Development of datasets, inverse models, and methods for adaptive fault detection and diagnostics in commercial buildings

点击翻译按钮获取中文摘要

30 to 50% of the energy use in commercial buildings is wasted due to poorly maintained, degraded, and improperly controlled equipment and components. Given that indoor climate control in commercial buildings accounts for 13% of the total energy use and 11% of the CO2 emissions in Canada, optimizing their operation represents great potential to reduce our environmental impact and to provide comfortable, healthy, and productive indoor environments. The overall objective of this research program is to optimize the energy use and occupant comfort in commercial buildings by using sensor, meter, and actuator data gathered in modern building automation and control systems. With this vision in mind, the research program will address four fundamental gaps in the literature: (1) create a dataset comprising common building faults, their sensory symptoms, occurrence frequencies, and impact on energy use and comfort; (2) develop inverse models that explain multiphysical processes and occupant behaviour in buildings from sensor, meter, and actuator data; (3) develop scalable methods to diagnose physical faults in building systems and components; and (4) develop scalable methods to diagnose and correct soft faults in controls programming. The research approaches entail field-scale data collection and analyses using existing controls and automation infrastructure of three office buildings in Carleton University, field trials, and building performance simulation. The proposed research program will make significant short-term and long-term intellectual, environmental, economic, and HQP contributions to Canada. New datasets, models, and methods will be created. These will help us understand how our buildings perform and are used today. Wider usage of fault detection and diagnostics methods developed in this research program will reduce the environmental and economic impact of buildings. Adoption of these methods by a Canadian building data analytics company will contribute to our knowledge-based economy. More importantly, two PhD, two MSc, and three undergraduate students will work on data from real buildings, learn their systems and components, and their shortcomings. In a team environment, they will conduct interdisciplinary research on building physics, indoor environmental quality, building performance simulation, and data-science. These skills are invaluable, as few engineering programs in Canada provide a comprehensive background in building engineering, despite buildings' major role in our economy and society.