Abstract
Industrial asset monitoring depends on AI (Artificial Intelligence) driven analytics to enhance performance; however, approaches differ according to asset complexity, data availability, and operational context. This paper explores decision-support strategies for monitoring engineered-to-order (EtO) and configure-to-order (CtO) assets, comparing predictive analytics strategies, insight generation, and return on investment (ROI). Analysing two real-world cases, we illustrate how AI-powered diagnostics, operational variability, and system integration impact decision-making and action-taking. The findings emphasise AI’s potential role in improving asset resilience, optimising maintenance strategies, and supporting data-driven decision-making within industrial ecosystems, with ramifications for interoperability, efficiency, and business model innovation.
Keywords
Condition monitoring, Operational technology, Artificial intelligence, Asset management, Decision making, Decision support systems, Investments, Predictive analytics, Condition, Data availability, Decision supports, Decisions makings, Monitoring approach, Operational technologies, Performance
Reference
Anderson, M., West, S., & Alves, K. (2025). Differentiating Monitoring Approaches for Engineered-to-Order (EtO) and Configure-to-Order (CtO) Assets. In IET Conference Proceedings (pp. 135–137). Institution of Engineering and Technology. Presented at 11th International Conference on AI and the Digital Economy, CADE 2025, Venice, July 14-16, 2025. https://doi.org/10.1049/icp.2025.2975