Data-driven remote fault detection and diagnosis of HVAC terminal units using machine learning techniques

PhD Thesis


Dey, M. (2020). Data-driven remote fault detection and diagnosis of HVAC terminal units using machine learning techniques. PhD Thesis London South Bank University School of Engineering https://doi.org/10.18744/lsbu.9499w
AuthorsDey, M.
TypePhD Thesis
Abstract

The modernising and retrofitting of older buildings has created a drive to install building management systems (BMS) aimed to assist building managers pave the way towards smarter energy use, improve maintenance and increase occupants comfort inside a building. BMS is a computerised control system that controls and monitors a building’s equipment, services such as lighting, ventilation, power systems, fire and security systems, etc. Buildings are becoming more and more complex environments and energy consumption has globally increased to 40% in the past decades. Still, there is no generalised solution or standardisation method available to maintain and handle a building’s energy consumption. Thus this research aims to discover an intelligent solution for the building’s electrical and mechanical units that consume the most power. Indeed, remote control and monitoring of Heating, Ventilation and Air-Conditioning (HVAC) units based on the received information through the thousands of sensors and actuators, is a crucial task in BMS. Thus, it is a foremost task to identify faulty units automatically to optimise running and energy usage. Therefore, a comprehensive analysis on HVAC data and the development of computational intelligent methods for automatic fault detection and diagnosis is been presented here for a period of July 2015 to October 2015 on a real commercial building in London. This study mainly investigated one of the HVAC sub-units namely Fan-coil unit’s terminal unit (TU). It comprises of the three stages: data collection, pre-processing, and machine learning. Further to the aspects of machine learning algorithms for TU behaviour identification by employing unsupervised, supervised, and semi-supervised learning algorithms and their combination was employed to make an automatic intelligent solution for building services. The accuracy of these employed algorithms have been measured in both training and testing phases, results compared with different suitable algorithms, and validated through statistical measures. This research provides an intelligent solution for the real time prediction through the development of an effective automatic fault detection and diagnosis system creating a smarter way to handle the BMS data for energy optimisation.

Year2020
PublisherLondon South Bank University
Digital Object Identifier (DOI)https://doi.org/10.18744/lsbu.9499w
File
License
File Access Level
Open
Publication process dates
Deposited31 Jul 2023
Funder/ClientDemand Logic
Innovate UK
Additional information

Collaborative PhD studentship between London South Bank University and Demand Logic Ltd. as a part of the Innovate UK funded research project (EP/M506734/1)

Permalink -

https://openresearch.lsbu.ac.uk/item/9499w

Download files


File
Thesis.pdf
License: CC BY 4.0
File access level: Open

  • 55
    total views
  • 43
    total downloads
  • 1
    views this month
  • 1
    downloads this month

Export as

Related outputs

Power Grid Frequency Forecasting from μPMU Data using Hybrid Vector-Output LSTM network
Dey, M., Wickramarachchi, D., Rana, S.P., Simmons, .C.V and Dudley, S. (2023). Power Grid Frequency Forecasting from μPMU Data using Hybrid Vector-Output LSTM network. 2023 IEEE PES Innovative Smart Grid Technologies Europe (ISGT EUROPE). 23 - 26 Oct 2023 IEEE. https://doi.org/10.1109/ISGTEUROPE56780.2023.10408056
Power Grid Frequency Forecasting from μPMU Data using Hybrid Vector-Output LSTM network
Dey, M., Wickramarachchi, D., Rana, S.P., Simmons, C.v. and Dudley, S. (2023). Power Grid Frequency Forecasting from μPMU Data using Hybrid Vector-Output LSTM network. 2023 IEEE PES Innovative Smart Grid Technologies Europe (ISGT EUROPE). https://doi.org/10.1109/isgteurope56780.2023.10408056
Radiation-free Microwave Technology for Breast Lesion Detection using Supervised Machine Learning Model
Rana, S., Dey, M., Loretoni, R., Duranti, M., Ghavami, M., Dudley-Mcevoy, S. and Tiberi, G. (2023). Radiation-free Microwave Technology for Breast Lesion Detection using Supervised Machine Learning Model. Tomography. 9 (1), pp. 105-129. https://doi.org/10.3390/tomography9010010
High-resolution electrical measurement data processing
Dey, M. and Rana, S. (2022). High-resolution electrical measurement data processing. GB2599698
Detecting Power Grid Frequency Events from μPMU Voltage Phasor Data Using Machine Learning
Dey, M., Rana, S., Wylie, J., Simmons, C. V. and Dudley-Mcevoy, S. (2022). Detecting Power Grid Frequency Events from μPMU Voltage Phasor Data Using Machine Learning. The IET 11th International Conference on Renewable Power Generation. IET London: Savoy Place. 22 - 23 Sep 2022 Institute of Engineering and Technology (IET).
Automated breast lesion localisation in microwave imaging employing simplified pulse coupled neural network
Dey, M., Rana, S., Loretoni, R., Duranti, M., Sani, L., Vispa, A., Raspa, G., Ghavami, M., Dudley-Mcevoy, S. and Tiberi, G. (2022). Automated breast lesion localisation in microwave imaging employing simplified pulse coupled neural network. PLoS ONE. https://doi.org/10.1371/journal.pone.0271377
Markerless Gait Classification Employing 3D IR-UWB Physiological Motion Sensing
Rana, S., Dey, M., Ghavami, M. and Dudley-Mcevoy, S. (2022). Markerless Gait Classification Employing 3D IR-UWB Physiological Motion Sensing. IEEE Sensors Journal. 22 (7), pp. 6931-6941. https://doi.org/10.1109/JSEN.2022.3154092
Radial Basis Function for Breast Lesion Detection from MammoWave Clinical Data
Rana, S., Dey, M., Riccardo Loretoni, Michele Duranti, Lorenzo Sani, Alessandro Vispa, Ghavami, M., Sandra Dudley and Gianluigi Tiberi (2021). Radial Basis Function for Breast Lesion Detection from MammoWave Clinical Data. Diagnostics. 11 (10). https://doi.org/10.3390/diagnostics11101930
Solar farm voltage anomaly detection using high-resolution μ PMU data-driven unsupervised machine learning
Dey, M., Rana, S., Simmons, Clarke V. and Dudley-Mcevoy, S. (2021). Solar farm voltage anomaly detection using high-resolution μ PMU data-driven unsupervised machine learning. Applied Energy. 303, p. 117656. https://doi.org/10.1016/j.apenergy.2021.117656
Automated breast lesion localisation in microwave imaging employing simplified pulse coupled neural network
Dey, M., Rana, S., Loretoni, R., Duranti, M., Sani, L., Vispa, A., Raspa, G., Ghavami, M., Dudley-Mcevoy, S. and Tiberi, G. (2021). Automated breast lesion localisation in microwave imaging employing simplified pulse coupled neural network. London South Bank University. https://doi.org/10.18744/lsbu.8xz49
Automated terminal unit performance analysis employing x-RBF neural network and associated energy optimisation – A case study based approach
Dey, M., Rana, S. and Dudley-Mcevoy, S. (2021). Automated terminal unit performance analysis employing x-RBF neural network and associated energy optimisation – A case study based approach. Applied Energy. 298, p. 117103. https://doi.org/10.1016/j.apenergy.2021.117103
3D Gait Abnormality Detection Employing Contactless IR-UWB Sensing Phenomenon
Rana, S., Dey, M., Ghavami, M. and Dudley-McEvoy, S. (2021). 3D Gait Abnormality Detection Employing Contactless IR-UWB Sensing Phenomenon. IEEE Transactions on Instrumentation and Measurement. 70. https://doi.org/10.1109/TIM.2021.3069044
A Case Study Based Approach for Remote Fault Detection Using Multi-Level Machine Learning in A Smart Building
Dey, M, Rana, SP and Dudley, S (2020). A Case Study Based Approach for Remote Fault Detection Using Multi-Level Machine Learning in A Smart Building. Smart Cities. 3 (2), pp. 401-419. https://doi.org/10.3390/smartcities3020021
A robust FLIR target detection employing an auto-convergent pulse coupled neural network
Dey, M., Rana, S.P. and Siarry, P. (2019). A robust FLIR target detection employing an auto-convergent pulse coupled neural network. Remote Sensing Letters. 10 (7), pp. 639-648. https://doi.org/10.1080/2150704x.2019.1597296
Boosting content based image retrieval performance through integration of parametric & nonparametric approaches
Rana, S., Dey, M. and Siarry, P. (2019). Boosting content based image retrieval performance through integration of parametric & nonparametric approaches. Journal of Visual Communication and Image Representation. 58, pp. 25-219. https://doi.org/10.1016/j.jvcir.2018.11.015
Signature Inspired Home Environments Monitoring System Using IR-UWB Technology
Rana, S., Dey, M., Ghavami, M. and Dudley-Mcevoy, S. (2019). Signature Inspired Home Environments Monitoring System Using IR-UWB Technology. Sensors. 19 (2), p. 385. https://doi.org/10.3390/s19020385
Non-Contact Human Gait Identification through IR-UWB Edge Based Monitoring Sensor
Rana, S., Dey, M, Ghavami, M and Dudley-McEvoy, S (2019). Non-Contact Human Gait Identification through IR-UWB Edge Based Monitoring Sensor. IEEE Sensors Journal. https://doi.org/10.1109/JSEN.2019.2926238
Machine Learning Approaches for Automated Lesion Detection in Microwave Breast Imaging Clinical Data
Rana, S., Dey, M., Tiberi, G., Sani, L., Vispa, A., Raspa, G., Duranti, M., Ghavami, M. and Dudley-Mcevoy, S. (2019). Machine Learning Approaches for Automated Lesion Detection in Microwave Breast Imaging Clinical Data. Scientific Reports. 9, p. 10510. https://doi.org/10.1038/s41598-019-46974-3
ITERATOR: A 3D Gait Identification from IR-UWB Technology
Rana, S., Dey, M, Ghavami, M and Dudley, S (2019). ITERATOR: A 3D Gait Identification from IR-UWB Technology. International Conference of the IEEE Engineering in Medicine & Biology Society (EMBC) (EMBC 2019). Berlin, Germany 23 - 27 Jul 2019
Semi-supervised learning techniques for automated fault detection and diagnosis of HVAC systems
Dey, M., Rana, S. and Dudley, S. (2018). Semi-supervised learning techniques for automated fault detection and diagnosis of HVAC systems. IEEE International Conference on Tools with Artificial Intelligence (ICTAI-2018). Volos, Greece 05 - 07 Nov 2018 Institute of Electrical and Electronics Engineers (IEEE). https://doi.org/10.1109/ictai.2018.00136
Smart Building Creation in Large Scale HVAC Environments through Automated Fault Detection and Diagnosis
Dudley, S, Dey, M and Rana, S. (2018). Smart Building Creation in Large Scale HVAC Environments through Automated Fault Detection and Diagnosis. Future Generation Computer Systems. 108, pp. 950-966. https://doi.org/10.1016/j.future.2018.02.019
Remote Vital Sign Recognition Through Machine Learning Augmented UWB
Dudley, S, Rana, S., Dey, M, Brown, R and Siddiqui, H (2018). Remote Vital Sign Recognition Through Machine Learning Augmented UWB. European Conference on Antennas and Propagation. Excel London, Docklands 09 - 13 Apr 2018 London South Bank University. https://doi.org/10.1049/cp.2018.0978
A Self Regulating and Crowdsourced Indoor Positioning System through Wi-Fi Fingerprinting for Multi Storey Building
Rana, S., Dey, M and Dudley, S (2018). A Self Regulating and Crowdsourced Indoor Positioning System through Wi-Fi Fingerprinting for Multi Storey Building. Sensors. 18 (11), pp. 1-15. https://doi.org/10.3390/s18113766
Semi-Supervised Learning Techniques for Automated Fault Detection and Diagnosis of HVAC System
Dudley, S, Dey, M and Rana, S. (2018). Semi-Supervised Learning Techniques for Automated Fault Detection and Diagnosis of HVAC System. IEEE International Conference on Tools with Artificial Intelligence (ICTAI-2018). Volos, Greece 05 - 07 Nov 2018
A PID inspired feature extraction method for HVAC terminal units
Dey, M., Gupta, M., Rana, S., Turkey, M. and Dudley-Mcevoy, S. (2017). A PID inspired feature extraction method for HVAC terminal units. IEEE Conference on Technologies for Sustainability (SusTech 2017). Phoenix, Arizona, USA 12 - 14 Nov 2017 Institute of Electrical and Electronics Engineers (IEEE). https://doi.org/10.1109/sustech.2017.8333470
Unsupervised Learning Techniques for HVAC Terminal Unit Behaviour Analysis
Dey, M, Gupta, M, Turkey, M and Dudley, S (2017). Unsupervised Learning Techniques for HVAC Terminal Unit Behaviour Analysis. IEEE International Conference on Smart City Innovations. Fremont, California, USA 04 - 08 Aug 2017 Institute of Electrical and Electronics Engineers (IEEE). https://doi.org/10.1109/UIC-ATC.2017.8397584
UWB Localization Employing Supervised Learning Method
Rana, S., Dey, M., Siddiqui, H., Tiberi, G., Ghavami, M. and Dudley, S (2017). UWB Localization Employing Supervised Learning Method. IEEE International Conference on Ubiquitous Wireless Broadband 2017. Salamanca, Spain 12 - 15 Sep 2017 Institute of Electrical and Electronics Engineers (IEEE). https://doi.org/10.1109/ICUWB.2017.8250971
A PID Inspired Feature Extraction for HVAC Terminal Units
Dey, M, Gupta, M, Rana, S., Turkey, M and Dudley, S (2017). A PID Inspired Feature Extraction for HVAC Terminal Units. IEEE Conference on Technologies for Sustainability (SusTech 2017). Phoenix, Arizona, USA 12 - 14 Nov 2017 Institute of Electrical and Electronics Engineers (IEEE).