Ojas Pradhan
Current Organizations / Institutes
The organizations/institutes from the scholar's latest article
Ojas Pradhan has a total of 38 co-authors. Here are the top co-authors by number of shared publications:
- Jin Wen
Drexel University
8 shared publications - Zheng O'NEill
Texas A&M University
8 shared publications - Teresa Wu
Arizona State University
5 shared publications - Kasim Selcuk Candan
Arizona State University, Tempe, AZ, USA
4 shared publications - Jiajing Huang
School of Data Science and Analytics, Kennesaw State University, Marietta, 30060, GA, USA
3 shared publications - Guowen Li
J. Mike Walker’66 Department of Mechanical Engineering, Texas A&M University
2 shared publications
Latest Publications
- 4 June 2024
- Published by Elsevier in Energy and Buildings
- Vol. 317
An entropy-based causality framework for cross-level faults diagnosis and isolation in building HVAC systems
- 4 June 2024
- Published by Elsevier in Energy and Buildings
- Vol. 317
An entropy-based causality framework for cross-level faults diagnosis and isolation in building HVAC systems
- 23 May 2024
- Published by Taylor & Francis in Science and Technology for the Built Environment
- Vol. 30 (8) , 1035-1048
Evaluation of data imputation approaches for multi-stream building systems data 1
- 23 May 2024
- Published by Taylor & Francis in Science and Technology for the Built Environment
- Vol. 30 (8) , 1035-1048
Evaluation of data imputation approaches for multi-stream building systems data 1
- 15 April 2024
- Published by Taylor & Francis in Science and Technology for the Built Environment
- Vol. 30 (5) , 415-432
A hardware-in-the-loop (HIL) testbed for cyber-physical energy systems in smart commercial buildings
- 15 April 2024
- Published by Taylor & Francis in Science and Technology for the Built Environment
- Vol. 30 (5) , 415-432
A hardware-in-the-loop (HIL) testbed for cyber-physical energy systems in smart commercial buildings
- Open Access
- 15 November 2023
- Published by Association for Computing Machinery (ACM)
- p. 307-309
CYDRES: CYber Defense and REsilient System for securing grid-interactive efficient buildings
- 15 November 2023
- Published by Association for Computing Machinery (ACM)
- p. 307-309
Open AccessCYDRES: CYber Defense and REsilient System for securing grid-interactive efficient buildings
- Open Access
- 15 November 2023
- Published by Association for Computing Machinery (ACM)
- p. 296-297
Dynamic Bayesian Networks for Fault Prognosis
A dynamic Bayesian Network (DBN)-based fault prognosis framework is proposed in this study to predict the future fault probabilities of gradual faults. The proposed framework utilizes the trend in prediction error generated from data driven forecasting models to estimate the future fault beliefs. The accuracy and scalability of the proposed method is evaluated using the data from a Modelica-based virtual testbed. Overall, the developed framework demonstrates good potential in estimating future fault probabilities of gradual faults.
- 15 November 2023
- Published by Association for Computing Machinery (ACM)
- p. 296-297
Open AccessDynamic Bayesian Networks for Fault Prognosis
A dynamic Bayesian Network (DBN)-based fault prognosis framework is proposed in this study to predict the future fault probabilities of gradual faults. The proposed framework utilizes the trend in prediction error generated from data driven forecasting models to estimate the future fault beliefs. The accuracy and scalability of the proposed method is evaluated using the data from a Modelica-based virtual testbed. Overall, the developed framework demonstrates good potential in estimating future fault probabilities of gradual faults.
- 18 August 2023
- Published by Drexel University Libraries
A Dynamic Bayesian Network Framework for Data-Driven Fault Diagnosis and Prognosis of Smart Building Systems
Buildings are subject to faults in their heating, ventilation and air-conditioning (HVAC) systems that can lead to excessive energy wastage, poor indoor climate, equipment failures and high maintenance costs. Field studies have shown that employing fault detection, diagnosis and prognosis (FDDP) tools followed up with equipment services and corrections can help achieve up to 40% of energy savings within the HVAC system and improve indoor climate, increase equipment lifecycle and reduce maintenance costs. The increasing adoption of building automation systems (BAS), Internet of Things (IoT) and other smart technologies in recent years have allowed large amounts of data to be continuously collected from building systems. This data-rich environment, along with the surge in data analytics and machine learning tools, has made cost-effective data-driven FDDP strategies possible. Compared to purely physics-based methods, data-driven methods require less explicit knowledge of the underlying physical system, thus are often easier to develop, and can learn certain intricate relationships that exist among data. Within the reported data-driven FDDP methods, there exists a few research gaps: 1) data imputation methods that leverage mutual information from correlated measurements to defy poor data quality from BAS have not been utilized efficiently; 2) there lacks a systematic and scalable fault diagnosis framework that incorporates probabilistic temporal relationships to track fault evolution; 3) existing fault diagnosis strategies typically focus on traditional rule-based control strategies and their scalability for advanced control strategies such as Guideline 36 have not been explored yet; 4) active threats information such as cyber-attacks, are typically not incorporated in an FDDP framework; 5) fault prognosis strategies to preemptively identify gradual faults for predictive maintenance have rarely been studied. This research attempts to address the above-mentioned research gaps through the following: Data Imputation: reported data imputation methods that are suitable for handling and repairing multi-source BAS data are evaluated. Data collected from a medium-sized, mixed-use institution building situated in Stockholm, Sweden and a small commercial building simulated in a laboratory setup is used to evaluate five different data imputation methods. Results demonstrate that incorporating time-lagged cross-correlations within the k-Nearest Neighbor (kNN) method helps to significantly improve the imputation accuracy and minimize the impact of repaired data on data-driven algorithms. Dynamic Bayesian Network (DBN)-based Framework for Cyber-Physical Fault Diagnosis: a DBN framework with discretized conditional probabilities parameters to represent the temporal relationships among building measurements is developed. Both domain knowledge and machine learning methods are used to develop the DBN structure and parameter model. The developed framework is evaluated for both traditional rule-based and Guideline 36 controls using datasets from a real building, a laboratory building, and a virtual testbed. Results show that the developed DBN framework is effective in diagnosing and isolating faults in systems even with different control strategies. The framework also successfully distinguishes whether system abnormalities originate from cyber-attacks or naturally occurring physical faults. Potential future direction to improve fault isolation using modified DBN topological structure is also reported in this study. DBN-based Framework for Fault Prognosis: an extension of the DBN framework in conjunction with Robust Multivariate Temporal (RMT) variate selection is proposed for fault prognosis. The RMT variate selection is used to extract localized temporal features from high dimensional datasets to determine the best inputs for training forecasting models. The expected fault-free behavior of multiple target variates, selected using domain knowledge, is forecasted using incoming data. The prediction errors generated from the forecasting phase are used as evidences in the DBN inference to estimate future fault probabilities. Gradual faults simulated in the virtual testbed are used to evaluate the prognosis framework. Results show that the developed framework is effective in prognosing gradual faults by leveraging the trending growth on the prediction errors. The research presented in this thesis contributes to the overall objective of developing a robust and cost-effective DBN-based framework for fault diagnosis and prognosis of building HVAC systems. Potential solutions to other existing challenges of implementing data-driven FDDP strategies, such as obtaining high-quality datasets, handling and repairing missing data, establishing a baseline model for detecting abnormalities despite other disturbances such as weather and internal conditions changes, and extracting temporal features from timeseries data are also examined.
- 18 August 2023
- Published by Drexel University Libraries
A Dynamic Bayesian Network Framework for Data-Driven Fault Diagnosis and Prognosis of Smart Building Systems
Buildings are subject to faults in their heating, ventilation and air-conditioning (HVAC) systems that can lead to excessive energy wastage, poor indoor climate, equipment failures and high maintenance costs. Field studies have shown that employing fault detection, diagnosis and prognosis (FDDP) tools followed up with equipment services and corrections can help achieve up to 40% of energy savings within the HVAC system and improve indoor climate, increase equipment lifecycle and reduce maintenance costs. The increasing adoption of building automation systems (BAS), Internet of Things (IoT) and other smart technologies in recent years have allowed large amounts of data to be continuously collected from building systems. This data-rich environment, along with the surge in data analytics and machine learning tools, has made cost-effective data-driven FDDP strategies possible. Compared to purely physics-based methods, data-driven methods require less explicit knowledge of the underlying physical system, thus are often easier to develop, and can learn certain intricate relationships that exist among data. Within the reported data-driven FDDP methods, there exists a few research gaps: 1) data imputation methods that leverage mutual information from correlated measurements to defy poor data quality from BAS have not been utilized efficiently; 2) there lacks a systematic and scalable fault diagnosis framework that incorporates probabilistic temporal relationships to track fault evolution; 3) existing fault diagnosis strategies typically focus on traditional rule-based control strategies and their scalability for advanced control strategies such as Guideline 36 have not been explored yet; 4) active threats information such as cyber-attacks, are typically not incorporated in an FDDP framework; 5) fault prognosis strategies to preemptively identify gradual faults for predictive maintenance have rarely been studied. This research attempts to address the above-mentioned research gaps through the following: Data Imputation: reported data imputation methods that are suitable for handling and repairing multi-source BAS data are evaluated. Data collected from a medium-sized, mixed-use institution building situated in Stockholm, Sweden and a small commercial building simulated in a laboratory setup is used to evaluate five different data imputation methods. Results demonstrate that incorporating time-lagged cross-correlations within the k-Nearest Neighbor (kNN) method helps to significantly improve the imputation accuracy and minimize the impact of repaired data on data-driven algorithms. Dynamic Bayesian Network (DBN)-based Framework for Cyber-Physical Fault Diagnosis: a DBN framework with discretized conditional probabilities parameters to represent the temporal relationships among building measurements is developed. Both domain knowledge and machine learning methods are used to develop the DBN structure and parameter model. The developed framework is evaluated for both traditional rule-based and Guideline 36 controls using datasets from a real building, a laboratory building, and a virtual testbed. Results show that the developed DBN framework is effective in diagnosing and isolating faults in systems even with different control strategies. The framework also successfully distinguishes whether system abnormalities originate from cyber-attacks or naturally occurring physical faults. Potential future direction to improve fault isolation using modified DBN topological structure is also reported in this study. DBN-based Framework for Fault Prognosis: an extension of the DBN framework in conjunction with Robust Multivariate Temporal (RMT) variate selection is proposed for fault prognosis. The RMT variate selection is used to extract localized temporal features from high dimensional datasets to determine the best inputs for training forecasting models. The expected fault-free behavior of multiple target variates, selected using domain knowledge, is forecasted using incoming data. The prediction errors generated from the forecasting phase are used as evidences in the DBN inference to estimate future fault probabilities. Gradual faults simulated in the virtual testbed are used to evaluate the prognosis framework. Results show that the developed framework is effective in prognosing gradual faults by leveraging the trending growth on the prediction errors. The research presented in this thesis contributes to the overall objective of developing a robust and cost-effective DBN-based framework for fault diagnosis and prognosis of building HVAC systems. Potential solutions to other existing challenges of implementing data-driven FDDP strategies, such as obtaining high-quality datasets, handling and repairing missing data, establishing a baseline model for detecting abnormalities despite other disturbances such as weather and internal conditions changes, and extracting temporal features from timeseries data are also examined.
- Top Cited Papers
- 27 March 2023
- Published by Elsevier in Applied Energy
- Vol. 339
A review of data-driven fault detection and diagnostics for building HVAC systems
- 27 March 2023
- Published by Elsevier in Applied Energy
- Vol. 339
Top Cited PapersA review of data-driven fault detection and diagnostics for building HVAC systems
- 14 June 2022
- Published by Taylor & Francis in Science and Technology for the Built Environment
- Vol. 28 (9) , 1138-1149
A cosine-based correlation information entropy approach for building automatic fault detection baseline construction
Building automatic fault detection and diagnosis (AFDD) technologies have shown great potential for energy savings. To enable AFDD, a baseline depicting the normal operation mode is needed to detect whether the building operation deviates from normality. Existing research using physics-based knowledge and models for AFDD has mainly taken a trial-and-error approach to determine if a given baseline is sufficient via empirical experiments. A mechanism to support decisions such as how many samples and what samples should be included in the baseline is currently lacking. In this study, a data-driven method for AFDD baseline construction based on information entropy is developed. The entropy is derived based on cosine similarity among typical building automation system measurements in conjunction with outdoor weather information. The performance of the proposed method is evaluated using real building data. Evaluation results indicate that the fault detection strategy adopting the proposed method has similar or better accuracy in detecting faults compared to the same fault detection strategy using the baseline construction method from the literature. In addition, the use of entropy enables the proposed method to automatically construct and assess the baseline consisting of information-rich samples.
- 14 June 2022
- Published by Taylor & Francis in Science and Technology for the Built Environment
- Vol. 28 (9) , 1138-1149
A cosine-based correlation information entropy approach for building automatic fault detection baseline construction
Building automatic fault detection and diagnosis (AFDD) technologies have shown great potential for energy savings. To enable AFDD, a baseline depicting the normal operation mode is needed to detect whether the building operation deviates from normality. Existing research using physics-based knowledge and models for AFDD has mainly taken a trial-and-error approach to determine if a given baseline is sufficient via empirical experiments. A mechanism to support decisions such as how many samples and what samples should be included in the baseline is currently lacking. In this study, a data-driven method for AFDD baseline construction based on information entropy is developed. The entropy is derived based on cosine similarity among typical building automation system measurements in conjunction with outdoor weather information. The performance of the proposed method is evaluated using real building data. Evaluation results indicate that the fault detection strategy adopting the proposed method has similar or better accuracy in detecting faults compared to the same fault detection strategy using the baseline construction method from the literature. In addition, the use of entropy enables the proposed method to automatically construct and assess the baseline consisting of information-rich samples.
- Open Access
- 17 November 2021
- Published by Association for Computing Machinery (ACM)
- p. 365-368
Dynamic bayesian network-based fault diagnosis for ASHRAE guideline 36
A dynamic Bayesian Network (DBN) is proposed in this study to diagnose faults for building heating, ventilating, and air-conditioning (HVAC) systems that are controlled based on American Society of Heating, Refrigerating and Air-Conditioning Engineers (ASHRAE)'s Guideline 36: High Performance Sequence of Operation for HVAC (hereinafter Guideline 36). Guideline 36 provides recommendations on supervisory-level control. HVAC systems that adopt these strategies have more comprehensive setpoint reset schedules and more advanced control logics than typical HVAC systems. It is hence of interest to understand how faults might affect the performance of HVAC systems that are controlled based on Guideline 36 and whether we can develop strategies to diagnose and isolate faults even for systems with such comprehensive control sequences. Contrarily to a Bayesian Network (BN), DBN method incorporates the temporal dependencies of fault nodes between time steps using temporal conditional probabilities. This allows fault beliefs to accumulate over time and thus improves diagnosis accuracy. In this study, the accuracy and scalability of the proposed method is evaluated using the data from a Modelica-based simulated testbed. Overall, the developed DBN shows good potential in diagnosing and isolating the root fault causes for HVAC systems that are controlled based on the Guideline 36 control sequence.
- 17 November 2021
- Published by Association for Computing Machinery (ACM)
- p. 365-368
Open AccessDynamic bayesian network-based fault diagnosis for ASHRAE guideline 36
A dynamic Bayesian Network (DBN) is proposed in this study to diagnose faults for building heating, ventilating, and air-conditioning (HVAC) systems that are controlled based on American Society of Heating, Refrigerating and Air-Conditioning Engineers (ASHRAE)'s Guideline 36: High Performance Sequence of Operation for HVAC (hereinafter Guideline 36). Guideline 36 provides recommendations on supervisory-level control. HVAC systems that adopt these strategies have more comprehensive setpoint reset schedules and more advanced control logics than typical HVAC systems. It is hence of interest to understand how faults might affect the performance of HVAC systems that are controlled based on Guideline 36 and whether we can develop strategies to diagnose and isolate faults even for systems with such comprehensive control sequences. Contrarily to a Bayesian Network (BN), DBN method incorporates the temporal dependencies of fault nodes between time steps using temporal conditional probabilities. This allows fault beliefs to accumulate over time and thus improves diagnosis accuracy. In this study, the accuracy and scalability of the proposed method is evaluated using the data from a Modelica-based simulated testbed. Overall, the developed DBN shows good potential in diagnosing and isolating the root fault causes for HVAC systems that are controlled based on the Guideline 36 control sequence.