A new project led by the University of Wollongong’s SMART Digital Living Lab aims to revolutionise building efficiency by using image recognition to assess occupancy and artificial intelligence to forecast temperatures.
Researchers at UOW’s SMART Infrastructure Facility are partnering with Grosvenor Engineering Group, Enviro Building Services and the NSW Government to create smarter living in buildings.
Senior research fellow Dr Rohan Wickramasuriya is leading the team looking at new ways to optimise heating, ventilation and cooling of buildings.
The project aims to solve several practical problems in building management, including accurate counting of building and room occupation and accurate forecasting of indoor temperature.
Anonymised real building data is being collected from equipment maintained by Grosvenor, while Enviro’s office spaces provide image data. This data will be used to train “deep neural networks” – an aspect of artificial intelligence – to predict outcomes.
“The project’s focus is to increase the efficiency of building environments,” Dr Wickramasuriya says.
Current systems used to estimate building occupancy – a pre-requisite for optimising HVAC systems and space – are about 66 per cent accurate. In comparison, the new image-recognition based system developed in this research is about 93 per cent accurate.
A room temperature forecasting model also allows building managers to test various power regimes and their impact on keeping a room’s temperate within the comfort zone.
“For instance, by forecasting room temperatures as a function of external and internal conditions, we expect to find that it is more efficient to pump cool night air into a building, rather than turning off the system at 6pm and allowing rooms to heat up due to lack of ventilation,” Dr Wickramasuriya explains.
“Outcomes expected from this project include a readily deployable, accurate and IoT compliant people counter; accurate indoor temperature forecasting algorithm and a prototype vibration sensor.”
Grosvenor maintains more than 17,000 facilities across Australia and oversees $2.2 billion worth of assets under management for large corporate companies.
Rod Kington, Grosvenor’s national sustainability manager, says the partnership with UOW will “enable us to incorporate the knowledge gained across our vast building network”.
“We are expecting to further enhance and innovate within the built environment from the insights gained from this research. Our main purpose is to make buildings operate more efficiently by driving down inputs from labour, energy, water and carbon dioxide.
“The research into deep neural networks moves us down the pathway toward machine learning and artificial intelligence which will be significant future drivers of value when maintaining building assets.”
Project results are expected to be delivered mid-year.