An ontological framework for AR-enhanced maintenance management

This paper presents an ontology design framework that integrates opportunistic maintenance (OM) strategies, Stackelberg game theory models, Nash equilibrium concepts, and augmented reality (AR) to enhance decision-making, information visualization and contextualization in industrial settings. Traditional OM approaches often lack real-time, context-aware decision support, efficient resource allocation, and multi-agent collaboration, essential for dynamic optimization strategies. Integrating Stackelberg game theory models into OM enhances resource allocation and scheduling through hierarchical decision-making, allowing a leader-follower to optimally distribute resources while providing data-rich visualization and supporting adaptive, strategic planning in maintenance management. In dynamic multi-agent environments with multiple stakeholders, achieving Nash equilibrium leads to stable and efficient resource allocation, as no participant can unilaterally improve their outcome without impacting others. By incorporating Stackelberg game dynamics, Nash equilibrium concepts, and AR, the conceptual framework facilitates structured strategic planning, balancing leadership-driven optimization with equilibrium-based stability in decision-making and visualization. Evaluation of this ontology is proposed through a case study in a laboratory setting. The proposed ontology serves as a knowledge base for improving decision-making and provides a replicable framework for future advancements in industrial maintenance management by enabling the integration of emerging technologies, such as foundation models and large language models (LLMs), to refine maintenance strategies.