8 Set 2022
Cognitive digital twin: An approach to improve the maintenance management
Digital technology is progressing at a rapid pace. Our need as an international defence company, whose business is underpinned by a deep understanding of technology integration and engineering, is to understand its impact and benefits.
Working in collaboration with Cranfield University we’re pleased to present this new research into Digital Twins, looking at the role this technology can play in asset maintenance.
For businesses like ours, Digital Twins can provide a means to better understand real-world entities. We utilise a Digital Twin approach across Babcock to better understand asset performance and enable prediction of future use to allow us to prevent failures, better plan maintenance and optimise our resources, inventory and supply chain to increase asset availability and reduce through-life costs.
The use of ontologies as part of a structured, repeatable approach to the definition, creation and management of digital twins is key to helping us realise their full potential in the engineering lifecycle. This allows us to manage the complexity of an individual twin and the interoperability of multiple twins as part of a system of systems that can be scaled to model real-world behaviours of assets and the environments in which they operate.
This research also examines the complex integration of different types of technical and contextual data a digital twin can provide. It incorporates technologies and techniques such as Artificial Intelligence and machine learning, data analytics and multi-physical simulations to model and predict behaviour – providing vital information to asset owners.
This paper importantly explores the impact of asset degradation and shows how collecting data across the life cycle of assets, together with accurate degradation models, can help us better predict the remaining useful life of components. In this way, we can move from reactive maintenance to proactive maintenance, avoiding downtime and optimising maintenance planning and costs through predictive maintenance.
The following research has been published by Cranfield University, in conjunction with Babcock International Group and co-author, Steve Penver, Head of Digital Integration, Babcock.