A discussion about the qualification of digital twins for maintenance models

Advancements in sensor technology have led to an abundance of data for decision-making systems, enabling an improved understanding of system status and facilitating more reliable and cost-effective maintenance options. Digital twins (DTs) serve as a vital bridge between these data and maintenance models. However, their trustworthiness in real-world settings remains uncertain. In this paper, we propose a comprehensive methodology for certifying and ensuring the quality, credibility, and interpretability of DTs. We present a concise review of the current state of DT qualification and classification, followed by the introduction of several evaluation indices for DTs. These indices are designed to facilitate more informed decisions and promote the broader adoption of DTs in maintenance optimization. A case study is provided to demonstrate the practical applicability and effectiveness of our proposed evaluation framework. Through this work, we aim to support better-informed decision-making and enhance system performance in maintenance optimization across various industries. Copyright (C) 2023 The Authors.