RSICC CODE PACKAGE PSR-496
1. NAME AND TITLE
SAFE-D/SAFE-R: Code System for the Analysis of Component Failure Data with a Compound Statistical Model.
2. CONTRIBUTOR
Kansas State University, Manhattan, Kansas.
3. CODING LANGUAGE AND COMPUTER
Fortran 77 and 90; IBM PC, IBM RS/6000, DEC Alpha (P00496/MNYCP/00).
4. NATURE OF PROBLEM SOLVED
Two separate but similar Fortran computer codes have been developed for the analysis of component failure data with a compound statistical model: SAFE-D and SAFE-R. The SAFE-D code (Statistical Analysis for Failure Estimation-failure-on-Demand) analyzes data which give the observed number of failures (failure to respond properly) in a specified number of demands for several similar components that should change their condition upon demand. The second program, SAFE-R (Statistical Analysis for Failure Estimation-failure Rate) is to be used to analyze normally operating components for which the observed number of failures in a specified operating time is given. In both these codes the failure parameter (failure probability per demand for SAFE-D or failure rate for SAFE-R) may be assumed equal for all similar components (the homogeneous failure model) or may be assumed to be a random variable distributed among similar components according to a prior distribution (the heterogeneous or compound failure model). Related information can be found at the developer's web site: http://www.mne.ksu.edu/~jks/.
5. METHOD OF SOLUTION
For the compound model analysis, the prior distribution may be chosen as one of several distribution families (e.g. lognormal, beta, gamma, Weibull, etc.). The parameters of the selected prior distribution are estimated from the failure data by any or all of the following methods: (i) matching the data mean and variance to those of the selected prior distribution, (ii) matching the data mean and variance to those of the marginal distribution, and (iii) maximizing the likelihood function of the marginal distribution. Both a chi-square and/or a Kolmogorov-Smirnov goodness-of-fit test can be performed in order to see how well the resulting statistical models describe the given failure data. Finally an analysis of the posterior distribution estimated for each component can be requested as well as various types of confidence intervals and tolerance intervals.
6. RESTRICTIONS OR LIMITATIONS
The codes must be compiled with the Lahey compiler using optimization "-o0" because with higher opts they do not work correctly. Floating point operations are performed by the coprocessor, integer operations by the main processor, and thus the executed sequence of floating point and integer operations can be different from what was intended by the programmer. This problem can be avoided by converting integer into floating point data before any other operations in a routine.
7. TYPICAL RUNNING TIME
The sample problems ran in <1 minute on each of the machines tested at RSICC.
8. COMPUTER HARDWARE REQUIREMENTS
SAFE-D and SAFE-R require I386 and above with math coprocessors and at least 2MB RAM. They can also be run on IBM RS/6000 or DEC Alpha Unix workstations.
9. COMPUTER SOFTWARE REQUIREMENTS
Either a Fortran 77 of 90 compiler is required on the DEC and IBM Unix workstations. The PC executables in the package were created with the Lahey LF90 Fortran Compiler Version 2.0li under Windows95.
10. REFERENCE
J. K. Shultis, N. D. Eckhoff, D. E. Johnson, and G. A. Milliken, "SAFE-R and SAFE-D: Computer Codes for the Analysis of Failure Data," NUREG/CR-2375 KSU-2075d (December 1997).
11. CONTENTS OF CODE PACKAGE
Included in the package are the referenced document and two diskettes written as self-extracting compressed DOS files which include source code, sample problems, and PC executables.
12. DATE OF ABSTRACT
August 2000.
KEYWORDS: RISK ASSESSMENT; COMPONENT FAILURE; PROBABILITY SAFETY ANALYSIS