296 fuel rate, and other factors. 3. Builds a physics-informed, adaptive machine learning model that recommends optimal speeds and predicts cycle times. 4. Produces real-time operator coaching messages via a rule engine. 5. Allows continuous retraining using recent high-quality operational data. The existing studies focus on stochastic cycle-time modeling, terrain classification, fuel consumption optimization, dynamic dispatching. However, few integrate with GPS-based road segmentation, telematics fusion, incremental/adaptive learning, physics-informed ML, real-time operator feedback. This research addresses that gap by fusing domain knowledge with ML. 1. RESEARCH METHODOLOGY This research uses Adaptive Machine Learning Model to ensure practical usability and sustained performance in dynamic operational environments, that continuously updates its predictive capability based on recent telemetry data. The model is designed to support operational decision-making by providing real-time and near-real-time recommendations that reflect current road, vehicle, and operational conditions. In open-pit coal mining operations, haul truck productivity represents a primary performance indicator, as hauling typically accounts for the largest proportion of operational cost and time. Productivity is defined as the amount of material transported per unit time and is directly influenced by payload capacity, haul distance, road conditions, and operator driving behavior. The productivity of a haul truck can be mathematically expressed as: = where denotes truck productivity (tons/hour), is the effective payload per cycle (tons), and is the total cycle time (hours). The illustration of truck’s cycle is described in below: Figue 1. Truck’s Hauling Cycle Truck’s hauling cycle starts from the arrival of truck in front loading area until travels to disposal area and return to front area. When there are any other haulers in front when a hauler arrive, it needs to queue until the precedent hauler has completed the loading process. The total cycle time is decomposed into several sequential operational phases: = + ℎ + + + where:
RkJQdWJsaXNoZXIy MTM0Mzk2