Due to the production process for continuous process manufacturing system (CPMS) cannot be stopped, the “opportunities” for maintenance can only occur within the specified time intervals. To improve the completion rate of production process, the focus of opportunistic maintenance for CPMS is whether the maintenance is to be performed at known time. Meanwhile, several opportunistic maintenance optimization models assumed imperfect maintenance to develop more reasonable maintenance plan. However, the parameters of imperfect maintenance cannot be accurately assessed (namely epistemic uncertainty) due to inadequate knowledge of maintenance and degradation mechanisms. This epistemic uncertainty was ignored in previous studies. Therefore, a novel opportunistic maintenance optimization model for CPMSs is proposed. The opportunity time window (OTW) concept is introduced to constrain the production-constrained maintenance opportunity. Three types of maintenance actions, including do nothing, perfect maintenance, and imperfect maintenance with epistemic uncertainty, are considered during the OTW to improve the production efficiency and performance of the manufacturing system. In the context of random and epistemic uncertainty, a stochastic fuzzy flow manufacturing network (SFFMN) is established to describe dynamic production processes and evaluate machine reliability. Moreover, a simulated annealing-based adaptive immune algorithm (SAAIA) with multiple immune operators is developed to address the opportunity maintenance optimization model of CPMSs. Finally, a case study of the hot rolling manufacturing system is provided to better understand the proposed method and demonstrate its effectiveness.