A Decision Tree-Based Dynamic Maintenance Interval Model Incorporating Driver Behavior and Traffic Congestion: An Application to an Electric Bus Fleet

In The increasing electrification of urban bus fleets necessitates maintenance strategies that reflect real-world operational variability rather than relying on fixed mileage intervals. This study proposes a Decision Tree (DT)-based dynamic maintenance interval model developed using approximately 58,343 high-resolution operational records collected from 20 drivers operating the same electric bus route under comparable boundary conditions. The dataset includes energy consumption, vehicle speed, vehicle mass, ambient temperature, road slope, acceleration, regenerative braking power, and traffic congestion indicators. Correlation analysis revealed strong associations between operational variables and failure indicators, with coefficients reaching up to 0.94. Among the evaluated regression techniques, the Decision Tree model demonstrated superior predictive performance (R² = 0.95, RMSE = 0.314, MSE = 0.1523, MAE = 0.343), outperforming Support Vector Machine (R² = 0.93) and Gaussian Process Regression (R² = 0.92). The optimal operating profile identified by the DT-based estimation indicated an energy consumption level of 501 kW, an average vehicle speed of 47 km/h, acceleration of 0.27 m/s², slope of 3.45%, and recuperation power of 612 kW under 23.5% traffic congestion. Driver-level comparisons showed that deviations from these optimal parameters resulted in measurable shifts in projected maintenance intervals, particularly for drivers exhibiting higher acceleration (≥0.35 m/s²) and elevated energy consumption (>540 kW). The findings demonstrate that maintenance thresholds in electric bus systems are strongly influenced by operational behavior and can be dynamically adjusted through data-driven modeling. The proposed framework offers a quantitative basis for predictive maintenance scheduling, enabling fleet operators to reduce premature servicing and mitigate failure risk while improving operational efficiency.