Inflection point principle combined with digital image correlation and machine learning for crack length measurement in fatigue tests

journal article in Web of Science

en

The visual inspection method is a widely used non-contact technique for measuring fatigue crack propagation, but it is inefficient, requiring frequent operator input. Digital image correlation (DIC) methods provide alternatives. However, full-field methods are computationally demanding, while line-based thresholding techniques are sensitive to material load conditions, reducing consistency. This study proposes and validates a new non-contact, physically-based method for real-time crack length evaluation. It eliminates the need for thresholding and enables higher testing frequencies due to its line-based nature, supporting accurate, versatile, and automated fatigue testing. The method integrates the inflection point principle with DIC and machine learning. Visual inspection serves as a validation baseline, using a novel setup that applies both methods simultaneously on the same side of the sample for direct comparison. The proposed method shows good agreement with baseline results, achieving mean absolute errors of 24 mu m (static) and 54 mu m (dynamic). Compared to line-based thresholding, it is four times more accurate (dynamic) and independent of load levels, though 1.7 times slower.

The visual inspection method is a widely used non-contact technique for measuring fatigue crack propagation, but it is inefficient, requiring frequent operator input. Digital image correlation (DIC) methods provide alternatives. However, full-field methods are computationally demanding, while line-based thresholding techniques are sensitive to material load conditions, reducing consistency. This study proposes and validates a new non-contact, physically-based method for real-time crack length evaluation. It eliminates the need for thresholding and enables higher testing frequencies due to its line-based nature, supporting accurate, versatile, and automated fatigue testing. The method integrates the inflection point principle with DIC and machine learning. Visual inspection serves as a validation baseline, using a novel setup that applies both methods simultaneously on the same side of the sample for direct comparison. The proposed method shows good agreement with baseline results, achieving mean absolute errors of 24 mu m (static) and 54 mu m (dynamic). Compared to line-based thresholding, it is four times more accurate (dynamic) and independent of load levels, though 1.7 times slower.

Digital image correlation; Crack length measurement; Inflection point method; Gaussian process regression; Machine learning

18.06.2025

ELSEVIER

AMSTERDAM

0167-8442

139

June

1–17

17