An Intelligent Fault Detection Framework for HVAC Systems with Alert Generation
Abstract
The HVACs used in commercial buildings are one of the major electricity consumers. They undergo periodic inspections to prevent discomfort and potential hazards to the occupants. The existing technologies for fault detection are either based on personnel expertise or condition monitoring. Prediction of possible faults in the system gives time to take proper measures to act upon those faults and reduce the risk of system breakdown. Machine Learning (ML) models are able to analyze and predict a vast dataset in a short time, which makes them dependable assistance for diagnosing faults in HVAC systems. Thus, there is a need to develop a reliable and robust system that could predict working conditions and provide necessary alerts about faults on time. This study proposes a predictive health maintenance system that predicts upcoming faults and generates alert messages with their root cause analysis. The Automated ML (AutoML) detected different faults with the highest accuracy of 98.32% by choosing the random forest as the classifier. The root cause analysis provided with the alert messages saves time and resources for rectifying the faults and taking preventive measures. Hence, fault diagnosis using ML algorithms can help increase the HVAC’s lifespan and effectiveness.
References
[1]
Chakraborty D and Elzarka H Early detection of faults in HVAC systems using an XGBoost model with a dynamic threshold Energy and Buildings 2019 185 326-344
[2]
Chauhan K, Jani S, Thakkar D, Dave R, Bhatia J, Tanwar S, Obaidat MS. Automated machine learning: the new wave of machine learning. In: 2020 2nd International Conference on Innovative Mechanisms for Industry Applications (ICIMIA), 2020; p. 205–12.
[3]
Chen C, Liu Y, Sun X, di Cairano-Gilfedder C, and Titmus S An integrated deep learning-based approach for automobile mainte nance prediction with GIS data Reliabil Eng Syst Saf 2021 216
[4]
Chen C, Zhu ZH, Shi J, Lu N, and Jiang B Dynamic predictive maintenance scheduling using deep learning ensemble for system health prognostics IEEE Sens J 2021 21 23 26878-26891
[5]
Gálvez A, Diez-Olivan A, Seneviratne D, and Galar D Fault detection and RUL estimation for railway HVAC systems using a hybrid model-based approach Sustainability 2021 13 12 6828
[6]
Han X, Wang Z, Xie M, He Y, Li Y, and Wang W Remaining useful life prediction and predictive maintenance strategies for multi-state manufacturing systems considering functional dependence Reliabil Eng Syst Saf 2021 210
[7]
Hesabi H, Nourelfath M, and Hajji A Predictive maintenance enabled by machine learning: Use cases and challenges in the automotive industry Reliabil Eng Syst Saf 2022 219
[8]
Hu J and Chen P Predictive maintenance of systems subject to hard failure based on proportional hazards model Reliabil Eng Syst Saf 2020 196
[9]
Li T, Zhao Y, Zhang C, Luo J, and Zhang X A knowledge-guided and data-driven method for building HVAC systems fault diagnosis Build Environ 2021 198
[10]
Li T, Zhao Y, Zhang C, Zhou K, and Zhang X A semantic model-based fault detection approach for building energy systems Build Environ 2022 207
[11]
Meng H, Liu X, Xing J, and Zio E A method for economic evaluation of predictive maintenance technologies by integrating system dynamics and evolutionary game modelling Reliabil Eng Syst Saf 2022 222
[12]
Ram SK, Sahoo SR, Das BB, Mahapatra K, and Mohanty SP Eternal-thing: a secure aging-aware solar energy harvester thing for sustainable IoT IEEE Trans Sustain Comput 2021 6 2 320-333
[13]
de Saporta B and Zhang Z Predictive maintenance for the heated hold-up tank Reliabil Eng Syst Saf 2013 115
[14]
Shohet R, Kandil MS, McArthur J. Machine learning algorithms for classification of boiler faults using a simulated dataset. In: IOP Conference Series: Materials Science and Engineering, vol. 609, 2019; IOP Publishing, p. 062007.
[15]
Shohet R, Kandil M, and McArthur J Simulated Boiler Fault Data IEEE Dataport 2019
[16]
Shohet R, Kandil MS, Wang Y, and McArthur J Fault detection for non-condensing boilers using simulated building automation system sensor data Adv Eng Inform 2020 46
[17]
Taheri S, Ahmadi A, Mohammadi-Ivatloo B, and Asadi S Fault detection diagnostic for HVAC systems via deep learning algorithms Energy Build 2021 250
[18]
Theissler A, Pérez-Velázquez J, Kettelgerdes M, and Elger G Predictive maintenance enabled by machine learning: use cases and challenges in the automotive industry Reliabil Eng Syst Saf 2021 215
[19]
Traore M, Chammas A, and Duviella E Supervision and prognosis architecture based on dynamical classification method for the predictive maintenance of dynamical evolving systems Reliabil Eng Syst Saf 2015 136 120-131
[20]
Tun W, Wong JKW, and Ling SH Hybrid random forest and support vector machine modeling for HVAC fault detection and diagnosis Sensors 2021 21 24 8163
[21]
Vuthaluru HB, Kotadiya N, Vuthaluru R, and French D CFD based identification of clinker formation regions in large scale utility boiler Appl Therm Eng 2011 31 8 1368-1380
[22]
Wong SC, Gatt A, Stamatescu V, McDonnell MD. Understanding data augmentation for classification: When to Warp? In: 2016 International Conference on Digital Image Computing: Techniques and Applications (DICTA), 2016; p. 1–6.
[23]
Yan K, Huang J, Shen W, and Ji Z Unsupervised learning for fault detection and diagnosis of air handling units Energy Build 2020 210
[24]
Yüce F, Hiller M. Condition monitoring of power electronic systems through data analysis of measurement signals and control output variables. IEEE J Emerg Select Topics Power Electron. 2021;10(5): 5118–5131.
Index Terms
- An Intelligent Fault Detection Framework for HVAC Systems with Alert Generation
Index terms have been assigned to the content through auto-classification.
Recommendations
On undetectable faults and fault diagnosis
The presence of an undetectable fault ui may modify the response of a detectable fault dj to a test set used for fault diagnosis. This may impact the accuracy of fault diagnosis based on the responses of single faults. Many state-of-the-art diagnosis ...
Graceful Degradation in Algorithm-Based Fault Tolerant Multiprocessor Systems
Algorithm-based fault tolerance (ABFT) is a technique which improves the reliability of a multiprocessor system by providing concurrent error detection and fault location capability to it. It encodes data at the system level and modifies the algorithm ...
A Recovery-Oriented Approach for Software Fault Diagnosis in Complex Critical Systems
This paper proposes an approach to software faults diagnosis in complex fault tolerant systems, encompassing the phases of error detection, fault location, and system recovery. Errors are detected in the first phase, exploiting the operating system ...
Comments
Information & Contributors
Information
Published In
© The Author(s), under exclusive licence to Springer Nature Singapore Pte Ltd 2023. Springer Nature or its licensor (e.g. a society or other partner) holds exclusive rights to this article under a publishing agreement with the author(s) or other rightsholder(s); author self-archiving of the accepted manuscript version of this article is solely governed by the terms of such publishing agreement and applicable law.
Publisher
Springer-Verlag
Berlin, Heidelberg
Publication History
Published: 12 August 2023
Accepted: 30 June 2023
Received: 19 October 2022
Author Tags
Qualifiers
- Research-article
Contributors
Other Metrics
Bibliometrics & Citations
Bibliometrics
Article Metrics
- 0Total Citations
- 0Total Downloads
- Downloads (Last 12 months)0
- Downloads (Last 6 weeks)0
Reflects downloads up to 11 Feb 2025