Selective maintenance is often applied to many industrial environments when the maintenance actions are performed between sequence missions. When the length of maintenance or work mission time is stochastic and there are multiple maintenance workers with different capacity, previous works to determine maintenance and mission times are unsuitable for it. Assuming that the time of work mission is random and maintenance time is determined, to maximise system reliability of next work mission, this paper proposes a stochastic model for a two-state system comprising several series-parallel components with multiple maintenance workers under the maintenance time limit. The optimal maintenance plan is obtained by hybrid intelligent optimisation algorithm. The validity and feasibility of the model are verified by the simulation.