A digital twin is a virtual adaptation of a process, system, or a product. The scope of digital twins are near limitless and at present implementations are only scratching the surface of its potential. Ultimately digital twins act as a conduit that allows us to scrutinize physical entities from a computer. In the context of asset management, a digital twin could portray the relationship between the environment, condition, and operational context of an asset and its associated risk of failure and cost to the business.
The technology and its expected benefits extend into the domains of Machine Learning (ML), Artificial Intelligence (AI) and the Internet of Things (IoT). Digital twins are constantly evolving as these technologies mature. However, digital twins are not yet the high high-fidelity real-time simulations everyone expects.
To put its current limitations in context, we need to understand what degrees of freedom are. In statistics degrees of freedom describe the number of independent variables which are free to vary in a calculation. Conservatively a digital twin model of a complete aircraft frame has a trillion degrees of freedom. To simulate such a complex system in real-time is not a trivial task. Not even for the fastest computers in the world.
Fortunately, most businesses do not need to simulate an aircraft or any system nearly as complex. Even simple digital twins are immensely powerful and represent a strong competitive differentiator if employed correctly. In the context of asset management, the coupling of condition monitoring data, maintenance history, and historical fleet data allow digital twins to paint a clear of an asset’s health, improving safety and reliability.
A digital twin is a platform that incorporates and displays information. Ultimately the amalgamation of every analysis and data point portrays a complete picture of the asset. In an ideal world, a digital twin is not measuring or reporting on a few metrics, it is a like for like representation of its physical counterpart which allows for any type of analysis to be performed on demand, and the results displayed.
Data from sensors, asset information, condition information, operational information and more, are fed into a digital twin. Our model combines this information, analyses it, then displays recommendations and findings in an intuitive graphical manner. For maintenance teams, the digital twin would communicate asset health and information on failures that might occur soon. However, maintenance strategy execution is not as simple as fixing or replacing assets. The overall business context of the asset must be considered when deciding on an appropriate course of action. Our asset management platform bridges the gap between raw data and information, and actionable strategies conscious of business constraints and context.
Modla is an analytical engine, that when combined with asset models, provides live recommendations and analytics: