Abstract: Mine ventilation network solving is a key link in the work of “one pass, three precautions” in coal mines. Aiming at the problems of large airflow deviation, poor solution accuracy and low computational efficiency in mine ven-tilation network, a ventilation network solution method integrating rough set attribute simplification and weighted least squares (WLS) is proposed. The method identifies the key parameters in the ventilation network by rough set attribute approximation algorithm, constructs the residual branch set of the minimum spanning tree by using Prim preferential queuing algorithm, and introduces the WLS-residual branch determination method for iterative optimization of the branch weights, which reduces the data error in the ventilation network solution. The results show that the method improves the calculation accuracy and solving efficiency of the airflow of complex ventilation network, and the deviation of airflow calculation is 0.1%~1.1%, which provides theoretical basis and technical support for the airflow regulation of mine ventilation system.