Eyada, Osama K. (1990, ASQC) Virginia Polytechnic Institute and State University, Blacksburg, VA
The worldwide proliferation of fraudulently certified materials has brought about the need for a new approach to the control of purchased material quality. Nuclear power, defense, aerospace, and many other industries are affected by the supply of poor quality clones that presume to be original replacement parts. These fraudulent materials take the form of threaded fasteners, pipe flanges, relays, and countless other components. Most utilized supplier quality assurance audit programs have not effectively stopped the influx of fraudulent materials. These programs fail to assimilate supplier procurement and product information for the performance of effective audits. Available supplier information such as maintenance reports, purchase orders, and receipt inspection reports can provide valuable insights for increasing effectiveness of supplier quality assurance audits. The assembly, manipulation, and use of this information is presented in this paper in the form of an expert system. This expert system, programmed in the logic programming language PROLOG, contains three key components: the Knowledge Base, the Statistical Modules, and the Inference Engine.
The Knowledge Base is a compilation of supplier and product information presented as PROLOG knowledge representations of facts. These facts are acted upon by the Statistical Modules producing additional key facts that are appended to the central Knowledge Base. The Inference Engine utilizes rules established from accepted quality assurance practices to produce expert advisories from the known facts in the Knowledge Base.
Through this system, users are informed of potential weak areas in a supplier's quality assurance program, high failures of supplier products, auditor training requirements, and supplier utilization volume.