Selective maintenance is often applied in many industrial environments where maintenance is performed between sequence missions. When the length of maintenance or work mission time is stochastic, previous research based on deterministic mission times is unsuitable. Assume that the time of work mission is random and maintenance time is determined in a two-state and parallel system, to maximise system reliability of next work mission in this paper a stochastic model is proposed under the maintenance time limit. The optimal maintenance plan is obtained with a hybrid intelligent optimisation algorithm. A simulation was performed to verify the validity and feasibility of the proposed model.