Researchers at the SMART Infrastructure Facility at the University of Wollongong (UOW) have partnered with industry leaders and a government agency to complete a project that is set to improve building efficiency by keeping temperatures consistent within a set comfort zone.
Funded by Grosvenor Engineering Group (Grosvenor), Enviro Building Services (Enviro) and the New South Wales Government (through the Department of Industry), the project is part of SMART’s Digital Living Lab, which provides an Internet of Things (IoT) network to create smarter living in buildings.
The team, led by senior research fellow Dr Rohan Wickramasuriya, is looking at ways of optimising the heating, ventilation and cooling of buildings under the Building Energy Monitoring project.
Anonymised real building data is collected from equipment maintained by Grosvenor, while Enviro’s office spaces are providing image data. This data will be used to train deep neural networks to predict outcomes.
“Both Grosvenor and Enviro are leading building services providers that were open to innovate and collaborate with the university’s research facilities for our latest project,” says Wickramasuriya.
“The project’s focus is to increase the efficiency of building environments. 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 six pm and allowing rooms to heat up due to lack of ventilation.”
Grosvenor maintains over 17,000 facilities across Australia and oversees $2.2 billion worth of assets under management for large corporate companies.
Rod Kington, national sustainability manager for Grosvenor, says, “We regularly partner with customers and thought leaders to drive innovation that meets the needs of the built environment. The UOW partnership will enable us to incorporate the knowledge gained across our vast building network.”
The research will investigate:
- image recognition-based room occupation detection
- application of deep learning neural networks for room temperature forecasting, and
- a vibration sensor fault diagnosis prototype with results visualised using an online dashboard.
It aims to solve three key practical problems in building management. These include:
- accurate counting of building/room occupation
- accurate forecasting of indoor temperature to help assess the impact of different power regimes, and
- mode of operations for the HVAC system – building a smart sensor that can detect issues in rotating equipment, such as fans, before they become problems.
“Outcomes expected from this project include a readily deployable, accurate and IoT compliant people counter, an accurate indoor temperature forecasting algorithm and a prototype vibration sensor,” adds Wickramasuriya.
Accurate estimation of building occupancy is a prerequisite to optimising both HVAC systems and space utilisation. Current systems used for this purpose are about 66 percent accurate, while the new image recognition-based system developed in this research is about 93 percent accurate.
“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,” says Kington.
Project results are expected by mid-year.
Image courtesy of UOW Australia.