Risk assessment of mechanical and electrical failures as a data‑driven foundation for alarming systems in autonomous dump trucks

Engineering notes

Key topics: autonomous driving. See the paper for implementation details and experimental results.

Chinese explanation / 中文解读

中文解读待补充：本站会优先为端到端自动驾驶、BEV感知、3D目标检测、轨迹预测、路径规划、LiDAR感知等高价值论文补充中文说明。

Original abstract

Effective risk analysis of dump truck failures is vital for enhancing reliability, minimizing downtime, and ensuring safety in mining operations. This study investigates failure modes of conventional dump trucks using three years of maintenance records from the Sarcheshmeh Copper Mine workshop, focusing only on mechanical and electrical failures (automation-related faults are outside the scope). Applying Pareto analysis and expert validation to key subsystems, a risk matrix was developed that identifies the engine as the dominant source of failures—accounting for 30% of incidents—followed by wheel and electrical systems. Primary engine failure mechanisms include power deficiency, coolant and oil leaks, and internal component malfunctions, all of which critically impair operational reliability. For each failure mode, targeted corrective actions were proposed (e.g., predefined sensor thresholds triggering alarms). Building on these findings, the study recommends tailored sensor and monitoring technologies to enable early fault detection and support preventive maintenance strategies for autonomous dump trucks. This sensor-based framework facilitates real‑time risk classification and effective mitigation. Grounded in empirical data, the proposed methodology provides a data‑driven, reproducible framework for improving safety and reliability, while acknowledging current limitations (static thresholds, autonomy‑failure exclusion) and future steps (predictive analytics).

Links and sources

• PDF from original source

Comments