structural Engineering, Politecnico di Milano, P.za L. Da Vinci 3, 033 Milan,
More informationBayesian Reliability Analysis: Statistical Challenges from Science-Based Stockpile Stewardship
: Statistical Challenges from Science-Based Stockpile Stewardship Alyson G. Wilson, Ph.D. agw@lanl.gov Statistical Sciences Group Los Alamos National Laboratory May 22, 28 Acknowledgments Christine Anderson-Cook
More informationeqr094: Hierarchical MCMC for Bayesian System Reliability
eqr094: Hierarchical MCMC for Bayesian System Reliability Alyson G. Wilson Statistical Sciences Group, Los Alamos National Laboratory P.O. Box 1663, MS F600 Los Alamos, NM 87545 USA Phone: 505-667-9167
More informationModeling Environment
Topic Model Modeling Environment What does it mean to understand/ your environment? Ability to predict Two approaches to ing environment of words and text Latent Semantic Analysis (LSA) Topic Model LSA
More informationAP1000 European 19. Probabilistic Risk Assessment Design Control Document
19.15 Chemical and Volume Control System 19.15.1 System Description See subsection 9.3.6.2. 19.15.2 System Operation See subsection 9.3.6.4. 19.15.3 Performance during Accident Conditions See subsection
More informationIntroduction to Probabilistic Machine Learning
Introduction to Probabilistic Machine Learning Piyush Rai Dept. of CSE, IIT Kanpur (Mini-course 1) Nov 03, 2015 Piyush Rai (IIT Kanpur) Introduction to Probabilistic Machine Learning 1 Machine Learning
More informationImportance Analysis for Uncertain Thermal-Hydraulics Transient Computations
Importance Analysis for Uncertain Thermal-Hydraulics Transient Computations Mohammad Pourgol-Mohammad *a, Seyed Mohsen Hoseyni b a Department of Mechanical Engineering, Sahand University of Technology,
More informationMachine Learning CMPT 726 Simon Fraser University. Binomial Parameter Estimation
Machine Learning CMPT 726 Simon Fraser University Binomial Parameter Estimation Outline Maximum Likelihood Estimation Smoothed Frequencies, Laplace Correction. Bayesian Approach. Conjugate Prior. Uniform
More informationCHAPTER 2 Estimating Probabilities
CHAPTER 2 Estimating Probabilities Machine Learning Copyright c 2017. Tom M. Mitchell. All rights reserved. *DRAFT OF September 16, 2017* *PLEASE DO NOT DISTRIBUTE WITHOUT AUTHOR S PERMISSION* This is
More informationEstimation of accidental environmental release based on containment measurements
Estimation of accidental environmental release based on containment measurements Péter Szántó, Sándor Deme, Edit Láng, Istvan Németh, Tamás Pázmándi Hungarian Academy of Sciences Centre for Energy Research,
More informationParameter Estimation Method Using Bayesian Statistics Considering Uncertainty of Information for RBDO
th World Congress on Structural and Multidisciplinary Optimization 7 th - 2 th, June 205, Sydney Australia Parameter Estimation Method Using Bayesian Statistics Considering Uncertainty of Information for
More informationCalculation method for the determination of leak probabilities for complex structural geometries and load conditions
3 Reactor safety research 3.1 Calculation method for the determination of leak probabilities for complex structural geometries and load conditions Dr. Jürgen Sievers Yan Wang When it comes to assessing
More informationVariability within multi-component systems. Bayesian inference in probabilistic risk assessment The current state of the art
PhD seminar series Probabilistics in Engineering : g Bayesian networks and Bayesian hierarchical analysis in engeering g Conducted by Prof. Dr. Maes, Prof. Dr. Faber and Dr. Nishijima Variability within
More informationMulti-Unit Nuclear Plant Risks and Implications of the Quantitative Health Objectives
Multi-Unit Nuclear Plant Risks and Implications of the Quantitative Health Objectives Presented at the International Topical Meeting on Probabilistic Safety Assessment and Analysis (PSA2015) April 27,
More informationDEPARTMENT OF COMPUTER SCIENCE Autumn Semester MACHINE LEARNING AND ADAPTIVE INTELLIGENCE
Data Provided: None DEPARTMENT OF COMPUTER SCIENCE Autumn Semester 203 204 MACHINE LEARNING AND ADAPTIVE INTELLIGENCE 2 hours Answer THREE of the four questions. All questions carry equal weight. Figures
More informationReliability Analysis of Power Substation with Common Cause Failure
Reliability Analysis of Power Substation with Common Cause Failure Yoong-Tae Byeon, Kiryang Kwon, Jin-O Kim Hanyang University, Seoul, Korea okim@hanyag.ac.kr Abstract-The power system need to sustain
More information1 A simple example. A short introduction to Bayesian statistics, part I Math 217 Probability and Statistics Prof. D.
probabilities, we ll use Bayes formula. We can easily compute the reverse probabilities A short introduction to Bayesian statistics, part I Math 17 Probability and Statistics Prof. D. Joyce, Fall 014 I
More informationNUCLEAR SAFETY AND RELIABILITY WEEK 3
Nuclear Safety and Reliability Dan Meneley Page 1 of 10 NUCLEAR SAFETY AND RELIABILITY WEEK 3 TABLE OF CONTENTS - WEEK 1 1. Introduction to Risk Analysis...1 Conditional Probability Matrices for Each Step
More informationARTICLE. Downloaded by [Harbin Engineering University] at 18:58 14 June 2013
Journal of Nuclear Science and Technology, 2013 Vol. 50, No. 7, 695 708, http://dx.doi.org/10.1080/00223131.2013.790304 ARTICLE Considerations of uncertainties in evaluating dynamic reliability by GO-FLOW
More informationComputational Perception. Bayesian Inference
Computational Perception 15-485/785 January 24, 2008 Bayesian Inference The process of probabilistic inference 1. define model of problem 2. derive posterior distributions and estimators 3. estimate parameters
More informationBayesian Inference and MCMC
Bayesian Inference and MCMC Aryan Arbabi Partly based on MCMC slides from CSC412 Fall 2018 1 / 18 Bayesian Inference - Motivation Consider we have a data set D = {x 1,..., x n }. E.g each x i can be the
More informationDS-GA 1002 Lecture notes 11 Fall Bayesian statistics
DS-GA 100 Lecture notes 11 Fall 016 Bayesian statistics In the frequentist paradigm we model the data as realizations from a distribution that depends on deterministic parameters. In contrast, in Bayesian
More informationCOMP90051 Statistical Machine Learning
COMP90051 Statistical Machine Learning Semester 2, 2017 Lecturer: Trevor Cohn 17. Bayesian inference; Bayesian regression Training == optimisation (?) Stages of learning & inference: Formulate model Regression
More informationPreliminary Statistics Lecture 2: Probability Theory (Outline) prelimsoas.webs.com
1 School of Oriental and African Studies September 2015 Department of Economics Preliminary Statistics Lecture 2: Probability Theory (Outline) prelimsoas.webs.com Gujarati D. Basic Econometrics, Appendix
More informationA Bayesian model for event-based trust
A Bayesian model for event-based trust Elements of a foundation for computational trust Vladimiro Sassone ECS, University of Southampton joint work K. Krukow and M. Nielsen Oxford, 9 March 2007 V. Sassone
More informationModeling Common Cause Failures in Diverse Components with Fault Tree Applications
Modeling Common Cause Failures in Diverse s with Fault Tree Applications Joseph R. Belland, Isograph Inc. Key Words: Common Cause Failures, Fault Trees, Beta Factor SUMMARY & CONCLUSIONS A common cause
More informationAvailability analysis of nuclear power plant system with the consideration of logical loop structures
Availability analysis of nuclear power plant system with the consideration of logical loop structures MATSUOKA Takeshi 1, 2 1. Mechanical Systems Engineering, Department of Engineering, Utsunomiya University,
More informationRisk Elicitation in Complex Systems: Application to Spacecraft Re-entry
Risk Elicitation in Complex Systems: Application to Spacecraft Re-entry Simon Wilson 1 Cristina De Persis 1 Irene Huertas 2 Guillermo Ortega 2 1 School of Computer Science and Statistics Trinity College
More informationEstimation of Quantiles
9 Estimation of Quantiles The notion of quantiles was introduced in Section 3.2: recall that a quantile x α for an r.v. X is a constant such that P(X x α )=1 α. (9.1) In this chapter we examine quantiles
More informationBayesian Machine Learning
Bayesian Machine Learning Andrew Gordon Wilson ORIE 6741 Lecture 2: Bayesian Basics https://people.orie.cornell.edu/andrew/orie6741 Cornell University August 25, 2016 1 / 17 Canonical Machine Learning
More informationThe Bayesian Choice. Christian P. Robert. From Decision-Theoretic Foundations to Computational Implementation. Second Edition.
Christian P. Robert The Bayesian Choice From Decision-Theoretic Foundations to Computational Implementation Second Edition With 23 Illustrations ^Springer" Contents Preface to the Second Edition Preface
More informationHierarchical sparse Bayesian learning for structural health monitoring. with incomplete modal data
Hierarchical sparse Bayesian learning for structural health monitoring with incomplete modal data Yong Huang and James L. Beck* Division of Engineering and Applied Science, California Institute of Technology,
More informationBayesian Inference for Binomial Proportion
8 Bayesian Inference for Binomial Proportion Frequently there is a large population where π, a proportion of the population, has some attribute. For instance, the population could be registered voters
More informationPrediction of Collapse for Tunnel Portal Slopes using General Linear Model
Disaster Mitigation of Debris Flows, Slope Failures and Landslides 523 Prediction of Collapse for Tunnel Portal Slopes using General Linear Model Yong Baek, 1) Jong-Hwa Na, 2) O-Il Kwon, 3) Yong-Seok Seo
More informationBayesian Inference for Normal Mean
Al Nosedal. University of Toronto. November 18, 2015 Likelihood of Single Observation The conditional observation distribution of y µ is Normal with mean µ and variance σ 2, which is known. Its density
More informationUncertainty Quantification in Performance Evaluation of Manufacturing Processes
Uncertainty Quantification in Performance Evaluation of Manufacturing Processes Manufacturing Systems October 27, 2014 Saideep Nannapaneni, Sankaran Mahadevan Vanderbilt University, Nashville, TN Acknowledgement
More informationDerivation of Paris Law Parameters from S-N Curve Data: a Bayesian Approach
Derivation of Paris Law Parameters from S-N Curve Data: a Bayesian Approach Sreehari Ramachandra Prabhu 1) and *Young-Joo Lee 2) 1), 2) School of Urban and Environmental Engineering, Ulsan National Institute
More informationQuantitative evaluation of Dependability
Quantitative evaluation of Dependability 1 Quantitative evaluation of Dependability Faults are the cause of errors and failures. Does the arrival time of faults fit a probability distribution? If so, what
More informationValue of Information Analysis with Structural Reliability Methods
Accepted for publication in Structural Safety, special issue in the honor of Prof. Wilson Tang August 2013 Value of Information Analysis with Structural Reliability Methods Daniel Straub Engineering Risk
More informationANALYSIS OF INDEPENDENT PROTECTION LAYERS AND SAFETY INSTRUMENTED SYSTEM FOR OIL GAS SEPARATOR USING BAYESIAN METHODS
ANALYSIS OF INDEPENDENT PROTECTION LAYERS AND SAFETY INSTRUMENTED SYSTEM FOR OIL GAS SEPARATOR USING BAYESIAN METHODS G. Unnikrishnan 1 *, Shrihari 2, Nihal A. Siddiqui 3 1 Department of Health, Safety
More informationReliability of Technical Systems
Reliability of Technical Systems Main Topics 1. Short Introduction, Reliability Parameters: Failure Rate, Failure Probability, etc. 2. Some Important Reliability Distributions 3. Component Reliability
More informationA BAYESIAN FRAMEWORK FOR THE QUANTITATIVE MODELLING OF THE ENIQ METHODOLOGY FOR QUALIFICATION OF NON-DESTRUCTIVE TESTING
Institute for Energy A BAYESIAN FRAMEWORK FOR THE QUANTITATIVE MODELLING OF THE ENIQ METHODOLOGY FOR QUALIFICATION OF NON-DESTRUCTIVE TESTING Authors: Luca Gandossi, Kaisa Simola DG JRC Institute for Energy
More informationStudy on Quantification Methodology of accident sequences for Tsunami Induced by Seismic Events.
Study on Quantification Methodology of accident sequences for Tsunami Induced by Seismic Events 1 Keisuke Usui, 2 Hitoshi Muta, 3 Ken Muramatsu 1 Graduate Student, Corporative Major in Nuclear Energy:
More informationModular Bayesian uncertainty assessment for Structural Health Monitoring
uncertainty assessment for Structural Health Monitoring Warwick Centre for Predictive Modelling André Jesus a.jesus@warwick.ac.uk June 26, 2017 Thesis advisor: Irwanda Laory & Peter Brommer Structural
More informationPATTERN RECOGNITION AND MACHINE LEARNING CHAPTER 2: PROBABILITY DISTRIBUTIONS
PATTERN RECOGNITION AND MACHINE LEARNING CHAPTER 2: PROBABILITY DISTRIBUTIONS Parametric Distributions Basic building blocks: Need to determine given Representation: or? Recall Curve Fitting Binary Variables
More informationEvaluation of conformity criteria for reinforcing steel properties
IASSAR Safety, Reliability, Risk, Resilience and Sustainability of Structures and Infrastructure 12th Int. Conf. on Structural Safety and Reliability, Vienna, Austria, 6 10 August 2017 Christian Bucher,
More informationOptimization of the Sulfolane Extraction Plant Based on Modeling and Simulation
Korean J. Chem. Eng., 17(6), 712-718 (2000) Optimization of the Sulfolane Extraction Plant Based on Modeling and Simulation Yu-Jung Choi, Tae-In Kwon and Yeong-Koo Yeo Department of Chemical Engineering,
More informationA Study on Reliability Analysis for Reinforced Earth Retaining Walls
A Study on Reliability Analysis for Reinforced Earth Retaining Walls Byung Sik, Chun Department of Civil Engineering, Hanyang University, Seoul, Korea(Rep.) hengdang@unitel.co.kr Kyung Min, Kim Department
More informationStep-Stress Models and Associated Inference
Department of Mathematics & Statistics Indian Institute of Technology Kanpur August 19, 2014 Outline Accelerated Life Test 1 Accelerated Life Test 2 3 4 5 6 7 Outline Accelerated Life Test 1 Accelerated
More informationBayesian Approach in Structural Tests with Limited Resources
Bayesian Approach in Structural Tests with Limited Resources *Kidong Park 1), David Webber 2), Changsoon Rha 3), Jidae Park 4), & Junggil Lee 1), 2), 4), 5) Health, Safety & Environment Division, Samsung
More informationUniform Hazard Spectrum(UHS) for performance based seismic design
Uniform Hazard Spectrum(UHS) for performance based seismic design *Jun-Kyoung Kim 1), Soung-Hoon Wee 2) and Seong-Hwa Yoo 2) 1) Department of Fire Protection and Disaster Prevention, Semyoung University,
More informationUsing Probability to do Statistics.
Al Nosedal. University of Toronto. November 5, 2015 Milk and honey and hemoglobin Animal experiments suggested that honey in a diet might raise hemoglobin level. A researcher designed a study involving
More informationOUTPUT UPDATING IN SEVERE ACCIDENT UNCERTAINTY ASSESSMENT; A BAYESIAN FRAMEWORK
OUTPUT UPATING IN SEVERE ACCIENT UNCERTAINTY ASSESSMENT; A BAYESIAN FRAMEWORK Mohammad Pourgol-Mohammad 1, Seyed Mohsen Hoseyni 2, 1 epartment of Mechanical Engineering, Sahand University of Technology,
More information