Article
Thermodynamics
Fangliang Zhong, John Kaiser Calautit, Yupeng Wu
Summary: This study evaluates the performance differences of proposed convolutional and recurrent neural networks for fault detection and diagnosis (FDD) in limited seasonal fault data scenarios and an ideal scenario covering multiple climatic conditions. The results show that FDD architectures trained on sufficient fault data in a specific season have poor generalization ability to identify faults in unseen seasons. Additionally, the coverage of fault data in different seasons is more important for enhancing FDD performances than the amount of fault data in each season. These findings are crucial for researchers to consider when evaluating data-driven FDD methods.
Review
Energy & Fuels
Zhelun Chen, Zheng O'Neill, Jin Wen, Ojas Pradhan, Tao Yang, Xing Lu, Guanjing Lin, Shohei Miyata, Seungjae Lee, Chou Shen, Roberto Chiosa, Marco Savino Piscitelli, Alfonso Capozzoli, Franz Hengel, Alexander Kuehrer, Marco Pritoni, Wei Liu, John Clauss, Yimin Chen, Terry Herr
Summary: This paper reviews and summarizes the literature on data-driven fault detection and diagnostics (FDD) for building HVAC systems, focusing on the process, systems studied, and evaluation metrics. It identifies challenges such as real-building deployment, performance evaluation, scalability, interpretability, cyber security, data privacy, and user experience that data-driven FDD methods still face despite promising performance reported in the literature.
Review
Computer Science, Information Systems
Guannan Li, Yunpeng Hu, Jiangyan Liu, Xi Fang, Jing Kang
Summary: Faults in building energy systems require efficient fault detection and diagnosis to ensure smooth operation and performance. Feature engineering plays a key role in generating optimal model inputs for fault detection models. Challenges include data volume, diversity, quality, and performance evaluation of feature engineering algorithms and fault detection models. Future work should focus on designing a robust and automated feature engineering strategy considering the relationships between fault-related features and real-time impacts.
Article
Construction & Building Technology
Marco Pritoni, Guanjin Lin, Yimin Chen, Raphael Vitti, Christopher Weyandt, Jessica Granderson
Summary: This paper presents a field study on the implementation of fault auto-correction algorithms in commercial FDD platforms. Through testing in multiple buildings and different systems, it successfully achieves automatic fault correction and improves the operation of HVAC systems.
BUILDING AND ENVIRONMENT
(2022)
Review
Construction & Building Technology
Faeze Hodavand, Issa J. Ramaji, Naimeh Sadeghi
Summary: Intelligence in Industry 4.0 has led to the development of smart buildings with various control systems for data collection, optimization, and fault detection. Digital Twin (DT) technology offers a sustainable solution for facility management. This research comprehensively reviews DT performance evaluation in building life cycle and predictive maintenance. The study emphasizes the advantages of data-driven methods and highlights the importance of unsupervised and semi-supervised learning for building operations with HVAC systems. Future research should focus on developing interpretable models and exploring the potential of deep learning methods.
Review
Thermodynamics
Vijay Singh, Jyotirmay Mathur, Aviruch Bhatia
Summary: This review study focuses on the latest research and developments in fault detection and diagnostics (FDD) of Heating Ventilation and Air Conditioning (HVAC) systems. The basics of FDD and the methods developed for it are discussed, with emphasis on the use of machine learning techniques. The paper also covers fault prognosis, fault modeling, and provides a comparative study of different FDD methods. Future challenges and the importance of more efficient FDD systems in reducing energy consumption are also discussed.
INTERNATIONAL JOURNAL OF REFRIGERATION
(2022)
Article
Construction & Building Technology
Tingting Li, Yang Zhao, Chaobo Zhang, Jing Luo, Xuejun Zhang
Summary: Fault diagnosis plays a critical role in energy conservation of building HVAC systems. This paper proposes a knowledge-guided and data-driven fault diagnosis method that integrates the advantages of both knowledge-driven and data-driven methods, accurately interprets faults, and reveals fault mechanisms through local causal graphs.
BUILDING AND ENVIRONMENT
(2021)
Review
Energy & Fuels
William Nelson, Charles Culp
Summary: Energy consumption is a significant cost in building operations, and faults can lead to increased energy consumption and reduced thermal comfort. Recent advancements in automated fault detection and diagnostics, as well as machine learning algorithms, offer opportunities for more accurate results. However, there are still obstacles to overcome for widespread adoption in commercial and scientific domains.
Review
Energy & Fuels
Simon P. Melgaard, Kamilla H. Andersen, Anna Marszal-Pomianowska, Rasmus L. Jensen, Per K. Heiselberg
Summary: This review provides an overview of fault detection and diagnosis (FDD) in building systems, revealing that FDD for buildings is still in its early stages globally with inconsistent use of terminologies and definitions. A lack of data statements in reviewed articles could impact reproducibility and practical development in this field.
Article
Chemistry, Analytical
Wunna Tun, Kwok-Wai (Johnny) Wong, Sai-Ho Ling
Summary: This article presents a framework for HVAC fault detection using HVACSIM+ simulated data and GAF-2DCNN method. By converting time-series sensor data into informative 2D images and extracting features using 2DCNN, this method captures hidden temporal relationships in 1D signals. Experimental results demonstrate high accuracy and precision in HVAC fault detection using this method.
Article
Thermodynamics
Michael Wetter, Paul Ehrlich, Antoine Gautier, Milica Grahovac, Philip Haves, Jianjun Hu, Anand Prakash, Dave Robin, Kun Zhang
Summary: The current process of specifying, installing, and commissioning building control sequences is manual and lacks formal quality control, resulting in low performance sequences at scale. To address this, a digitized building control delivery workflow with formal verification and a Control Description Language was introduced to allow customization, testing, and improvement of sequences by mechanical designers. This process has led to a proposed standard, ASHRAE 231P, for digitizing the building control delivery process through a standardized format for exchanging control logic.
Article
Automation & Control Systems
Viet Tra, Manar Amayri, Nizar Bouguila
Summary: Incomplete data is a common problem in data-driven energy and building solutions. This paper proposes a new framework called DV-MPPCA to address the fault detection problem in buildings with incomplete data. The framework combines a variational autoencoder (VAE) for data compression and a mixture of principal component analyzers (MPPCA) for density estimation. Experimental results demonstrate the exceptional performance of DV-MPPCA, even with high missing rates.
IEEE TRANSACTIONS ON AUTOMATION SCIENCE AND ENGINEERING
(2023)
Article
Energy & Fuels
Paria Movahed, Saman Taheri, Ali Razban
Summary: Long-term operation of HVAC systems can lead to failures, higher energy consumption, and maintenance costs. Fault detection diagnostic (FDD) is commonly used to prevent malfunctions, and machine learning methods have gained interest due to their high accuracy. However, existing studies suffer from biased classification algorithms and high false positives. To address these challenges and improve diagnostic performance, this study proposes a novel data-driven framework using principal component analysis, time series anomaly detection, and random forest.
Article
Thermodynamics
Liang Zhang, Matt Leach
Summary: This study developed a novel analysis methodology that comprehensively evaluates the impact of sensor faults on sensor selection and FDD accuracy. Monte Carlo simulation is used to deal with multiple stochastic sensor inaccuracies and provide probabilistic analysis results. The methodology can be useful for sensor design and operation maintenance.
BUILDING SIMULATION
(2022)
Article
Construction & Building Technology
Shuangyu Wei, Paige Wenbin Tien, Yupeng Wu, John Kaiser Calautit
Summary: Occupants' behavior and electrical equipment usage have a significant impact on building energy demand. This study proposes a real-time detection and recognition approach using deep learning and computer vision techniques to efficiently control building energy. Experimental results demonstrate high accuracy in equipment and occupancy detection, and a case study shows the influence of the approach on building energy demand. The results highlight the importance of monitoring real-time occupancy and electrical equipment usage and the advantages of using deep learning detection techniques to optimize building energy efficiency.
JOURNAL OF BUILDING ENGINEERING
(2022)
Article
Construction & Building Technology
Samiran Khorat, Debashish Das, Rupali Khatun, Sk Mohammad Aziz, Prashant Anand, Ansar Khan, Mattheos Santamouris, Dev Niyogi
Summary: Cool roofs can effectively mitigate heatwave-induced excess heat and enhance thermal comfort in urban areas. Implementing cool roofs can significantly improve urban meteorology and thermal comfort, reducing energy flux and heat stress.
ENERGY AND BUILDINGS
(2024)
Article
Construction & Building Technology
Qi Li, Jiayu Chen, Xiaowei Luo
Summary: This study focuses on the vertical wind conditions as a main external factor that limits the energy assessment of high-rise buildings in urban areas. Traditional tools for energy assessment of buildings use a universal vertical wind profile estimation, without taking into account the unique wind speed in each direction induced by the various shapes and configurations of buildings in cities. To address this limitation, the study developed an omnidirectional urban vertical wind speed estimation method using direction-dependent building morphologies and machine learning algorithms.
ENERGY AND BUILDINGS
(2024)
Article
Construction & Building Technology
Xiaojun Luo, Lamine Mahdjoubi
Summary: This paper presents an integrated blockchain and machine learning-based energy management framework for multiple forms of energy allocation and transmission among multiple domestic buildings. Machine learning is used to predict energy generation and consumption patterns, and the proposed framework establishes optimal and automated energy allocation through peer-to-peer energy transactions. The approach contributes to the reduction of greenhouse gas emissions and enhances environmental sustainability.
ENERGY AND BUILDINGS
(2024)
Article
Construction & Building Technology
Ying Yu, Yuanwei Xiao, Jinshuai Chou, Xingyu Wang, Liu Yang
Summary: This study proposes a dual-layer optimization design method to maximize the energy sharing potential, enhance collaborative benefits, and reduce the storage capacity of building clusters. Case studies show that the proposed design significantly improves the performance of building clusters, reduces energy storage capacity, and shortens the payback period.
ENERGY AND BUILDINGS
(2024)
Article
Construction & Building Technology
Felix Langner, Weimin Wang, Moritz Frahm, Veit Hagenmeyer
Summary: This paper compares two main approaches to consider uncertainties in model predictive control (MPC) for buildings: robust and stochastic MPC. The results show that compared to a deterministic MPC, the robust MPC increases the electricity cost while providing complete temperature constraint satisfaction, while the stochastic MPC slightly increases the electricity cost but fulfills the thermal comfort requirements.
ENERGY AND BUILDINGS
(2024)
Article
Construction & Building Technology
Somil Yadav, Caroline Hachem-Vermette
Summary: This study proposes a mathematical model to evaluate the performance of a Double Skin Facade (DSF) system and its impact on indoor conditions. The model considers various design parameters and analyzes their effects on the system's electrical output and room temperature.
ENERGY AND BUILDINGS
(2024)
Article
Construction & Building Technology
Ruijun Chen, Holly Samuelson, Yukai Zou, Xianghan Zheng, Yifan Cao
Summary: This research introduces an innovative resilient design framework that optimizes building performance by considering a holistic life cycle perspective and accounting for climate projection uncertainties. The study finds that future climate scenarios significantly impact building life cycle performance, with wall U-value, windows U-value, and wall density being major factors. By using ensemble learning and optimization algorithms, predictions for carbon emissions, cost, and indoor discomfort hours can be made, and the best resilient design scheme can be selected. Applying this framework leads to significant improvements in building life cycle performance.
ENERGY AND BUILDINGS
(2024)