Deep learning in fault detection and diagnosis of building HVAC systems: A systematic review with meta analysis

Zhang, Fan; Saeed, Nausheen; Sadeghian, Paria

doi:10.1016/j.egyai.2023.100235

Cited by 29 publications

(10 citation statements)

References 108 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…Generally, in the studies dealing with DL, researchers focused on user preferences and not on the number of people in the building, which could be empty, full, or partially occupied. Enhancing the use of energy in buildings has been extensively researched in the literature, particularly in managing HAVC systems by incorporating DL techniques, as clearly revised in the studies [24][25][26][27][28][29].…”

Section: Literature Reviewmentioning

confidence: 99%

Intelligent Power Management Models for Buildings: A Comparative Analysis

Talib,

Croock

2024

JESA

View full text Add to dashboard Cite

Power management in several sectors poses the problem of conserving the consumed power while satisfying the imposed conditions It is considered as a proactive control and management of the organization's energy consumption to save use and reduce energy expenses. Therefore, there is an actual need to include smart energy management systems in buildings in order to reduce the consumed energy. In this work, a comparative analysis is presented to evaluate deep and machine-learning approaches in the context of intelligent models for conserving power in smart buildings. The deep learning model is structured by using Deep Neural Networks (DNN), while machine learning models are represented by Random Forest (RF), Support Vector Machine (SVM), K-Nearest Neighbor (K-NN), and Naive Bayes (NB). These models adopt three classes: full (power in full consumption), select (power in partial consumption), and shout down (no power consumption). Moreover, feature reduction methods of Boruta and Principal Component Analysis (PCA) are implemented to reduce the complexity of the models. The proposed models are trained and tested using a measured dataset for a building. Comparison results of the proposed models showed that the Random Forest attracts more attention regarding classification accuracy by 100% and a reasonable classification time of 1.23 seconds. The effectiveness of the comparative analysis which indicating the highest accuracy results for RF makes it as a suitable model to be implemented as an optimal one in real-time power management systems.

show abstract

Section: Literature Reviewmentioning

confidence: 99%

Intelligent Power Management Models for Buildings: A Comparative Analysis

Talib,

Croock

2024

JESA

View full text Add to dashboard Cite

show abstract

“…The emergence of DL implementations in HVAC system research can be traced back to 2018, with the seminal paper by Guo et al [ 21 ] on using a deep belief network (DBN) for fault diagnosis in air-conditioning systems. This study laid the foundation for subsequent research in this field [ 22 ].…”

Section: Introductionmentioning

confidence: 99%

“…Hence, CNNs have been shown to be versatile in handling HVAC data, either in 1D or 2D form. Although both 1D and 2D representations are well described in the literature, 1D forms are generally preferred due to their simpler preprocessing requirements, unlike 2D CNNs, which usually require data conversion to images [ 22 ].…”

Section: Introductionmentioning

confidence: 99%

Improving the Efficiency of Fan Coil Units in Hotel Buildings through Deep-Learning-Based Fault Detection

Matetić

Štajduhar

Wolf

et al. 2023

Sensors

View full text Add to dashboard Cite

Optimizing the performance of heating, ventilation, and air-conditioning (HVAC) systems is critical in today’s energy-conscious world. Fan coil units (FCUs) play a critical role in providing comfort in various environments as an important component of HVAC systems. However, FCUs often experience failures that affect their efficiency and increase their energy consumption. In this context, deep learning (DL)-based fault detection offers a promising solution. By detecting faults early and preventing system failures, the efficiency of FCUs can be improved. This paper explores DL models as fault detectors for FCUs to enable smarter and more energy-efficient hotel buildings. We tested three contemporary DL modeling approaches: convolutional neural network (CNN), long short-term memory network (LSTM), and a combination of CNN and gated recurrent unit (GRU). The random forest model (RF) was additionally developed as a baseline benchmark. The fault detectors were tested on a real-world dataset obtained from the sensory measurement system installed in a hotel and additionally supplemented with simulated data via a physical model developed in TRNSYS. Three representative FCU faults, namely, a stuck valve, a reduction in airflow, and an FCU outage, were simulated with a much larger dataset than is typically utilized in similar studies. The results showed that the hybrid model, integrating CNN and GRU, performed best for all three observed faults. DL-based fault detectors outperformed the baseline RF model, confirming these solutions as viable components for energy-efficient hotels.

show abstract

“…Nevertheless, faults and anomalies can happen, resulting in both performance degradation and energy losses. Integrating Fault Detection and Diagnosis (FDD) methods in monitoring and maintenance processes of these systems can help identifying errors and flaws timely and efficiently and implementing energy conservation measures leading to significant energy savings [1]. FDD has been a large research field in the last decades and the first applications in the real estate and in the district heating industries have emerged together with the higher availability of measurement data and of web-based analytic services.…”

Section: Introductionmentioning

confidence: 99%

Transfer learning methodology for machine learning based fault detection and diagnostics applied to building services

Chavan,

Réhault,

Rist

2023

J. Phys.: Conf. Ser.

View full text Add to dashboard Cite

Machine Learning (ML) models for Fault Detection and Diagnosis (FDD) can automatically detect anomalies in the operation in large facilities or district heating networks and can help tackling energy wastes. Nevertheless, the development of ML-models is a costly and tedious task requiring large amounts of labelled data. Setting up ML-models for a high number of systems is effort and know-how intensive. However, assets like commercial buildings and district heating networks are constituted of systems with similar topologies. Transferring a ML model initially trained on a source system to a multitude of similar target systems, can help reducing the training costs and facilitating the scalability of ML-based FDD in those assets. To enable this, we have developed a methodology that assesses the potential for Transfer Learning (TL) from a source system to target systems by determining the covariate and concept shifts between the source and target domains and integrating the source model into the target system if the TL assessment is positive. We used a patented method for the model development, that combines two ML-models, that are initially trained on a source system by means of a feedback system. We implemented this methodology on district heating (DH) substations, as DH systems typically contain this kind of subsystems with similar topologies and have thus a high scalability potential for TL. Initial findings showed the effectiveness of TL in adapting the source model to the target domain, resulting in enhanced FDD capabilities with significantly reduced training efforts.

show abstract

Deep learning in fault detection and diagnosis of building HVAC systems: A systematic review with meta analysis

Cited by 29 publications

References 108 publications

Intelligent Power Management Models for Buildings: A Comparative Analysis

Intelligent Power Management Models for Buildings: A Comparative Analysis

Improving the Efficiency of Fan Coil Units in Hotel Buildings through Deep-Learning-Based Fault Detection

Transfer learning methodology for machine learning based fault detection and diagnostics applied to building services

Contact Info

Product

Resources

About