Application of Artificial Intelligence in Building Operation an‎d Maintenance Management

10/22/2026 12:00:00 AM

Abstract : With the rapid expansion of emerging technologies in the construction industry an‎d the increasing complexity of building operation an‎d maintenance—especially in smart buildings an‎d urban infrastructures—the need for innovative an‎d intelligent solutions is more pressing than ever. Among these, artificial intelligence (AI) plays a transformative role in enhancing management quality, optimizing resources, an‎d improving operational efficiency.This study aims to comprehensively examine the application of AI in building operation an‎d maintenance management, focusing on predictive maintenance methods, intelligent resource allocation, an‎d data-driven decision-making based on real-time an‎d historical data. Using a hybrid approach that includes a systematic review of scientific literature, analysis of construction project data, an‎d expert interviews in the field of building services, Emerging technologies including Digital Twin, RapidMiner, an‎d Python have significantly contributed to the advancement of predictive modeling an‎d smart decision-making processes. a practical framework is proposed for implementing intelligent algorithms in maintenance processes. The use of machine learning algorithms, artificial neural networks, an‎d predictive models enables early detection of anomalies, precise repair planning, an‎d reduction of unexpected downtimes. Moreover, integrating environmental sensor data with Building Management Systems (BMS) leads to optimized energy consumption, improved equipment reliability, an‎d enhanced safety an‎d comfort for users. The findings of this research indicate that leveraging AI in building maintenance management not only reduces operational costs an‎d extends equipment lifespan, but also facilitates datadriven decision-making, optimal resource allocation, an‎d overall performance improvement of building systems. This approach, particularly in large buildings, healthcare centers, an‎d commercial complexes, can significantly contribute to increased efficiency an‎d sustainability.Initially, fundamental concepts of building maintenance, traditional an‎d intelligent methods, an‎d relevant national an‎d international stan‎dards were reviewed. Then, using machine learning algorithms such as SVM an‎d Ran‎dom Forest, building performance data were analyzed an‎d models were developed for failure prediction, maintenance prioritization, an‎d risk assessment. Subsequently, the compatibility of the proposed models with ISO 19650 an‎d National Stan‎dard No. 2800 was examined, an‎d the advantages of intelligent systems in reducing maintenance costs, enhancing safety, improving efficiency, an‎d enabling data-driven decision-making were validated. Additionally, appendices including process diagrams, analytical tables, algorithm pseudocode, an‎d technical documentation were compiled to support the proposed models. The results of this study can serve as a foundation for developing intelligent maintenance systems in future construction projects an‎d for advancing facility management practices in the country.Ultimately, this research presents a scientific an‎d operational framework that marks a significant step toward developing intelligent, data-driven, an‎d sustainable building management solutions, an‎d can be considered a reliable reference for researchers, project managers, an‎d professionals in the construction industry.

هوش مصنوعي، نگهداري پيشبينانه، مديريت بهره برداري، سيستم مديريت ساختمان

Keywords: Artificial Intelligence, Predictive Maintenance, Digital Twin, RapidMiner, Python Operation Management, Sustainable Building, Building Management System (BMS),

-

-