Aiming at the problem of the variable demand of ventilation system and the prominent problems of ventilation energy consumption, this paper conducts air volume optimization research on mine ventilation network based on fireworks algorithm (FWA). In order to solve the problem that FWA is easy to be precocious and fall into the local optimal solution, a kind of opposition-based enhanced fireworks algorithm (OBEFWA) is proposed. The algorithm adopts the strategy of uniform opposition-based initialization, which competes evenly distributed random populations with opposition-based populations, and selects the optimal initial population as the starting point of subsequent search. Then, the fireworks explosion radius is finely controlled, so that explosion radius of fireworks populations of different generations shows non-linear decline, and that of the same population generation adjusts adaptively. The minimum dynamic threshold is set to decrease waste of search resources. Finally, selection strategy of elite opposition-based learning is adopted to strengthen search for neighbourhood of elite fireworks, so as to improve global exploration ability of the algorithm. Through comparison experiments with FWA, enhanced fireworks algorithm(EFWA), and multi-group adaptive particle swarm optimization algorithm (MA-PSO), it is proved that the method of mine ventilation network air volume optimization based on OBEFWA has better optimization ability and convergence accuracy. Applying OBEFWA to mine ventilation network optimization, the total ventilation energy consumption after the implementation of the optimization is reduced by 14.54kW, and the energy saving effect is up to 20.46%, which validates that the algorithm is effective to achieve the goal of energy saving and consumption reduction.