Artificial Intelligence Tools for Failure Event Data Management and Probability Risk Analysis for Failure Prevention
Jeffrey T. Fong, Pedro V. Marcal
Over the last thirty years, much research has been done on the development of failure event databases and fatigue modeling of crack growth in pressure vessels and piping. According to a USNRC report (NUREG/CR6674, 2000), results of a fatigue crack growth model showed that "cracks initiate rather early in the (nuclear power) plant life. There is about a 50-percent probability of initiating a fatigue crack after only 10 years of operation. Over this 10 years, about 50 percent of these initiated cracks are predicted to grow to become leaking cracks." To improve processing of failure event reporting and more timely risk assessment of critical structures and components, we applied a computer linguistic concept (Schank, 1972) and a natural language toolkit (Lopez, 2002) to develop a software code named ANLAP. This tool will automatically extract statistical data from failure event reports with linkage to fatigue modeling codes for life estimation and risk assessment of aging structures and components.
and Marcal, P.
Artificial Intelligence Tools for Failure Event Data Management and Probability Risk Analysis for Failure Prevention, Materials Science & Technology 2009, Pittsburgh, PA, [online], https://tsapps.nist.gov/publication/get_pdf.cfm?pub_id=903592
(Accessed December 4, 2023)