Integrating Spatial Digital Twin with Automation System in Smart Infrastructure Asset Management (2023-2025)

Industries are lacking a central platform to gather and analyse disparate OT (Operational
Technology) data sources. These data can be location-based, in multi-dimensional formats with
various frequencies and fidelity. Current industrial automation systems need to be improved to
aggregate dispersed OT data, for robust management of asset health, operation, and
root-cause analysis in the Water, Waste-Water, Mining, and Oil & Gas industries.
Furthermore, there is a lack of spatial dimension in those automation systems, which is essential in
developing a smart, resilient, and mature Digital twin integrated with industrial IoT (IIoT), where 2D,
3D and 4D (time-based) data are used and connected to in-built or third-party analytical tools
to better identify and predict production and process bottlenecks. As such, a composable
the system architecture is crucial to address these challenges and improving efficiency, smartness,
and resilience of infrastructure.

Key Objectives:
* To predict failure, its location, and automated root cause analysis
* To move from preventative to location-based predictive maintenance and more efficient
operations
* To identify and predict process bottlenecks
* To address both static and dynamic data processing

Deliverables:
1. Design and prototype a novel system architecture to integrate multi-dimensional georeferenced data
(e.g. BIM, utilities, and other scanned environments) with a numerical automation system
2. Design and develop a sensor management component in the spatial digital twin
3. Build analytics modules to support a self-correcting system
4. Create a case study to demonstrate and validate the usability and effectiveness of the prototype to
improve the automation processes.

Emerson Rockfield Logo