The problem of improving the efficiency of designing process of knowledge bases and expert systems remains a relevant issue. The effectiveness of this process can be improved by using the principles of conceptual (cognitive) modelling and generative programming‐based approaches, in particular, a model‐driven development.
This paper describes implementation and application of the model‐driven development approach for the design of rule‐based expert systems and knowledge bases. The implementation proposed takes into account peculiarities of the intelligent systems development process, such as stages of conceptualization and formalization, and provides the practical use of ontologies and conceptual models as computation‐independent and subject domain models.
An extension of UML, namely, the Rule Visual Modelling Language is used to represent logical rules and create platform‐independent and platform‐specific models. Rule Visual Modelling Language elements ensure that some features of a programming language for knowledge bases, for example, CLIPS, are taken into account. Therefore, CLIPS and the Personal Knowledge Base Designer are used as the targeted platforms for generation of source codes and specifications.
The applicability of the approach is demonstrated by a case study: development of the knowledge base and expert system for identification of the causes of damages and destruction of construction materials in petrochemistry.
This paper describes a decision support approach for selecting construction materials in the field of petrochemistry. The correct selection of construction materials is the basis for the provision of durability, long lifetime, and the safety of the designed and upgraded equipment. The proposed hybrid approach is based on the joint application of case-based reasoning and multi-criteria decision-making methods, particularly the aggregation and ranking alternatives nearby the multi-attribute ideal situation (ARAMIS) and aggregation of individual ranking/ complex of aggregation of individual ranking (AIR/CAIR) methods are used. In turn, ARAMIS enables the processing of individual preferences, which are represented in the form of numeric and verbal estimates, and AIR/CAIR is used for processing rankings (strictly or partially ordered sets of alternatives). The primary advantage of this approach is that it considers the experience of previous successful solutions of the materials selection problem, demonstrates the validity of the obtained results using the mathematical theory of multi-criteria decision making and explains the decision making process. The approach is implemented in the form of the expert system. The case model, algorithms, and an illustrative example of application of the proposed approach are also presented.
scite is a Brooklyn-based organization that helps researchers better discover and understand research articles through Smart Citations–citations that display the context of the citation and describe whether the article provides supporting or contrasting evidence. scite is used by students and researchers from around the world and is funded in part by the National Science Foundation and the National Institute on Drug Abuse of the National Institutes of Health.