Asset information requirements for blockchain-based digital twins: A data-driven predictive analytics perspective

Purpose: The purpose of this study is to identify the key data categories and characteristics defined by asset information requirements (AIR) and how this affects the development and maintenance of an asset information model (AIM) for a blockchain-based digital twin (DT). Design/methodology/approach: A mixed-method approach involving qualitative and quantitative analysis was used to gather empirical data through semistructured interviews and a digital questionnaire survey with an emphasis on AIR for blockchain-based DTs from a data-driven predictive analytics perspective. Findings: Based on the analysis of results three key data categories were identified, core data, static operation and maintenance (OM) data, and dynamic OM data, along with the data characteristics required to perform data-driven predictive analytics through artificial intelligence (AI) in a blockchain-based DT platform. The findings also include how the creation and maintenance of an AIM is affected in this context. Practical implications: The key data categories and characteristics specified through AIR to support predictive data-driven analytics through AI in a blockchain-based DT will contribute to the development and maintenance of an AIM. Originality/value: The research explores the process of defining, delivering and maintaining the AIM and the potential use of blockchain technology (BCT) as a facilitator for data trust, integrity and security.