Method for regulating required airflow in mine roadways based on MSCALA

To address insufficient precision in determining ventilation resistance adjustment ranges and the susceptibility of coordinated multi-branch airflow regulation to disturbance-induced imbalance in conventional required-airflow regulation for mine roadways, this study proposed a method for regulating required airflow in mine roadways based on the Multi-Strategy Collaborative Artificial Lemming Algorithm (MSCALA). An on-demand airflow optimization and regulation model was established with airflow in the target air-demand branch as the objective. An exact penalty function method was used to transform constraints during optimization, and airflow sensitivity theory was used to select the resistance-adjustment branch set and determine reasonable ventilation resistance adjustment ranges. MSCALA, developed by incorporating a good point set population initialization strategy, a strategy combining an adaptive weight factor and a nonlinear escape coefficient, an Artificial Bee Colony global exploration strategy, and a Cauchy mutation strategy into the Artificial Lemming Algorithm (ALA), was then used to determine the optimal ventilation resistance adjustment value for each resistance-adjustment branch, thereby achieving precise airflow regulation. Experimental results showed that when the gas concentration in the air-demand branch exceeded the limit, the maximum airflow optimized by MSCALA for the target branch reached 7.01 m³/s, 66.11% higher than the initial airflow of 4.22 m³/s. MSCALA outperformed comparison algorithms including ALA, the Dung Beetle Optimizer, the Black-Winged Kite Algorithm, and the Enhanced Adaptive Lemming Algorithm in global search capability, convergence speed, and optimization performance. The method enables rapid, precise, and dynamic regulation of airflow in air-demand branches and effectively addresses insufficient airflow when the gas concentration exceeds the limit.