A review of data-driven fault detection and diagnostics for building HVAC systems

Applied Energy, Journal Year: 2023, Volume and Issue: 339, P. 121030 - 121030

Published: March 27, 2023

Language: Английский

---

AI in HVAC fault detection and diagnosis: A systematic review

Energy Reviews, Journal Year: 2024, Volume and Issue: 3(2), P. 100071 - 100071

Published: Feb. 9, 2024

Recent studies show that artificial intelligence (AI), such as machine learning and deep learning, models can be adopted have advantages in fault detection diagnosis for building energy systems. This paper aims to conduct a comprehensive systematic literature review on (FDD) methods heating, ventilation, air conditioning (HVAC) covers the period from 2013 2023 identify analyze existing research this field. Our work concentrates explicitly synthesizing AI-based FDD techniques, particularly summarizing these offering classification. First, we discuss challenges while developing HVAC Next, classify into three categories: those based traditional hybrid AI models. Additionally, also examine physical model-based compare them with methods. The analysis concludes FDD, despite its higher accuracy reduced reliance expert knowledge, has garnered considerable interest compared physics-based However, it still encounters difficulties dynamic time-varying environments achieving resolution. Addressing is essential facilitate widespread adoption of HVAC.

Language: Английский

---

Comparative study on deep transfer learning strategies for cross-system and cross-operation-condition building energy systems fault diagnosis

Energy, Journal Year: 2022, Volume and Issue: 263, P. 125943 - 125943

Published: Nov. 3, 2022

Language: Английский

---

Digital Twin of HVAC system (HVACDT) for multiobjective optimization of energy consumption and thermal comfort based on BIM framework with ANN-MOGA

Advances in Building Energy Research, Journal Year: 2022, Volume and Issue: 17(2), P. 125 - 171

Published: Oct. 26, 2022

This study proposes a novel Digital Twin framework of heating, ventilation, and air conditioning (HVACDT) system to reduce energy consumption while increasing thermal comfort. The is developed help the facility managers better understand building operation enhance HVAC function. based on Building Information Modelling (BIM) combined with newly created plug-in receive real-time sensor data as well comfort optimization process through Matlab programming. In order determine if suggested practical, were collected from Norwegian office between August 2019 October 2021 used test framework. An artificial neural network (ANN) in Simulink model multiobjective genetic algorithm (MOGA) are then improve system. comprised distributors, cooling units, heating pressure regulators, valves, gates, fans, among other components. this context, several characteristics, such temperatures, pressure, airflow, control, factors considered decision variables. objective functions, predicted percentage dissatisfied (PPD) usage both calculated. As result, ANN's variables function correlated well. Furthermore, MOGA presents different design that can be obtain best possible solution terms usage. results show average savings for four days summer roughly 13.2%, 10.8% three months (June, July, August), keeping PPD under 10%. Finally, compared traditional approaches, HVACDT displays higher level automation management.

Language: Английский

---

Generative pre-trained transformers (GPT)-based automated data mining for building energy management: Advantages, limitations and the future

Energy and Built Environment, Journal Year: 2023, Volume and Issue: 5(1), P. 143 - 169

Published: June 16, 2023

Advanced data mining methods have shown a promising capacity in building energy management. However, the past decade, such are rarely applied practice, since they highly rely on users to customize solutions according characteristics of target systems. Hence, major barrier is that practical applications remain laborious. It necessary enable computers human-like ability solve tasks. Generative pre-trained transformers (GPT) might be capable addressing this issue, as some GPT models GPT-3.5 and GPT-4 powerful abilities interaction with humans, code generation, inference common sense domain knowledge. This study explores potential most advanced model (GPT-4) three scenarios management, i.e., load prediction, fault diagnosis, anomaly detection. A performance evaluation framework proposed verify capabilities generating prediction codes, diagnosing device faults, detecting abnormal system operation patterns. demonstrated can automatically tasks domain, which overcomes domain. In exploration GPT-4, its advantages limitations also discussed comprehensively for revealing future research directions

Language: Английский

---

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

Buildings, Journal Year: 2023, Volume and Issue: 13(6), P. 1426 - 1426

Published: May 31, 2023

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

Language: Английский

---

In-situ sensor calibration for building HVAC systems with limited information using general regression improved Bayesian inference

Building and Environment, Journal Year: 2023, Volume and Issue: 234, P. 110161 - 110161

Published: March 5, 2023

Language: Английский

---

Adaptive fault diagnosis of machining processes enabled by hybrid deep learning and incremental transfer learning

Computers in Industry, Journal Year: 2025, Volume and Issue: 167, P. 104262 - 104262

Published: Feb. 14, 2025

Language: Английский

---

A hierarchical object oriented Bayesian network-based fault diagnosis method for building energy systems

Applied Energy, Journal Year: 2021, Volume and Issue: 306, P. 118088 - 118088

Published: Nov. 3, 2021

Language: Английский

---

Enhancing Interpretability of Data-Driven Fault Detection and Diagnosis Methodology with Maintainability Rules in Smart Building Management

Journal of Sensors, Journal Year: 2022, Volume and Issue: 2022, P. 1 - 48

Published: Jan. 4, 2022

Data-driven fault detection and diagnosis (FDD) methods, referring to the newer generation of artificial intelligence (AI) empowered classification such as data science analysis, big data, Internet things (IoT), industry 4.0, etc., become increasingly important for facility management in smart building design city construction. While data-driven FDD methods nowadays outperform majority traditional approaches, physically based models mathematically models, terms both efficiency accuracy, interpretability those does not grow significantly. Instead, according literature survey, becomes main concern creates barriers be adopted real-world industrial applications. In this study, we reviewed existing approaches mechanical & electrical engineering (M&E) services faults discussed modern methods. Two strategies integrating expert reasoning were proposed. Lists rules, knowledge maintainability, international/local standards concluded various M&E services, including heating, ventilation air-conditioning (HVAC), plumbing, fire safety, elevator systems on surveys 110 buildings Singapore. The surveyed results significantly enhance potentially performance accuracy promote practices.

Language: Английский

---