01850nas a2200145 4500008004100000245007900041210006900120520131700189100002001506700002501526700002401551700001801575700002201593856008901615 2010 eng d00aModeling and Measurement Constraints in Fault Diagnostics for HVAC Systems0 aModeling and Measurement Constraints in Fault Diagnostics for HV3 aMany studies have shown that energy savings of five to fifteen percent are achievable in commercial buildings by detecting and correcting building faults, and optimizing building control systems. However,in spite of good progress in developing tools for determining HVAC diagnostics, methods to detect faults in HVAC systems are still generally undeveloped. Most approaches use numerical filtering or parameter estimation methods to compare data from energy meters and building sensors to predictions from mathematical or statistical models. They are effective when models are relatively accurate and data contain few errors. In this paper, we address the case where models are imperfect and data are variable, uncertain, and can contain error. We apply a Bayesian updating approach that is systematic in managing and accounting for most forms of model and data errors. The proposed method uses both knowledge of first principle modeling and empirical results to analyze the system performance within the boundaries defined by practical constraints. We demonstrate the approach by detecting faults in commercial building air handling units. We find that the limitations that exist in air handling unit diagnostics due to practical constraints can generally be effectively addressed through the proposed approach.1 aNajafi, Massieh1 aAuslander, David, M.1 aBartlett, Peter, L.1 aHaves, Philip1 aSohn, Michael, D. uhttps://simulationresearch.lbl.gov/publications/modeling-and-measurement-constraints00472nas a2200121 4500008004100000245007400041210006900115100002000184700002500204700001800229700002200247856008100269 2010 eng d00aA Statistical Pattern Analysis Framework for Rooftop Unit Diagnostics0 aStatistical Pattern Analysis Framework for Rooftop Unit Diagnost1 aNajafi, Massieh1 aAuslander, David, M.1 aHaves, Philip1 aSohn, Michael, D. uhttps://simulationresearch.lbl.gov/publications/statistical-pattern-analysis00509nas a2200133 4500008004100000245007900041210006900120260001200189100002000201700002500221700002400246700001800270856008700288 2008 eng d00aApplication of Machine Learning in Fault Diagnostics of Mechanical Systems0 aApplication of Machine Learning in Fault Diagnostics of Mechanic c10/20081 aNajafi, Massieh1 aAuslander, David, M.1 aBartlett, Peter, L.1 aHaves, Philip uhttps://simulationresearch.lbl.gov/publications/application-machine-learning-fault01212nas a2200145 4500008004100000245009100041210006900132260001200201520069300213100002000906700002500926700002400951700001800975856007300993 2008 eng d00aFault Diagnostics and Supervised Testing: How Fault Diagnostic tools can be Proactive?0 aFault Diagnostics and Supervised Testing How Fault Diagnostic to c11/20083 aThe topic of fault detection and diagnostics (FDD) is studied from the perspective of proactive testing. Unlike most research focus in the diagnosis area in which system outputs are analyzed for diagnosis purposes, in this paper the focus is on the other side of the problem: manipulating system inputs for better diagnosis reasoning. In other words, the question of how diagnostic mechanisms can direct system inputs for better diagnosis analysis is addressed here. It is shown how the problem can be formulated as decision making problem coupled with a Bayesian Network based diagnostic mechanism. The developed mechanism is applied to the problem of supervised testing in HVAC systems.1 aNajafi, Massieh1 aAuslander, David, M.1 aBartlett, Peter, L.1 aHaves, Philip uhttp://www.actapress.com/Content_of_Proceeding.aspx?proceedingID=50301442nas a2200145 4500008004100000245008800041210006900129260001000198520092700208100002001135700002501155700002401180700001801204856007401222 2008 eng d00aOvercoming the Complexity of Diagnostic Problems due to Sensor Network Architecture0 aOvercoming the Complexity of Diagnostic Problems due to Sensor N c11/083 a
In fault detection and diagnostics, limitations coming from the sensor network architecture are one of the main challenges in evaluating a system's health status. Usually the design of the sensor network architecture is not solely based on diagnostic purposes, other factors like controls, financial constraints, and practical limitations are also involved. As a result, it quite common to have one sensor (or one set of sensors) monitoring the behaviour of two or more components. This can significantly extend the complexity of diagnostic problems. In this paper a systematic approach is presented to deal with such complexities. It is shown how the problem can be formulated as a Bayesian network based diagnostic mechanism with latent variables. The developed approach is also applied to the problem of fault diagnosis in HVAC systems, an application area with considerable modeling and measurement constraints.
1 aNajafi, Massieh1 aAuslander, David, M.1 aBartlett, Peter, L.1 aHaves, Philip uhttps://www.actapress.com/Content_Of_Proceeding.aspx?ProceedingID=50301795nas a2200181 4500008004100000050001500041245009300056210006900149260001200218300001200230490000800242520124800250100001801498700001701516700002001533700001301553856004701566 2007 eng d aLBNL-6097900aA Semi-automated Commissioning Tool for VAV Air Handling Units: Functional Test Analyzer0 aSemiautomated Commissioning Tool for VAV Air Handling Units Func c01/2007 a380-3910 v1133 aA software tool that automates the analysis of functional tests for air-handling units is described. The tool compares the performance observed during manual tests with the performance predicted by simple models of the components under test that are configured using design information and catalog data. Significant differences between observed and expected performance indicate the presence of faults. Fault diagnosis is performed by analyzing the variation of these differences with operating point using expert rules and fuzzy inferencing.
The tool has a convenient user interface to facilitate manual entry of measurements made during a test. A graphical display compares the measured and expected performance, highlighting significant differences that indicate the presence of faults. The tool is designed to be used by commissioning providers conducting functional tests as part of either new building commissioning or retro-commissioning, as well as by building owners and operators conducting routine tests to check the performance of their HVAC systems. The paper describes the input data requirements of the tool, the software structure, the graphical interface, and summarizes the development and testing process used.
1 aHaves, Philip1 aKim, Moosung1 aNajafi, Massieh1 aXu, Peng uhttp://gaia.lbl.gov/btech/papers/60979.pdf