PreprintPDF Available
Preprints and early-stage research may not have been peer reviewed yet.

Abstract and Figures

A comparative study between using a dynamic Bayesian network (DBN) against using a static Bayesian network (BN) for building heating ventilating, and air conditioning fault diagnosis (HVAC) is presented. Contrarily to a static BN, DBN method incorporates temporal dependencies between fault nodes between timesteps using temporal conditional probabilities. This allows fault beliefs to accumulate over time and hence improves the diagnosis accuracy. The two methods are evaluated using real building data obtained from a campus building. Overall, the DBN showed improved fault belief when diagnosing and isolating faults across various components and subsystems. Sensitivity tests on the temporal conditional probabilities for DBN showed that the model is robust.
Content may be subject to copyright.
Ojas Pradhan is a doctoral student in the Building Science and Engineering Group (BSEG) at Drexel University, Philadelphia, PA. Jin Wen, Ph.D. is a Professor
in the Department of Civil, Architectural, and Environmental Engineering department at Drexel University, Philadelphia, PA. Yimin Chen, Ph.D. is a Senior
Scientific Engineering Associate in the Building Technology & Urban Systems Division at Lawrence Berkeley National Laboratory (LBNL), Berkeley, CA. Teresa
Wu, Ph.D. is a Professor of Industrial Engineering, School of Computing, Informatics, Decision Systems Engineering at Arizona State University, Tempe, AZ.
Zheng O’Neill, Ph.D. is an Associate Professor in the Department of Mechanical Engineering at Texas A&M University at College Station, TX.
Dynamic Bayesian Network for Fault Diagnosis
Ojas Pradhan Jin Wen, PhD Yimin Chen, PhD Teresa Wu, PhD Zheng O’Neill, PhD
A comparative study between using a dynamic Bayesian network (DBN) against using a static Bayesian network (BN) for building heating ventilating,
and air conditioning fault diagnosis (HVAC) is presented. Contrarily to a static BN, DBN method incorporates temporal dependencies between fault
nodes between timesteps using temporal conditional probabilities. This allows fault beliefs to accumulate over time and hence improves the diagnosis accuracy.
The two methods are evaluated using real building data obtained from a campus building. Overall, the DBN showed improved fault belief when diagnosing
and isolating faults across various components and sub-systems. Sensitivity tests on the temporal conditional probabilities for DBN showed that the model
is robust.
Studies and field practices have shown that applying automated fault detection and diagnosis (AFDD) tools in
HVAC systems, followed up with service and corrections, can help reduce the energy waste, improve occupant comfort
and extend equipment lifecycle (Piette et al. 2001). Within the AFDD framework, the process of locating and isolating
the fault root causess has been challenging since a detailed and accurate reasoning of the HVAC system and its control
strategies is required (Zhao et al. 2015, 2017). Several inference and classification approaches have been developed and
used as a fault diagnosis tool in the field. Among them, Bayesian networks (BN) based on the probability inference
theorem that infers the fault causes based on a set of observations have been popular. The BN models have performed
well even when complete information about the system is not available (Mirnaghi et al. 2020).
Successfully implemented BNs for fault diagnosis for different HVAC components have been reported in existing
literature for both component-level and whole building fault diagnosis. For instance, Zhao et al. proposed a component-
level diagnostic BN for 28 different faults in air handling units (AHUs) in (Zhao et al. 2015, 2017), and for intelligent
chiller FDD in (Zhao et al. 2013). Similarly, Xiao et al. (2014) developed a BN based FDD strategy for diagnosis typical
VAV terminal unit faults. For whole building fault diagnosis, Chen et al. (2018) developed a BN model using expert and
physical knowledge using weather and schedule information-based pattern matching (WPM). Although the existing
studies demonstrate good potentials of BNs for both component-level and whole building fault diagnosis, the BN
structure model used are event-based, time-invariant models (i.e., information from the previous time steps are not
carried over to the next time step). Instead, a DBN model is more suitable for a continuous-time engineering system
such as a building HVAC system (Murphy 2002). The main advantage is that a DBN carries over past information
which allows fault belief to accumulate over time. Therefore, a DBN increases diagnosis accuracy by eliminating
measurement errors and only retain faults that are persistent over time.
Given the lack of a comprehensive comparison study between the conventional BN and a DBN, in this study, the
WPM-BN model developed by Chen et al. (2018) is cssonverted to a DBN for whole building fault diagnosis. Fault free
and artificially implemented fault data from a real campus building are used to evaluate the effectiveness of the DBN.
Dynamic Bayesian Network
Bayesian networks used for fault diagnosis are directed acyclic network in which the nodes represent the faults
and symptoms (evidences) from measurements and observations, and the arcs represent the direct probabilistic
dependencies among the connected nodes. The probability of a fault based on observed symptoms, defined as the
posterior probability, P(F|S) can be calculated using the Bayes’ theorem as (Murphy 2012):
𝑃(𝑆) (1)
Where, P(F) is the prior probability of a fault occurring, P(S|F) is the conditional probability of a symptom
occurring given the fault state, and P(S) is the observation of symptom states.
A DBN is an extension of the conventional static BN which can represent temporal relationships of the fault and
symptom nodes between different time steps. Figure 1 shows the difference between a BN and a DBN with one fault
and one symptom node for n-time steps. In a static BN, the probability of a fault node (Ft+1) only depends on the
corresponding symptom node (St+1), whereas, in a DBN, the probability of node Ft+1 depends on its symptom nodes
St+1 and its own values at the previous time step Ft.
Figure 1. Schematics of a static BN (left) and a dynamic BN (right)
The additional dependency on the fault node from the previous time step requires a temporal conditional
probability table (CPT) between P(Ft+1|F), to define the relationship. The temporal CPTs carry over posterior
probabilities from the previous to the current time step.
Similar to the faulty-symptom CPTs or the prior probability, temporal CPTs can be estimated either from historical
process data or from expert knowledge. Maximum likelihood estimation (MLE) and Bayesian estimation (BE) are some
of the techniques used to estimate the unknown probabilities (Amin et al. 2019). However, utilizing statistical techniques
to obtain the probability distributions is a major challenge for building system data since (i) ground truth data that
confirms the root fault causes of natural-occurring faults are hard to obtain, and (ii) even if the ground truth data exists
for a specific building, the probability distributions learned from data in that specific building system are usually not
scalable to other building systems (Chen et al. 2018). Hence, in this study, the temporal CPT are also developed using
expert knowledge and sensitivity analysis is performed to evaluate the impact of the temporal CPT values in the fault
diagnosis outcome.
The development of the DBN methodology is divided into seven sub-tasks. First, a dynamic baseline method is
developed to automatically generate a baseline for each incoming snapshot building system data. Pattern matching
method as described by Chen et al. (2017) is used to identify, from a historical baseline data pool, those building data
that have similar weather and schedule information. The purpose of this is to compare incoming snapshot data with
historical baseline data that are under similar weather and internal load conditions. Following this, the DBN structure
which includes the nodes for fault and evidence, and the causal relation between them based on expert knowledge is
developed. Various probability distributions for each fault node and evidence node, including the LEAK distribution is
calculated and assigned in the parameter model. Next, code to generate the evidence event is developed to compare the
incoming snapshot data with the baseline. An evidence event is classified to be abnormal if the incoming data is
significantly different from the baseline, i.e., is higher than the statistical threshold. Based on the judgment in this step,
the Bayesian inference is trigged, and the posterior probabilities of each fault node is calculated based on the Bayes’
theorem. Finally, the posterior probabilities are ranked, and the root fault is isolated based on pre-defined rules.
The DBN structure model is based on 13 fault nodes that represent faults in the whole building as described by
Chen et al. (2018). 15 evidence nodes that represent the observable fault symptoms are developed for the faults. The
evidence nodes are established from two sources: direct measurements and virtual measurements (combination of direct
measurements). To connect the fault nodes with the evidence nodes, causal relations based on expert knowledge are
developed for each fault case that indicate the probability set of evidence along with the severity level and direction
(positive or negative) of the evidence.
The method is evaluated using a campus building at Drexel University. This building is a seven-story, mixed use
commercial building that includes classrooms, laboratory space and offices. The HVAC system configuration consists
of one chiller, two steam-to-hot water heat exchange systems (for hot water and VAV reheat) and 3 AHUs. All the
HVAC equipment is controlled and monitored in a BAS through which faults can be implemented remotely.
14 faults were artificially implemented in the test building. Data were collected for the periods when the faults
were implemented. Data that represented baseline conditions were also collected. Both data were used to evaluate the
developed DBN. It was found that when applying static BN or DBN for fault diagnosis, both methods correctly
diagnosed 11 out of the 14 cases, i.e., identified the root causes of the faults. For two of the three reminding cases,
both methods ranked the implemented faults and some other faults as root causes. A closer manual inspection of the
data revealed that nature faults have occurred during these two cases and the ground thruth was unclear. For the other
reminding case, the implemented fault did not yield any symptom.
Although both methods perform similiarly, the major benefit of using a DBN is seen when analyzing the time
series plots for posterior probabilities of the fault nodes. For example, on 9/7/2016, a supply air temperature sensor
negative bias fault has been artificially implemented on AHU-2 in the building. According to the diagnosis results, the
fault belief (posterior probabilities) obtained for AHU2-SA-Temp-Bias-N node is stronger when using a DBN than a
static BN. Figure 2 presents the posterior probability of the top 3 ranked faults using a static BN and a DBN,
respectively. The AHU2-SA-Temp-Bias-N fault node (shown in blue) is observed to be consistently high inside the fault
window when using a DBN. Since a DBN allows evidence to accumulate over time, whereas only evidence from a single
time step is considered for inference in a static BN, the fault belief is often limited to a lower value when using a static
BN. Similar trends are seen across rest of the fault cases evaluated in this section.
Figure 2. Time series posterior probability result using a static and dynamic BN for top three fault nodes (2016/09/07)
A parameter sensitivity test is performed to evaluate the impact of the temporal conditional probabilities on the
diagnosis accuracy. It is seen that the posterior probability values of some fault nodes change, however, the fault isolation
accuracy is not affected and does not change the fault ranking. Therefore, the developed DBN framework is robust
against the change in temporal conditional probabilities and can successfully diagnose faults with a stronger fault belief
than a static BN.
Amin M.T., F. Khan and S. Imtiaz. 2019. Fault detection and pathway analysis using a dynamic Bayesian network, Chemical
Engineering Science. 195: 777–790
Chen Y. and J. Wen. 2017. A Whole Building Fault Detection Using Weather Based Pattern Matching and Feature Based
PCA Method. IEEE International Conference on Big Data (BIGDATA).
Chen Y., J. Wen, T. Chen and O. Pradhan. 2018. Bayesian Networks for Whole Building Level Fault Diagnosis and Isolation.
5th International High Performance Buildings Conference at Purdue.
Mirnaghi M.S., and F. Haghighat. 2020. Fault detection and diagnosis of large-scale HVAC systems in buildings using data-
driven methods: A comprehensive review, Energy and Buildings.
Murphy, K.P. 2002. Dynamic Bayesian Networks: Representation, Inference and Learning.
Murphy, K.P. 2012. Machine Learning: A Probabilistic Perspective, Chapter 2, Probability. MIT press.
Piette M.A., S.K. Kinney and P. Haves. 2001. Analysis of an information monitoring and diagnostic system to improve
building operations, Energy and Buildings.
Xiao, F., Y. Zhao , J. Wen and S. Wang. 2014. Bayesian network based FDD strategy for variable air volume terminals,
Automation in Construction.
Zhao Y., F. Xiao and S. Wang. 2013. An intelligent chiller fault detection and diagnosis methodology using Bayesian belief
network, Energy and Buildings.
Zhao Y., J. Wen and S. Wang. 2017. Diagnostic Bayesian networks for diagnosing air handling units faults - Part II: Faults in
coils and sensors, Applied Thermal Engineering. 90: 145–157.
Zhao Y., J. Wen, F. Xiao, X. Yang and S. Wang. 2015. Diagnostic Bayesian networks for diagnosing air handling units faults
– Part I: Faults in dampers, fans, filters and sensors, Applied Thermal Engineering. 111: 1272–1286.
ResearchGate has not been able to resolve any citations for this publication.
Conference Paper
Full-text available
Buildings consume about 40% of primary energy in the U.S., and 51% of the primary energy usage in commercial buildings are consumed by heating, ventilation and air conditioning (HVAC) system. Malfunctioning sensors, components, and control systems, as well as degrading HVAC and lighting components are main the reasons for energy waste and unsatisfactory indoor environment. In building HVAC systems, faults occurring in one component or equipment can cause abnormality in other closed subsystems. Therefore, a system level fault diagnosis method is helpful to locate root-cause for such faults. Bayesian network (BN) is a prevalent tool in fault diagnosis which can handle probabilistic reasoning of uncertainty. In this paper, a two-layer Bayesian network which consists of fault layer and fault symptom layer is developed to diagnose system level faults that have an impact on multiple subsystems for building HVAC system during a cooling operation mode. Weather/schedule information based Pattern Matching (WPM) method is developed create the baseline data and to generate LEAK probabilities for the developed BN. BAS data from a campus building during the cooling season are collected to evaluate the effectiveness of the proposed method.
Full-text available
Faults in air handling units (AHUs) affect the building energy efficiency and indoor environmental quality significantly. There is still a lack of effective methods for diagnosing AHU faults automatically. In this study, a diagnostic Bayesian networks (DBNs)-based method is proposed to diagnose 28 faults, which cover most of common faults in AHUs. The basic idea is to fully utilize all diagnostic information in an information fusion way. The DBNs are developed based on a comprehensive survey of AHU fault detection and diagnosis (FDD) methods and fault patterns reported in three AHU FDD projects including NIST 6964, ASHRAE projects RP-1020 and RP-1312. The study is published in two parts. In the Part I, the methodology is described firstly. Four DBNs are developed to diagnose faults in fans, dampers, ducts, filters and sensors. There are 10 typical faults concerned and 14 fault detectors introduced. Evaluations are made using the experimental data from the ASHRAE Project RP-1312. Results show that the DBN-based method is effective in diagnosing faults even when the diagnostic information is uncertain and incomplete.
Full-text available
This paper presents a diagnostic Bayesian network (DBN) for fault detection and diagnosis (FDD) of variable air volume (VAV) terminals. The structure of the DBN illustrates qualitatively the casual relationships between faults and symptoms. The parameters of the DBN describe quantitatively the probabilistic dependences between faults and evidence. The inputs of the DBN are the evidences which can be obtained from measurements in building management systems (BMSs) and manual tests. The outputs are the probabilities of faults concerned. Two rules are adopted to isolate the fault on the basis of the fault probabilities to improve the robustness of the method. Compared with conventional rule-based FDD methods, the proposed method can work well with uncertain and incomplete information, because the faults are reported with probabilities rather than in the Boolean format. Evaluations are made on a dynamic simulator of a VAV air-conditioning system serving an office space using TRNSYS. The results show that it can correctly diagnose ten typical VAV terminal faults.
Abnormal operation of HVAC systems can result in an increase in energy usage as well as poor indoor air quality, thermal discomfort, and low productivity. Building automated systems (BAS) collects a massive amount of data related to the operation of each component of HVAC systems. Although BAS has been implemented in many buildings over the past decade, the collected data have not been analyzed thoroughly. Some studies have relied on data-mining methods to predict, detect, and diagnose faults in HVAC systems. This paper critically reviews the existing literature and identifies the research gaps in data-driven data mining fault detection and diagnosis (FDD) methods studies on HVAC systems. In this review, data-driven based FDD methods are classified into three classes, namely supervised, unsupervised, and hybrid-learning methods. The hybrid approaches are introduced as the preferred methods among the existing approaches to be used in online FDD processes. Furthermore, some components of HVAC systems and their potential faults are discussed in detail. The outcome of this review shows that data-driven based approaches are more promising for the FDD process of large-scale HVAC systems than model-based and knowledge-based ones. Moreover, an optimal approach could involve both supervised and unsupervised learning (hybrid methods).
A dynamic Bayesian network (DBN) based fault detection, root cause diagnosis, and fault propagation pathway identification scheme is proposed. The proposed methodology generates evidence from monitored process data and uses the information to update the DBN that captures the process knowledge. A new dynamic Bayesian anomaly index (DBAI) based control chart is proposed for detection purpose. Following the detection of the fault(s), root cause(s) is diagnosed using the smoothing inference of a DBN, and fault propagation pathway is identified from the cause-effect relationships among the process variables. The proposed methodology is applied to a binary distillation column and a continuous stirred tank heater (CSTH). The result shows that it can detect the fault and diagnose the root cause of the fault precisely. The result has been compared to the performance of the Shewhart control chart, principal component analysis (PCA) and static BN. The comparative study confirms that the proposed methodology is a more efficient fault detection and diagnosis (FDD) tool.
A generic intelligent fault detection and diagnosis (FDD) strategy is proposed in this study to simulate the actual diagnostic thinking of chiller experts. A three-layer Diagnostic Bayesian Network (DBN) is developed to diagnose chiller faults based on the Bayesian Belief Network (BBN) theory. The structure of the DBN is a graphical and qualitative illustration of the intrinsic causal relationships among causal factors in Layer 1, faults in Layer 2 and fault symptoms in Layer 3. The parameters of the DBN represent the quantitative probabilistic relationships among the three layers. To diagnose chiller faults, posterior probabilities of the faults under observed evidences are calculated based on the probability analysis and the graph theory. Compared with other FDD strategies, the proposed strategy can make use of more useful information of the chiller concerned and expert knowledge. It is effective and efficient in diagnosing faults based on uncertain, incomplete and conflicting information. Evaluation of the strategy was made on a 90-ton water-cooled centrifugal chiller reported in ASHRAE RP-1043.
This paper discusses a demonstration of a technology to address the problem that buildings do not perform as well as anticipated during design. We partnered with an innovative building operator to evaluate a prototype information monitoring and diagnostic system (IMDS). The IMDS consists of a set of high-quality sensors, data acquisition software and hardware, and data visualization software including a web-based remote access system, that can be used to identify control problems and equipment faults. The information system allowed the operators to make more effective use of the building control system and freeing up time to take care of other tenant needs. They report observing significant improvements in building comfort, potentially improving tenant health and productivity. The reduction in the labor costs to operate the building is about US$ 20,000 per year, which alone could pay for the information system in about 5 years. A control system retrofit based on findings from the information system is expected to reduce energy use by 20% over the next year, worth over US$ 30,000 per year in energy cost savings. The operators are recommending that similar technology be adopted in other buildings.
Modelling sequential data is important in many areas of science and engineering. Hidden Markov models (HMMs) and Kalman filter models (KFMs) are popular for this because they are simple and flexible. For example, HMMs have been used for speech recognition and bio-sequence analysis, and KFMs have been used for problems ranging from tracking planes and missiles to predicting the economy. However, HMMs and KFMs are limited in their “expressive power”. Dynamic Bayesian Networks (DBNs) generalize HMMs by allowing the state space to be represented in factored form, instead of as a single discrete random variable. DBNs generalize KFMs by allowing arbitrary probability distributions, not just (unimodal) linear-Gaussian. In this thesis, I will discuss how to represent many different kinds of models as DBNs, how to perform exact and approximate inference in DBNs, and how to learn DBN models from sequential data. In particular, the main novel technical contributions of this thesis are as follows: a way of representing Hierarchical HMMs as DBNs, which enables inference to be done in O(T) time instead of O(T 3), where T is the length of the sequence; an exact smoothing algorithm that takes O(log T) space instead of O(T); a simple way of using the junction tree algorithm for online inference in DBNs; new complexity bounds on exact online inference in DBNs; a new deterministic approximate inference algorithm called factored frontier; an analysis of the relationship between the BK algorithm and loopy belief propagation; a way of applying Rao-Blackwellised particle filtering to DBNs in general, and the SLAM (simultaneous localization and mapping) problem in particular; a way of extending the structural EM algorithm to DBNs; and a variety of different applications of DBNs. However, perhaps the main value of the thesis is its catholic presentation of the field of sequential data modelling.