Purpose The recent expansion of intelligent transportation systems has created an urgent need for adaptive, real-time traffic control on large highway bridges that are exposed to dynamic environmental disturbances, such as crosswinds, vibrations and traffic congestion. Conventional fixed-limit or static fuzzy-control methods cannot effectively balance safety and throughput when multiple disturbances occur simultaneously. Design/methodology/approach Therefore, this research develops a dynamic-inertia fuzzy control with particle swarm optimization framework to realize self-tuning speed regulation. Unlike existing adaptive or rule-based models, the proposed method combines dynamic inertia adjustment, rule optimization and robustness learning to enhance convergence stability, computational efficiency and interpretability. Findings Experimental results demonstrated that this method performed well in multiple key indicators. Specifically, its average response time was 1.0 s, steady-state error was 0.5 km/h, speed limit output stabilization time was 4.6 s, and information release delay was 87.2 ms. Furthermore, it excelled in suppressing traffic conflict incidents, minimizing the number of conflict incidents to only 4. In summary, the speed limit control mechanism constructed in the study demonstrates strong robustness and optimization effect in complex traffic scenarios. Originality/value Innovatively proposed a fuzzy control speed limit model that integrates real-time traffic flow, structural safety monitoring, and environmental perception data, and achieves precise adaptive adjustment of speed limit thresholds through a dynamic weight allocation mechanism. These findings highlight the advantages of the proposed method in balancing adaptability, stability and interpretability. This method provides scalable solutions for intelligent bridge traffic management and advances adaptive control theory in complex transportation systems.
Zheng et al. (Sat,) studied this question.