skip to main content
OSTI.GOV title logo U.S. Department of Energy
Office of Scientific and Technical Information

Title: PROBABILISTIC INFORMATION INTEGRATION TECHNOLOGY

Abstract

The Statistical Sciences Group at Los Alamos has successfully developed a structured, probabilistic, quantitative approach for the evaluation of system performance based on multiple information sources, called Information Integration Technology (IIT). The technology integrates diverse types and sources of data and information (both quantitative and qualitative), and their associated uncertainties, to develop distributions for performance metrics, such as reliability. Applications include predicting complex system performance, where test data are lacking or expensive to obtain, through the integration of expert judgment, historical data, computer/simulation model predictions, and any relevant test/experimental data. The technology is particularly well suited for tracking estimated system performance for systems under change (e.g. development, aging), and can be used at any time during product development, including concept and early design phases, prior to prototyping, testing, or production, and before costly design decisions are made. Techniques from various disciplines (e.g., state-of-the-art expert elicitation, statistical and reliability analysis, design engineering, physics modeling, and knowledge management) are merged and modified to develop formal methods for the data/information integration. The power of this technology, known as PREDICT (Performance and Reliability Evaluation with Diverse Information Combination and Tracking), won a 1999 R and D 100 Award (Meyer, Booker, Bement, Kerscher, 1999). Specificallymore » the PREDICT application is a formal, multidisciplinary process for estimating the performance of a product when test data are sparse or nonexistent. The acronym indicates the purpose of the methodology: to evaluate the performance or reliability of a product/system by combining all available (often diverse) sources of information and then tracking that performance as the product undergoes changes.« less

Authors:
; ;
Publication Date:
Research Org.:
Los Alamos National Lab., NM (US)
Sponsoring Org.:
US Department of Energy (US)
OSTI Identifier:
775296
Report Number(s):
LA-UR-01-1060
TRN: AH200123%%105
DOE Contract Number:  
W-7405-ENG-36
Resource Type:
Conference
Resource Relation:
Conference: Conference title not supplied, Conference location not supplied, Conference dates not supplied; Other Information: PBD: 1 Feb 2001
Country of Publication:
United States
Language:
English
Subject:
99 GENERAL AND MISCELLANEOUS//MATHEMATICS, COMPUTING, AND INFORMATION SCIENCE; AGING; DESIGN; EVALUATION; MANAGEMENT; METRICS; PERFORMANCE; PHYSICS; PRODUCTION; RELIABILITY; TESTING

Citation Formats

J. BOOKER, M. MEYER, and ET AL. PROBABILISTIC INFORMATION INTEGRATION TECHNOLOGY. United States: N. p., 2001. Web.
J. BOOKER, M. MEYER, & ET AL. PROBABILISTIC INFORMATION INTEGRATION TECHNOLOGY. United States.
J. BOOKER, M. MEYER, and ET AL. Thu . "PROBABILISTIC INFORMATION INTEGRATION TECHNOLOGY". United States. https://www.osti.gov/servlets/purl/775296.
@article{osti_775296,
title = {PROBABILISTIC INFORMATION INTEGRATION TECHNOLOGY},
author = {J. BOOKER and M. MEYER and ET AL},
abstractNote = {The Statistical Sciences Group at Los Alamos has successfully developed a structured, probabilistic, quantitative approach for the evaluation of system performance based on multiple information sources, called Information Integration Technology (IIT). The technology integrates diverse types and sources of data and information (both quantitative and qualitative), and their associated uncertainties, to develop distributions for performance metrics, such as reliability. Applications include predicting complex system performance, where test data are lacking or expensive to obtain, through the integration of expert judgment, historical data, computer/simulation model predictions, and any relevant test/experimental data. The technology is particularly well suited for tracking estimated system performance for systems under change (e.g. development, aging), and can be used at any time during product development, including concept and early design phases, prior to prototyping, testing, or production, and before costly design decisions are made. Techniques from various disciplines (e.g., state-of-the-art expert elicitation, statistical and reliability analysis, design engineering, physics modeling, and knowledge management) are merged and modified to develop formal methods for the data/information integration. The power of this technology, known as PREDICT (Performance and Reliability Evaluation with Diverse Information Combination and Tracking), won a 1999 R and D 100 Award (Meyer, Booker, Bement, Kerscher, 1999). Specifically the PREDICT application is a formal, multidisciplinary process for estimating the performance of a product when test data are sparse or nonexistent. The acronym indicates the purpose of the methodology: to evaluate the performance or reliability of a product/system by combining all available (often diverse) sources of information and then tracking that performance as the product undergoes changes.},
doi = {},
journal = {},
number = ,
volume = ,
place = {United States},
year = {2001},
month = {2}
}

Conference:
Other availability
Please see Document Availability for additional information on obtaining the full-text document. Library patrons may search WorldCat to identify libraries that hold this conference proceeding.

Save / Share: