Cross-equipment performance comparison also improved due to standardized data structures across heterogeneous fleets. Prior to implementation, differences in controller architectures limited direct comparability. The unified data model enabled consistent benchmarking under equivalent analytical criteria. Finally, the AI-assisted query interface demonstrated consistent retrieval accuracy for structured operational questions related to drilling duration, energy metrics, and equipment performance. This functionality reduced reliance on specialized data analysts and expanded access to operational intelligence across supervisory roles. Collectively, these results indicate that the proposed architecture enhances data continuity, analytical depth, and operational responsiveness. Beyond local process optimization, these improvements contribute to more predictable drilling performance and energy-aware decisionmaking within the broader mining value chain. 7. DISCUSSION: IMPLICATIONS FOR RESPONSIBLE MINING The digital transformation of production drilling extends beyond localized process optimization and represents a structural enabler for more responsible and predictable mineral supply. In the context of accelerating global demand for strategic minerals, reducing operational variability in early stages of the mining value chain has systemic implications for energy consumption, production stability, and resource efficiency. Drilling directly influences downstream fragmentation, which in turn affects comminution energy demand—one of the most energy-intensive stages in mining operations. By enabling realtime calculation and visualization of energy-related indicators such as specific energy per drilled meter, the proposed architecture supports more energy-aware operational decisions. Although the architecture does not directly reduce energy consumption, it provides the analytical foundation required to identify deviations, understand rock–tool interaction dynamics, and adjust operational parameters proactively. Such capability contributes to reducing cumulative inefficiencies that propagate along the production chain. From a data governance perspective, the consolidation of heterogeneous control signals into a standardized, traceable dataset strengthens transparency and accountability in operational management. Structured traceability by hole, equipment, and geological domain improves the reliability of performance assessments and supports evidence-based continuous improvement processes. In an environment where societal expectations increasingly demand responsible resource extraction, robust data governance becomes an essential pillar of operational credibility. The resilience mechanisms embedded in the architecture, particularly edge-level buffering and secure wireless transport, enhance data integrity under real mining conditions characterized by mobility and variable connectivity. Reliable data continuity reduces operational blind spots and strengthens the foundation for advanced analytics and long-term optimization strategies. Furthermore, democratizing access to operational intelligence through AI-assisted natural language interaction reduces technical barriers and accelerates decision-making across supervisory
RkJQdWJsaXNoZXIy MTM0Mzk2