In the domain of product design, process planning and manufacturing, multiple types of human expertise and knowledge are needed for various decision-making processes. This explains why knowledge-based systems are among the most researched technologies, and in many cases have proven to be effective systems.
Expert Systems Technology
Expert system (otherwise known as knowledge-based system) is an important branch of artificial intelligence (AI). Expert systems provide a natural, yet powerful and flexible means for obtaining solutions to a variety of manufacturing problems that often cannot be dealt with by other more orthodox methods. One study reported an investment of over $100 million in artificial intelligence research by large American manufacturing companies. Some of them have achieved impressive results (Dornan, 1987). Among the companies that benefited the most are Digital Equipment Corporation’s XCON, Boeing and Lockheed Georgia Corporation’s GenPlan. It is of the view of many that expert systems can make a significant contribution to improving process and production planning (Kusiak & Chen, 1988, Badiru, 1992, Jayaraman & Srivastava, 1996, Zhang & Chen, 1999).
Welbank (1983) defines an expert system as a program that has a wide base of knowledge in a restricted domain, and uses complex inferential reasoning to perform tasks, as human expert usually does. In other words, an expert system is a computer system containing a well-organised body of knowledge, which emulates expert problem solving skills in a bounded domain of expertise. The system is able to achieve expert levels of problem solving performance, which would normally be achieved by a skilled human when confronted with significant problems in the domain. As illustrated in Figure 1, an expert system consists of three main components, the knowledge base, inference engine and user interface.
Figure 1. Expert system’s architecture
Knowledge base is the heart of the system. It contains the knowledge needed for solving problems in a specific domain. Knowledge may be in the form of facts, heuristics (e.g. experiences, opinions, judgments, predictions, algorithms) and relationships usually gleaned from the mind of experts in the relevant domain. Knowledge may be represented using a variety of representation techniques (e.g. semantic nets, frames, predicate logic) (Jackson, 1986, Ignizio, 1991, Mital & Anand, 1994), but the most commonly used technique is “if-then” rules, also known as production rules. These rules are often represented in a tabulated form. The inference engine is employed during a consultation session to examine the status of the knowledge base, handle the content of the knowledge base and determine the order in which inferences are made. It may use various inference methods. The user interface part enables interaction of the system with the user. It mainly includes screen displays, a consultation/ advice dialogue and an explanation component. In addition, expert systems provide interfaces for communication with external programs such as databases and spreadsheets.