DEVELOPING A PROTOTYPE OF QUALITY CONTROL EXPERT SYSTEM FOR OFFSET PRINTING DOT VARIATIONS TROUBLESHOOTING

摘要

Printing Quality Control Expert System (PQCES) mainly describes the use of an expert system, a branch of Artificial Intelligence (AI), in controlling offset printing dot variations. The system can be largely divided into three parts: the knowledge base, which standard data and fault judgment information are acquired from some quality control devices; the inference engine, in which heuristic rules are constructed according to experienced offset printing operators and appropriate paper records; and the user interface, which the expert system tool, Nexpert Object, is applied to process knowledge and information in the environment of Windows. For knowledge engineering, the knowledge acquisition and representation of dot variations are edited with the editors of Nexpert Object. For instance, several quality control devices, such as dot-gain scale, control bars...etc., are transferred into objects and rules. The prototype of PQCES is constructed with these rules and related data. It is not only a Decision Support System (DSS) for improving the quality of offset printing operation, but also a training system for offset printing trouble-shooting training for the entry-level trainees.