Deep coal mining operates in increasingly extreme environments, where substantial dust generated during the mining process poses serious risks to both production safety and miners' health. To understand the dust transport pattern and miners' particulate exposure risk within a full-scale heading face under various ventilation configurations, airflow patterns and dust dispersion characteristics were systematically investigated using the Euler–Lagrangian approach. A user-defined function was developed to enable the dynamic injection of particles, simulating realistic dust generation processes. The average residence times of particles with varying sizes were calculated, and the number of particles entering the respiratory zone was quantified to assess the driver's exposure risk. Results revealed that the driver remained in the recirculation zone in all layouts. The centrally positioned ventilation cylinder facilitated the suspension of smaller particles. With a total suspension time of 300 s and an air supply velocity of 11 m/s, particles sized below 20 µm exhibited the longest average residence time—11.24% and 26.24% longer than in layout R (cylinder on the opposite side of the driver) and layout L (cylinder on the driver's side), respectively. Smaller respiratory dust (i.e., dp < 7.07 µm) and particles originating from the upper part of the dust injection surface were most likely to enter the driver's respiratory zone. Increasing the fresh air supply alone proved insufficient to reduce particulate exposure. Among the configurations, layout L was optimal, reducing particulate exposure by 65.12% compared to layout R. This study provides theoretical insights for optimizing ventilation strategies within the heading face.