An ontology-based knowledge framework for selection of joining process in plastic assembly

Abstract

Selection of assembly process is one of the important stage of product development which need to tackle at the earlier stage product realization. Selecting the most appropriate joining process needs various assembly joint information (liaison) which includes both the geometric and non-geometric information. To capture, represent, and reuse this information across domains is a highly knowledge-intensive process that necessitates the use of an active artificial intelligence (AI) tool. In this research, an AI tool called ontology-based knowledge framework is used to assist with identifying the best plastic assembly process to effectively support designers and process planners. The methodology for selecting a joining process and developing a knowledge-based framework is described, together with industrial application of the suggested approach is proposed. To express many key concepts like liaison, process, requirement for variant product etc., a joining process selection (JPS) ontology is created. To get the necessary knowledge for process selection that integrates several instances and knowledge rules, ontology mapping of joining method selection concepts is done using Semantic Web Rule Language (SWRL). The suggested method uses rule-based reasoning to automatically infer the best joining methods. Finally, industrial application of the suggested framework is proposed to assess the applicability of this approach.