An air handling unit’s energy usage can vary from the original design as components fail or fault – dampers leak or fail to open/close, valves get stuck, and so on. Such problems do not necessarily result in occupant complaints and, consequently, are not even recognized to have occurred. In spite of recent progress in the research and development of diagnostic solutions for air handling units, there is still a lack of reliable, scalable, and affordable diagnostic solutions for such systems. Modeling limitations, measurement constraints, and the complexity of concurrent faults are the main challenges in air handling unit diagnostics. The focus of this paper is on developing diagnostic algorithms for air handling units that can address such constraints more effectively by systematically employing machine-learning techniques. The proposed algorithms are based on analyzing the observed behavior of the system and comparing it with a set of behavioral patterns generated based on various faulty conditions. We show how such a pattern-matching problem can be formulated as an estimation of the posterior distribution of a Bayesian probabilistic model. We demonstrate the effectiveness of the approach by detecting faults in commercial building air handling units.

10aAir-handling unit10aBayesian network10aenergy management10afault detection and diagnosis10aHVAC systems10aMachine learning1 aNajafi, Massieh1 aAuslander, David, M.1 aBartlett, Peter, L.1 aHaves, Philip1 aSohn, Michael, D. uhttps://energyanalysis.lbl.gov/publications/application-machine-learning-fault01689nas a2200205 4500008004100000245007500041210006900116260002500185300001200210520100000222653001801222653000901240653003801249100002901287700001501316700002501331700002601356700002201382856007901404 2002 eng d00aModeling Transient Contaminant Transport in HVAC Systems and Buildings0 aModeling Transient Contaminant Transport in HVAC Systems and Bui aMonterey, California a217-2223 aA mathematical model of the contaminant transport in HVAC systems and buildings is described. The model accounts for transients introduced by control elements such as fans and control dampers. The contaminant transport equations are coupled to momentum equations and mass continuity equations of the air. To avoid modeling variable transport delays directly, ducts are divided into a large number of small sections. Perfect mixing is assumed in each section. Contaminant transport equations are integrated with momentum equations in a way that guarantees mass continuity by using two non-negative velocities for computing the mass transport between elements. Computer simulations illustrate how the model may be used to analyze and design control systems that respond to a sudden release of a toxic contaminant near a building. By coupling transient flow prediction with transient contaminant prediction, the model overcomes a number of problems with existing contaminant transport codes.

10aAir transport10ahvac10aModeling pollutant concentrations1 aFederspiel, Clifford, C.1 aLi, Huilin1 aAuslander, David, M.1 aLorenzetti, David, M.1 aGadgil, Ashok, J. uhttps://energyanalysis.lbl.gov/publications/modeling-transient-contaminant