Abstract: To address the defects of unreasonable distribution of air quantity, improper placement of ventilation control device, and high ventilation power consumption in complex mine ventilation networks, a non-linear optimization mathematical model for mine ventilation networks is constructed based on the graph theory and the ventilation network theory. This model takes the basic patterns of distribution of air quantity in mine ventilation networks, air quantity and air pressure in ventilation roadway, as well as the operating conditions of main ventilation fans as constraints, and uses an objective function that minimizes the ventilation network's power consumption. Afterward, the constraints are transformed into penalty terms in the objective function using the penalty function method. Based on the standard whale swarm optimization algorithm, a multi-strategy improvement method that integrates chaos reverse learning, Beta distribution, and non-linear self-adaptive inertia weight is proposed, with the view to enhancing the algorithm's local search and global optimization capabilities by improving solution accuracy and convergence speed. The improved whale swarm algorithm was used to solve the model, and the ventilation system of Xingdong Coal Mine of Jizhong Energy Co., Ltd. was simulated as the research object. The results show that the total power consumption of the mine ventilation network is reduced by 16.58%, and the distribution of air quantity of each air roadway in the mine is reasonable, which meets the actual ventilation requirements of the mine, demonstrating the feasibility and superiority of the adopted algorithm.