Digtital Engineering Lab
Key Research Area
BIM Model Enhancement and Intelligent Data Management
This area concentrates on refining BIM through model conditioning, which involves optimising and tailoring BIM models for specific project requirements. Data enrichment and validation are key processes here, enriching BIM models with additional, relevant information and ensuring the accuracy and reliability of this data. Utilising Large Language Models (LLM), semantic queries are employed to intelligently search and interpret the vast amounts of data within BIM, enhancing decision-making and efficiency in construction projects.
Advanced Planning and Scheduling with Generative AI
In this focus area, the lab leverages Deep Reinforcement Learning (DRL) combined with BIM and Large Language Models (LLM) technology to create generative planning and scheduling methods. This approach enables the automation of planning processes, generating optimal construction and maintenance schedules that adapt to changing project conditions and constraints. It enhances project management by providing more efficient, flexible, and cost-effective scheduling solutions.
Predictive Asset Maintenance with Digital Twins
This domain involves the development of digital twins, which are dynamic, virtual representations of physical assets. These digital twins are used for predictive maintenance, allowing for the forecasting of asset wear and tear and facilitating proactive maintenance strategies. By mirroring the real-time status of physical assets, digital twins enable the lab to analyse data and predict future conditions, leading to improved asset longevity and reduced maintenance costs.
Digital Technology-Enabled Carbon Emission Management
This area focuses on leveraging digital technologies to estimate, monitor, and control carbon emissions in the construction, infrastructure, and mining industries. By integrating tools such as AI, blockchain, and data analytics, the lab aims to develop comprehensive systems for accurately estimating the carbon footprint of various projects and operations. Monitoring involves real-time tracking of emissions, using sensors and IoT (Internet of Things) devices to collect data on energy consumption and waste production. The control aspect pertains to implementing strategies and technologies to reduce carbon output, such as optimising resource use, enhancing energy efficiency, and promoting sustainable practices. This approach not only aids in meeting environmental regulations and sustainability goals but also drives the industry towards a lower carbon future.
