The problem of disrupted flight recovery is a very complicated real-time network optimization problem, which belongs to NP-hard problem. Considering the situation caused by the shortage of aircraft resources, the closure of airports and the unplanned maintenance, this paper adopts multiple recovery options, such as flight delays, flight cancellations, flight swaps and so on. Based on Dantzig-Wolfe decomposition principle, the mathematical optimization models of master problem and sub-problem are established respectively. And column generation algorithm is introduced to solve this large integer programming problem. In the solving process, first, the initial feasible routes are constructed and the master problem is solved with CPLEX software based on the lines. Secondly, in view of the characteristics of the problem, some properties are proposed, then the sub-problem is solved by using the improved "label-setting algorithm", and in each iteration, multiple columns with reduced cost are added to reduce the number of iterations, then the branch and bound algorithm is used to handle the non-integer solutions. Finally, the correctness and efficiency of the method are verified by testing the practical instances of various scales, and the test results are analyzed and summarized. [ABSTRACT FROM AUTHOR]