An Effective Fault Detection Method for HVAC Systems Using the LSTM-SVDD Algorithm

Hui, Zhu; Yang, Wen Gang; Li, Shihong; Pang, Aiping

doi:10.3390/buildings12020246

Cited by 12 publications

(6 citation statements)

References 27 publications

(37 reference statements)

Supporting

Mentioning

Contrasting

Order By: Relevance

“…The use of virtual/soft sensors [ 80 , 81 , 92 ] and residual analysis [ 87 , 88 , 93 , 101 , 103 , 105 ] are also techniques worth mentioning in the context of the hybrid approach. All examples from the selected literature dealing with the hybrid approach are listed in Table 7 .…”

Section: Results Part I: Review and New Classification Of Fdd Approac...mentioning

confidence: 99%

“…Additionally, a variant of the artificial recurrent neural network called LSTM was proposed and it performed the best in prediction performance in comparison to the XGBoost method when the time-series data fluctuated greatly. Next, a framework was developed by Zhu et al [ 103 ] that provides guidelines for implementing predictive maintenance of building installations. When the data are collected, LSTM network is used to predict faults.…”

Section: Results Part Ii: State-of-the-art Techniques Used In Hvac Fd...mentioning

confidence: 99%

See 1 more Smart Citation

A Review of Data-Driven Approaches and Techniques for Fault Detection and Diagnosis in HVAC Systems

Matetić

Štajduhar

Wolf

et al. 2022

Sensors

View full text Add to dashboard Cite

Heating, ventilation, and air conditioning (HVAC) systems are a popular research topic because buildings’ energy is mostly used for heating and/or cooling. These systems heavily rely on sensory measurements and typically make an integral part of the smart building concept. As such, they require the implementation of fault detection and diagnosis (FDD) methodologies, which should assist users in maintaining comfort while consuming minimal energy. Despite the fact that FDD approaches are a well-researched subject, not just for improving the operation of HVAC systems but also for a wider range of systems in industrial processes, there is a lack of application in commercial buildings due to their complexity and low transferability. The aim of this review paper is to present and systematize cutting-edge FDD methodologies, encompassing approaches and special techniques that can be applied in HVAC systems, as well as to provide best-practice heuristics for researchers and solution developers in this domain. While the literature analysis targets the FDD perspective, the main focus is put on the data-driven approach, which covers commonly used models and data pre-processing techniques in the field. Data-driven techniques and FDD solutions based on them, which are most commonly used in recent HVAC research, form the backbone of our study, while alternative FDD approaches are also presented and classified to properly contextualize and round out the review.

show abstract

Section: Results Part I: Review and New Classification Of Fdd Approac...mentioning

confidence: 99%

Section: Results Part Ii: State-of-the-art Techniques Used In Hvac Fd...mentioning

confidence: 99%

A Review of Data-Driven Approaches and Techniques for Fault Detection and Diagnosis in HVAC Systems

Matetić

Štajduhar

Wolf

et al. 2022

Sensors

View full text Add to dashboard Cite

show abstract

“…Choi and Yoon [183] proposed an autoencoder-based FDD for BASs. The autoencoder (AE)-based model is used for the fault detection phase, and two types of informationgenerated structures were developed for the fault diagnosis process: recurrent error model (REM) and latent space model (LSM).…”

Section: Unsupervised Methodsmentioning

confidence: 99%

Digital Twin for Fault Detection and Diagnosis of Building Operations: A Systematic Review

Hodavand,

Ramaji,

Sadeghi

2023

Buildings

View full text Add to dashboard Cite

Intelligence in Industry 4.0 has led to the development of smart buildings with various control systems for data collection, efficient optimization, and fault detection and diagnosis (FDD). However, buildings, especially with regard to heating, ventilation, and air conditioning (HVAC) systems, are responsible for significant global energy consumption. Digital Twin (DT) technology offers a sustainable solution for facility management. This study comprehensively reviews DT performance evaluation in building life cycle and predictive maintenance. 200 relevant papers were selected using a systematic methodology from Scopus, Web of Science, and Google Scholar, and various FDD methods were reviewed to identify their advantages and limitations. In conclusion, data-driven methods are gaining popularity due to their ability to handle large amounts of data and improve accuracy, flexibility, and adaptability. Unsupervised and semi-supervised learning as data-driven methods are important for FDD in building operations, such as with HVAC systems, as they can handle unlabeled data and identify complex patterns and anomalies. Future studies should focus on developing interpretable models to understand how the models made their predictions. Hybrid methods that combine different approaches show promise as reliable methods for further research. Additionally, deep learning methods can analyze large and complex datasets, indicating a promising area for further investigation.

show abstract

“…Kim et al proposed two control algorithms considering temperature and humidity as the factors of the indoor environment to maintain the occupant comfort while lowering the energy consumption in conventional HVAC systems [15]. Other studies are based on the optimization and control of HVAC systems following different modeling techniques and methods [16][17][18][19]. Unfortunately, these methods require accurate models with a high level of computation, and they are difficult to implement in real control systems.…”

Section: Introductionmentioning

confidence: 99%

New Optimal Supply Air Temperature and Minimum Zone Air Flow Resetting Strategies for VAV Systems

et al. 2022

View full text Add to dashboard Cite

Buildings account for a large portion of the total energy use in the US; therefore, improving the operation of typical variable-air-volume (VAV) systems in buildings can provide a tremendous economic opportunity. ASHRAE Guideline 36 recommends a resetting strategy for supply air temperature (SAT) for VAV systems based on outside air temperature. However, this strategy may not produce optimal performance, particularly when simultaneous cooling and heating occurs in zones. In addition, there is no strategy recommended in the Guideline to reset the zone minimum airflow set point in a single-duct VAV terminal unit with reheat, although this setpoint has a great impact on zone reheat requirements and ventilation efficiency. Thus, this paper introduces new strategies to reset both the SAT and zone minimum airflow rate set points to improve the efficiency of typical VAV systems. The strategies were tested under various conditions through experiments performed in fully instrumented VAV systems located in the HVAC lab at the University of Cincinnati. The experiments were conducted on a chilled-water VAV system that serves three controlled zones with hot-water reheat VAV boxes controlled by a typical commercial BACnet web-based building automation system BAS. The simulation studies were performed using the building energy simulation software EnergyPlus to evaluate the strategies at a larger scale in various locations. The simulation results show that the proposed resetting strategies can provide fan energy savings between 1.6% and 5.7% and heating load savings between 7.7% to 33.7%, depending on the location. The laboratory testing shows that the proposed strategies can provide stable control performance in actual systems as well as achieving the anticipated reheat and fan energy savings. The result offers significant improvements that can be implemented in the Guideline for single-duct VAV system operation and control.

show abstract

An Effective Fault Detection Method for HVAC Systems Using the LSTM-SVDD Algorithm

Cited by 12 publications

References 27 publications

A Review of Data-Driven Approaches and Techniques for Fault Detection and Diagnosis in HVAC Systems

A Review of Data-Driven Approaches and Techniques for Fault Detection and Diagnosis in HVAC Systems

Digital Twin for Fault Detection and Diagnosis of Building Operations: A Systematic Review

New Optimal Supply Air Temperature and Minimum Zone Air Flow Resetting Strategies for VAV Systems

Contact Info

Product

Resources

About