Verification of a Rule-Based Expert System by Using SAL Model Checker

Abstract

Verification of a rule-based expert system ensures that the knowledge base of the expert system is logically correct and consistent. Application of verification into a rule-based expert system is one approach to integrate software engineering methodology and knowledge base system. The expert system, which we has built, is a rule-based system developed by using forward chaining method and Dempster-Shafer theory of belief functions or evidence. We use Z language as the modelling language for this expert system and SAL model checker as the verification tool. To be able to use SAL model checker, Z2SAL will translate the Z specification, which models the system. In this paper, we present some parts of our Z specification that represent some parts of our rule-based expert system. We also present some parts of our SAL specification and theorems that we added to this SAL specification. At the last, we present the usage of SAL model checker over these theorems. Based on these model-checking processes, we argue that the results are expected. This means that each of theorems can be model checked and the outputs of those model checking are the same as the outputs that we obtain from manual investigation; either it is VALID or INVALID. Other interpretation of the model check's results is some parts of our rule-based expert system have been verified.