Study of Estimation Methods for Probability of Detection for Structural Health Monitoring

• Activity Number: 51 - Recent Developments in Modeling High-Dimensional and Complex Data
• Type: Contributed
• Date/Time: Monday, August 3, 2020 : 10:00 AM to 2:00 PM
• Sponsor: SSC (Statistical Society of Canada)
• Author(s): Emily O'Connor* and Sabyasachi Basu and Jeong-Beom Ihn and James Dunne and Lawrence Pado
• Companies: The Boeing Company and The Boeing Company and The Boeing Company and The Boeing Company and The Boeing Company
• Keywords: reliability; POD; probability; SHM; structures; health

Abstract

Assessing the health of physical structures is vital for safety and integrity of aerospace products. One way statisticians commonly assess health of a structure is through estimating probability of detection (POD) for a flaw. The POD describes the likelihood of detection to a characteristic parameter of the flaw on the product, often the size of the flaw. This metric, along with others in reliability statistics, can help us improve our inspection schedules and confidence in our products. As new continuous monitoring technologies are developed, innovative statistical methods to estimate the probability of detection for these technologies are required to make sense of these rich new data sources. In this talk we will describe the development of these various techniques, how they are used and assessed, and give industry examples. We will also use simulation to compare and contrast the different methods of estimating the POD under several situations.