304 stress following the introduction of model-driven guidance. Productivity outcomes reflect system-level performance improvements, measured in terms of effective throughput per shift rather than isolated vehicle-level metrics. Table 2. Model Performance, Operational Impact, and Productivity Outcomes Evaluat ion Aspect Metric Obser ved Performance Operati onal Significance Speed Recommendati on Accuracy RMSE ±2.1 km/h Enables precise and safe real-time speed guidance CycleTime Prediction Accuracy MAE ±5.4 s per segment Support s reliable shortterm planning and forecasting CycleTime Consistency Variabi lity Reduction 5– 12% Improve s predictability and operational stability Fuel Consumption Reducti on 3–7% Lowers operating cost and environmental impact Braking Events Freque ncy Reduc ed Decreas es component wear and safety risk Operato r Behavior Variabi lity More uniform across shifts Reduces dependency on individual driving skill Product ivity Throug hput per shift ≈ 6% increase Improve s asset utilization and production output The proposed system offers several advantages over conventional static optimization and rule-based approaches. First, its adaptive learning capability allows the model to continuously update itself in response to evolving road, vehicle, and environmental conditions, minimizing performance degradation over time. Second, the integration of physics-based constraints with data-driven machine
RkJQdWJsaXNoZXIy MTM0Mzk2