Cognitive digital twins: enabling holistic asset management through semantic interoperability and human expertise integration

Abstract

The growing industrial interest in Digital Twins (DTs) has led to an expansive network of standalone DT solutions. Many of these twins operate in isolation, frequently lacking the features that enable seamless integration and communication with other systems. Based on these facts, this PhD project aims to propose a novel framework for creating DTs with advanced semantic capabilities, which are increasingly being referred to as Cognitive Digital Twins (CDTs). Beyond advancements of traditional DTs, these CDTs provide a means to formalise and transfer human expertise, which is crucial for enhancing DTs’ decision support, operational efficiency, and adaptability in complex asset management. Moreover, CDTs also have the potential to achieve significantly improved semantic interoperability among twins. This enhanced interoperability facilitates a consistent and efficient data flow and augments asset management procedures. Furthermore, it boosts awareness and insights regarding the operations and performance metrics of the mirrored assets. This comprehensive approach to DT development offers a reference frame that delineates how assets communicate, function, and evolve in a digitally twinned environment. This PhD thesis explores the potential of CDTs in improving the management of complex engineering assets by enhancing the transfer of human expertise and semantic interoperability within and among DTs. The thesis makes several contributions, starting with a systematic literature review to identify gaps in existing academic research and an industrial review that assesses current industry practices, highlighting the relevance of the research. A novel five-step methodology for developing CDTs is introduced, emphasising the use of top level ontologies (TLOs) and the integration of human expertise. This methodology ensures semantic consistency within the DT framework and has been validated in a laboratory setting. A CDT framework is also presented, prioritising flexibility, interoperability, and reusability aspects provided by this novel approach. The study primarily focuses on the manufacturing industry and underscores the role of ontologies in enhancing CDTs, bridging the gap between human understanding and automated systems. Future research directions are proposed, mainly aiming to optimise asset management, availability, and sustainability by integrating human knowledge into digital systems and promoting collaborative learning among CDTs.