Expert systems: rules

Rules seemingly have the same format as IF.. THEN.. statements in any other conventional computer language. The major difference is that the latter statements are constructed to be executed sequentially and always in the same order, whereas expert system rules are meant as little independent pieces of knowledge. It is the task of the inference engine to recognize the applicable rules. This may be different in different situations. There is no preset order in which the rules must be executed. Clarity of the rule base is an essential characteristic because it must be possible to control and follow the system on reasoning errors. The structuring of rules into rule sets favours comprehensibility and allows a more efficient consultation of the system. Because of the natural resemblance to real expertise, rule-based expert systems are the most popular. Many of the earlier developed systems are pure rule-based systems. 

Nevertheless, where it is difficult for a computer to learn expert system rules, the traditional expert system still has a place. A typical recent example of the use of expert systems is provided by the work of Dobrzanski and Madejski62 who have developed a prototype system for determining metal coating that provides an optimum combination of appearance, abrasion resistance, color, and other factors. A less scientific, but still intriguing, example of the use of these systems is HuskEval, an expert system for evaluating the quality of Siberian Huskies.63... 

Figure 2. Basic Step in an Expert System Rule Base.

Expert-System Rules for Diels-Alder Reactions... 

The Definite Clause Grammar (DCG) formalism [7] is utilized throughout this project. Grammar rules are used in the expert system rules to recognize the general class of the parent molecule in the disconnection (c.y., cyclohexene). The class determines the patterns used to construct the resultant synthons (discussed in Section 4). 

It should be clear that this notation applies to many different classes of reactions. Use and manipulation of this general form will be discussed in the next section. The following discussion outlines its use in expert system rules. 

Other systems have developed FMO reaction checks and used WLN for cataloging, but this system has relied heavily on a symbolic approach to chemistry, including application of grammar techniques to WLN strings. We feel that our system is very successful in the domain that it has been applied, eliminating hundreds of naive expert system rules. We also feel that our techniques are applicable to many other reactions as well. 

SpinPro is a typical backward chaining, rule-based expert system. Rule-based systems are systems in which the expert s knowledge is encoded primarily in the form of if-then rules, i.e., if a set of conditions are found to be true then draw a conclusion or perform an action. "Backward chaining" refers to the procedure for finding a solution to a problem. In a backward chaining system, the inference engine works backwards from a hypothesized solution to find facts that support the hypothesis. Alternative hypotheses are tried until one is found that is supported by the facts. 

DEREK Expert system, rules Sanderson and Earnshaw (1991)... 

A panel discussion was held to review the problems involved in sharing Knowledge bases. This discussion examines the advantages of sharing expert system rules, and the likelihood of knowledge bases being shared. The viewpoints are given by industrial representatives, a university professor, and chemical instrument vendors. 

In a rule-based expert system, rules provide a formal way of representing expert knowledge, which can represent relations, recommendations, directives, strategies and heuristics (Durkin, 1994). A mle consists of two parts the IF part, called the antecedent (premise or condition), and the THEN part, called the consequent (conclusion). The basic syntax of a rule is ... 

Formative evaluation of the system with a limited number of users has indicated that users are willing to use the help system if their knowledge is deficient. However, the advice that is available for novice users of the system is not always adequate. For instance, help screens including examples and limited practice are insufficient to enable novice users to accurately classify learning outcomes. This decision, like most of the others required of the users, is a complex, coordinate concept outcome that requires more instruction. We are exploring options, including the addition of more interactive instructional activities to the help system or the integration of other expert system rule bases. These rule bases will be executed by the help... 

The design steps and the design guidelines are converted into expert system rules (Appendix A) for ball and roller bearing design. This expert system when run by the user will provide him with the relevant bearing parameters and their values. 

---