Hybrid Predictive Maintenance for Building Systems: Integrating Rule-Based and Machine Learning Models for Fault Detection Using a High-Resolution Danish Dataset

Buildings, Год журнала: 2025, Номер 15(4), С. 630 - 630

Опубликована: Фев. 18, 2025

This study evaluates the effectiveness of six machine learning models, Artificial Neural Networks (ANN), Random Forest (RF), Extreme Gradient Boosting (XGBoost), Support Vector Machine (SVM), K-Nearest Neighbors (KNN), and Logistic Regression (LR), for predictive maintenance in building systems. Utilizing a high-resolution dataset collected every five minutes from office rooms at Aalborg University Denmark over ten-month period (27 February 2023 to 31 December 2023), we defined rule-based conditions label historical faults HVAC, lighting, occupancy systems, resulting 100,000 fault instances. XGBoost outperformed other achieving an accuracy 95%, precision 93%, recall 94%, F1-score 0.93, with computation time 60 s. The model effectively predicted critical such as “Light_On_No_Occupancy” (1149 occurrences) “Damper_Open_No_Occupancy” (8818 occurrences), demonstrating its potential real-time detection energy optimization management Our findings suggest that implementing frameworks can significantly enhance accuracy, reduce waste, improve operational efficiency.

Язык: Английский

---

Guardians of Reliability, Robustness, and Resilience: Adversarial Maintenance in the Era of Industry 4.0 and 5.0

Procedia Computer Science, Год журнала: 2025, Номер 253, С. 13 - 24

Опубликована: Янв. 1, 2025

Язык: Английский

---

Artificial intelligence and robotics in the hydrogen lifecycle: A systematic review

International Journal of Hydrogen Energy, Год журнала: 2025, Номер 113, С. 801 - 817

Опубликована: Март 1, 2025

Язык: Английский

---

Predictive Maintenance Algorithms, Artificial Intelligence Digital Twin Technologies, and Internet of Robotic Things in Big Data-Driven Industry 4.0 Manufacturing Systems

Mathematics, Год журнала: 2025, Номер 13(6), С. 981 - 981

Опубликована: Март 17, 2025

In Industry 4.0, predictive maintenance (PdM) is key to optimising production processes. While its popularity among companies grows, most studies highlight theoretical benefits, with few providing empirical evidence on economic impact. This study aims fill this gap by quantifying the performance of manufacturing in Visegrad Group countries through PdM algorithms. The purpose our research assess whether these generate higher operational profits and lower sales costs. Using descriptive statistics, non-parametric tests, Hodges–Lehmann median difference estimate, linear regression, authors analysed data 1094 enterprises. Results show that significantly improves performance, variations based geographic scope. Regression analysis confirmed as an essential predictor even after considering factors like company size, legal structure, Enterprises more effective cost management net were likely adopt PdM, revealed decision tree analysis. Our findings provide benefits algorithms their potential enhance competitiveness, offering a valuable foundation for business managers make informed investment decisions encouraging further other industries.

Язык: Английский

---

Artificial intelligence and circular supply chains: framework for applications and deployment from the triple bottom line model perspective

Annals of Operations Research, Год журнала: 2025, Номер unknown

Опубликована: Март 17, 2025

Язык: Английский

---