The advancement in digital technologies is revolutionising every facet of life, including the built environment, by shaping the design, construction and operation of buildings, from the way buildings are constructed, to how they are managed and interact with the occupants. Notwithstanding the recent progress made in the application of digital technologies, many challenges that could be addressed through these technologies are still affecting the productivity and efficiency of the Architecture Engineering and Construction (AEC) industry.
Our research focuses on the investigation, design, development, deployment and use of digital technologies and solutions such as BIM, digital twin, big data analytics, IoT and Machine Learning, among others, to address various issues affecting productivity, sustainability and/or efficiency in the AEC industry. With Construction Informatics ((application of digital technologies in construction) being the overarching research theme, the specific areas of focus include:
- Building Information Modelling (BIM) and digital twin
- Sustainable built environment
- The built environment as an enabler of healthy living
- Smart City
- Modern Methods of Construction (MMC).
We currently have two ongoing research projects in this field;
Big Data and Machine Learning-enabled Automated BIM for Projects (Auto-BIM): A Common Data Collaborative System for Improved Project Performance. Funded by Innovate UK, this two year project is valued at just under £900,000.
The ability of Building Information Modelling to achieve its potential benefits of 33% lower cost, 50% faster delivery, 50% lower emissions and 50% improvement in export as touted by the government task force on BIM is currently impeded by several challenges. These include the barrier to its adoption as a result of naming convention in line with ISO 19650 and the need for adequate building-information to accompany 3D representation of building materials, elements and products in a collaborative environment, all of which requires significant investment and efforts. For organisations that have surpassed the barrier to BIM-adoption, the main challenge remains getting everyone involved in collaborative projects to use CDE and to ascertain the exact-level of (and the specific) information required for different aspects and types of assets. In order to address these challenges, the proposed project adopts a cross-disciplinary approach through the innovative combination of BIM and construction knowledge with expertise in Machine Learning (ML) and Big Data Analytics. The project aims to create an innovative tool (Auto-BIM) as a plug-in to BIM models, and it consists of four key elements as follows:
- Automated Naming of BIM model in a CDE approach (Auto-BIMName): The Auto-BIMName will automate the process by of naming models and files by developing an intuitive plug-in tool within BIM environment. It also automates the process of generating TIDP and MIDP.
- Automated-Population-of-Building-Information (Auto-BIMPopulate): This will prepopulate the 3D-representation of products/elements with relevant metadata including the Omniclass classification, model number, service information, materials, etc.
- Automated Sharing of BIM Objects and Model Data (Auto-BIMShare): This provides a unique platform for sharing reusable object library and associated information in a way to facilitate common language across software boundaries
- Automated BIM learning Platform (Auto-BIMLearn): The Auto-BIMLearn would leverage historical data to support design, construction and asset management decisions. The Auto-BIM-Tool will facilitate this by providing Red-Amber-Green type decision-support underpinned by the Pros/Cons of previous projects.
Partners: Balfour Beatty Construction PLC | White Frog Publishing Limited | Leeds Beckett University | Hertfordshire University
Live Visualization of Emission - Towards Avoidance of Pollution Hotspot (LiVE-TAP). Funded by Innovate UK, this eighteen month project is valued at just under £500,00
This project aims to develop a holistic system which communicates 'accurate' live-emission-data of city-centre-streets and school-run-routes to citizens through digital means including mobile-phone apps. This will allow citizens/users to decide when (not) to use certain city-centre-streets/school-run-routes, or which ones (not) to use (i.e. avoidance behaviour), based on emission levels. This will help to greatly reduce the amount of emission inhaled by users and divert traffic away from highly polluted areas thereby reducing pollution. The acquired data will also be used to predict future-emission-levels to allow eco-healthy planning and inform local-authority policies.
The system will include
- Internet-of-Things sensors installed on city-centre-streets and school-run-routes to accurately measure key pollutants like NO2, CO2 and PM2.5s
- Mobile-phone/computer apps to directly relay live-emission-levels data to city-centre-streets and school-run-routes users and stakeholders using heat-maps on digital-geographic-maps.
- Cloud-storage, big-data-analytics and machine-learning-algorithms used with acquired data to predict future-emission-levels to allow eco-healthy planning and inform local-authority policies
- Emission-data-as-service to tour/trip/route plan providers (e.g. Tour-Planner, Google-maps,etc.) for improving their services.
- A crowdsourcing-platform hosted for future installers of IoT emission sensors to sell their data through Blockchain-Technology
Partners: Earthsense Systems Limited | Hertfordshire University | Leeds Beckett University | Wolverhamption City Council
For further information on any of these projects, please contact Dr Saheed Ajayi on 0113 812 7620 or by email to S.Ajayi@leedsbeckett.ac.uk.