BIM-based automated fault detection and diagnostics of HVAC systems in commercial buildings

Journal of Building Engineering, Journal Year: 2024, Volume and Issue: 87, P. 109022 - 109022

Published: March 8, 2024

In order to meet the growing demand for effective Automated Fault Detection and Diagnostics (AFDD) HVAC systems, innovative approaches are needed address limitations in data diversity access contextual information. This study introduces a methodology that leverages Building Information Modeling (BIM) enhance development of AFDD model. Feature engineering techniques utilized generate dynamic BIM features, compensating lack sensory Management Systems (BMS). By integrating analytics with BIM, comprehensive digital twin facility is created, which enables managers compare, reuse, develop models systems. The proposed demonstrates potential leveraging BIM-based knowledge overcome challenges associated limited sensor information availability by utilizing feature generation and, conversely, updating model analytics.

Language: Английский

---

Explainable AI: Bridging the Gap between Machine Learning Models and Human Understanding

Journal of Informatics Education and Research, Journal Year: 2024, Volume and Issue: unknown

Published: Jan. 1, 2024

Explainable AI (XAI) is one of the key game-changing features in machine learning models, which contribute to making them more transparent, regulated and usable different applications. In (the) investigation this paper, we consider four rows explanation methods—LIME, SHAP, Anchor, Decision Tree-based Explanation—in disentangling decision-making process black box models within fields. our experiments, use datasets that cover domains, for example, health, finance image classification, compare accuracy, fidelity, coverage, precision human satisfaction each method. Our work shows rule trees approach called (Decision explanation) mostly superior comparison other non-model-specific methods performing higher coverage regardless classifier. addition this, respondents who answered qualitative evaluation indicated they were very content with decision tree-based explanations these types are easy understandable. Furthermore, most famous sorts clarifications instinctive significant. The over discoveries stretch on utilize interpretable strategies facilitating hole between understanding thus advancing straightforwardness responsibility AI-driven decision-making.

Language: Английский

---

A Digital Twin Framework to Improve Urban Sustainability and Resiliency: The Case Study of Venice

Land, Journal Year: 2025, Volume and Issue: 14(1), P. 83 - 83

Published: Jan. 3, 2025

The digital transition is one of the biggest challenges new millennium. One key drivers this need to adapt rapidly changing and heterogeneous technological landscape that continuously evolving. Digital Twin (DT) technology can promote at an urban scale due its ability monitor, control, predict behaviour complex systems processes. As several scientific studies have shown, DTs be developed for infrastructure city management, facing global changes. are based on sensor-distributed networks support management propose intervention strategies future forecasts. In present work, a three-axial operative framework proposed developing DT system using Venice as case study. three axes were chosen sustainable development: energy, mobility, resiliency. fragile cultural heritage, which needs specific protection strategies. methodology starts from analysis state-of-the-arts technologies definition features. Three different proposed, aggregating features in list fields each axis. open-source database then analysed consider data already available city. Finally, services results show improve by adopting DT.

Language: Английский

---

Informing building retrofits at low computational costs: a multi-objective optimisation using machine learning surrogates of building performance simulation models

Journal of Building Performance Simulation, Journal Year: 2024, Volume and Issue: unknown, P. 1 - 17

Published: July 30, 2024

Machine learning (ML) algorithms are increasingly used as surrogates for building performance simulation (BPS) models to leverage their energy predictive capabilities while reducing computational costs. In parallel, researchers developing optimisation methods inform design and retrofit strategies but rarely employ ML-based BPS this purpose. This study proposes a coupled modelling approach that leverages the of surrogate multi-objective holistic operation retrofits at low The proposed methodology is demonstrated using an archetypal office in Ottawa, Canada. developed achieved competitive accuracies (adjusted R2: 0.90–0.99), identifying total peak saving measures with up 34% improvement occupant thermal comfort speeds 1266 times faster than traditional BPS-based approach. Results offer promising workflow applications requiring extensive computations scenario analyses, such net-zero retrofits.

Language: Английский

---

Explainable artificial intelligence for energy systems maintenance: A review on concepts, current techniques, challenges, and prospects

Renewable and Sustainable Energy Reviews, Journal Year: 2025, Volume and Issue: 216, P. 115668 - 115668

Published: April 8, 2025

Language: Английский

---

AI and Machine Learning in the Energy Sector

Advances in computational intelligence and robotics book series, Journal Year: 2025, Volume and Issue: unknown, P. 1 - 26

Published: Feb. 7, 2025

This chapter explores the innovative applications of Artificial Intelligence (AI) and Machine Learning (ML) in energy sector. With increasing demand for efficient management transition towards renewable sources, AI ML technologies offer promising solutions to address various challenges industry. The will delve into utilization data science, smart grids, forecasting methodologies, sophisticated control mechanisms optimize generation, consumption, distribution. Furthermore, it examine interplay between AI, ML, energy, society, highlighting potential these drive sustainability mitigate environmental impacts. Case studies practical examples illustrate successful implementation energy-focused research development systems.

Language: Английский

---

Enhancing energy efficiency in supermarkets: A data-driven approach for fault detection and diagnosis in CO2 refrigeration systems

Applied Energy, Journal Year: 2024, Volume and Issue: 377, P. 124479 - 124479

Published: Sept. 26, 2024

Language: Английский

---