Review of Progress in Quantitative Nondestructive Evaluation
A traditional way to estimate probability of detection (POD) from quantitative inspection data involves estimating the relationship between signal response and flaw size using a linear regression model of the (possibly) transformed data. Noise response data, when available, are used to estimate the detection threshold to control the probability of a false alarm. One of the direct results from the traditional POD method is that the POD will be close to zero where there is no flaw. However, the POD for the limiting case of a very small flaw (or no flaw) is actually the probability of a false alarm. In this paper, we will use both the noise data and the measured signal data to estimate the parameters of a combined model for signal and noise. The resulting POD estimate from the noise interference model provides a correct estimate of the positive probability of detection for small and zero flaw sizes.
American Institute of Physics
Li, M. and Meeker, William Q., "A noise interference model for estimating probability of detection for nondestructive evaluations" (2008). Center for Nondestructive Evaluation Conference Papers, Posters and Presentations. 78.