[4C3] Automated ultrasonic sizing of surface breaking cracks using snooker images and neural network machine learning systems
C Nageswaran
TWI Ltd, UK
Cracking of industrial components and structures poses a significant threat to their integrity. Cracks emerging from the surface of engineering components can be detected using ultrasonic inspection techniques. In addition to detecting the cracks, there is a need to measure their growth into the component, termed the through-wall extent (TWE). Ultrasonic techniques are well suited to interrogate the volume of metallic materials used in industry, but achieving sufficient sensitivity to the tip of very sharp cracks is difficult. Without an accurate knowledge of where the tip of the crack lies in high-resolution ultrasonic images there can be significant uncertainty in sizing the TWE of the cracking. This paper demonstrates a system using machine learning to automatically size surface-breaking cracks. This paper shows that artificial neural networks can be developed for effective industrial use when a limited amount of data is presented in a suitable way, as images termed snooker, and through the use of simulation to aid training.
