The underground water supply network system of coal mine is the key link to ensure the safety of coal mine production. Aiming at the problems of high energy consumption, high leakage rate and increased regulation complexity of the underground water supply network system of coal mine in Shaanxi province, the intelligent regulation and control policy research is carried out based on the actual working conditions of the underground water supply system. A two-level optimal scheduling model is established based on the factors affecting the pipeline network. The optimal water supply pressure and water supply of each pump house are determined through the first-level optimal scheduling. Then, the operation cost of the pump group is taken as the objective function to establish the second-level optimization model to seek the optimal operation scheme of the pump. In order to solve the problem that the traditional genetic algorithm is easy to fall into the local optimal solution, the combined mutation operator is used to improve the model. The experimental results show that the energy consumption of the underground coal mine water supply system is significantly reduced and the energy saving effect is remarkable, and the average daily energy saving is 8.8% under the premise of ensuring the safe operation of the water supply system.