A BIM-Integrated Eco-Digital Framework for Markov-Based Predictive Maintenance and Sustainability Assessment in Educational Buildings Towards Digital Twin Readiness

Document Type

Article

Publication Date

2026

Abstract

This study proposes a BIM-integrated Eco-Digital framework for enhancing predictive maintenance and sustainability assessment in educational buildings, supporting their tran- sition towards Digital Twin readiness. Existing facilities often rely on reactive maintenance practices, fragmented data systems, and limited integration of sustainability indicators, which hinder efficient lifecycle management and environmental performance. To address these challenges, the research develops a data-driven methodology that combines condition assessment (CA), Markov-based deterioration prediction (DP), and sustainability metrics within an interoperable BIM–facility management (FM) environment. The framework is validated through a real educational building case study, where a hierarchical asset structure and relative weighting system are established to prioritize maintenance actions based on both functional importance and condition state. The Markov model is employed to predict component deterioration under uncertainty, enabling proactive maintenance planning without reliance on real-time IoT data. Sustainability is incorporated through energy consumption analysis and lifecycle performance indicators, linking maintenance decisions to environmental impacts. Results demonstrate improved maintenance prioritization, enhanced predictive capability, and better integration of sustainability considerations within facility management workflows. The proposed framework mainly contributes to providing a practical, scalable approach for transforming conventional buildings into data-driven, sustainable assets, offering a viable pathway toward Digital Twin-enabled environments, particularly in contexts with limited digital infrastructure.

Link to Full Text

Share

COinS