Moynihan G P, Batson R G, Piwonka T S

Abstract: Due to the high cost associated with casting defects, there is a clear need for a rapid and accurate method for analyzing and correcting such defects. A frequent result of the application of computer-based systems in the foundry, has been to reduce the manufacture of non-conforming product as a result of process design deficiencies. Expert systems, a type of computer system employing artificial intelligence techniques, have similarly been applied to foundry quality control problems. As the technology of expert systems are applied to more complex problems, new modes of knowledge management must be used. The purpose of this research is to investigate the application of object-oriented expert system technology to the diagnosis and analysis of penetration and coating surface defects on castings, as well as the recommendation of corrective actions. A prototype system has been developed for this purpose. System recommendations include quantitative prescriptions for changes to the process design which eliminate the defect. The system was implemented on a microcomputer platform, with enhanced graphics capabilities to facilitate defect identification. The system has broad applications in the metalcasting industry, and is considered to be an initial step toward the development of a more comprehensive system.

Keywords: Casting, Coating, Defects, Development, Diagnose, Expert system, Penetration, Surface defects.