As of March 31, the Shuohuang Railway’s heavy-haul train has completed a cumulative safe autonomous driving mileage of 1,007,124 kilometers during its expanded trial phase, marking a milestone in the strategic transition from conventional heavy-haul transport to intelligent heavy-haul transport.
Since the initiation of the expanded trial for autonomous driving of heavy-haul trains on April 8, 2024, Shuohuang Railway has established a dual-track management system comprising the Autonomous Driving Expanded Trial Plan and Locomotive Autonomous Driving Management Measures, clearly defining the responsibilities of various departments. The Company has built a four-dimensional technical framework encompassing risk prevention & control, simulation verification, dynamic debugging, and data iteration. This process has generated a safety risk list with 20 categories of identified risks and 48 corresponding prevention & control measures, complemented by 20 multi-scenario simulation verifications and ongoing equipment debugging to create a complete closed-loop safety assurance for intelligent driving. The technological innovations presented four major breakthroughs: the scale of autonomous driving equipment has expanded from an initial 5 locomotives to 56; transportation marshaling now comprehensively covers standard trains, 10,000-tonne trains, and 20,000-tonne trains; operational segments cover 75% of the Shuohuang and Huangda lines; and the locomotives include both eight-axis and twelve-axis AC electric models, establishing a new transport model for “full model + full marshaling + multi-scenario” autonomous driving heavy-haul train. To enhance train operational efficiency, the Company develops intelligent decision-making algorithms by seamlessly integrating real-time line data, vehicle parameters, and dynamic models through the autonomous driving system. The speed has been improved by 2 kilometers per hour compared to manual driving and 100% automation of precise vehicle control has been achieved to eliminate human operational discrepancies, ensuring that trains can run safely, smoothly, and punctually according to established control strategies, effectively improving the stability of train operations and reducing the labor intensity for drivers while eradicating manual driving errors. In addition, indicators including safety, reliability, and intelligent application of the train operations have all met the expectations.
