Search

The paper presents a software implementation of an Intelligent System for Radiogram Analysis (ISAR). The system has to support radiologists in welds quality inspection. The image processing part of software with a graphical user interface and a welds classification part are described with selected classification results. Classification was based on a few algorithms: an artificial neural network, a k-means clustering, a simplified k-means and a rough sets theory.

In this paper an application, implemented functions and data base of welds defects destined to an Intelligent System for Radiogram Analysis ISAR for welds quality inspection is presented. System has to improve information contained in the radiogram, extract defects and decide on welds quality taking into account the relevant regulations.

W pracy przedstawiono koncepcję systemu do inteligentnej oceny jakości połączeń spawanych dokonywanej na podstawie komputerowej analizy radiogramów. Opisano założenia projektu, sprzęt stosowany do jego realizacji oraz oprogramowanie stworzone na potrzeby omawianego zadania. Projekt przewiduje ograniczenie udziału człowieka w podejmowaniu decyzji do niezbędnego minimum. System ma za zadanie automatyzację procesu wydawania opinii i informowania o stanie badanych złączy na podstawie obowiązujących norm. Intelligent system for radiogram analysis for welds quality inspection An intelligent system for radiogram analysis for welds quality inspection is presented in this paper. The conception of this project, hardware used in it and implemented software applications are described. The limitation of human influence in making decision about welds quality is the main aim of this project. The system is able to prepare an opinion about welds quality automatically taking into consideration existing European standards