Keynote Speech

The reliable detection and classification of defects is one of the most important tasks in nondestructive testing (NDT). Usually, trained interpreters evaluate the achieved results of inspection. The paper presents a simplified process that occurs in the mind of the operator during the recognition of signals and images. In many cases the process is laborious and time-consuming. Human interpretation is subjective, inconsistent, and often biased. The additional problems are caused by the insufficient quality of utilized signals or images. An incorrect classification may result in rejection of a part in good conditions or acceptance of a part with defects exceeding the limit defined by the relevant standards. Artificial intelligence has appeared in our research on non-destructive testing, along with the works on defects identification in eddy current systems. Participation in the EU project FilmFree and in the national project Intelligent Analysis of Radiographs (ISAR) significantly extended this area of research, especially in the field of automatic defect recognition in a digital radiography. The paper carried a brief overview of artificial intelligence algorithms applicable to nondestructive testing. It focuses on two methods: artificial neural networks and rough sets. Selected examples of applications of these methods in digital radiography and eddy current testing are given.