System inference is widely recognized as a critical challenging issue. Discrete event simulation model construction is the relevant approach regarding of this issue. Indeed, it allows to discover a Fuzzy Discrete Event System Specification (Fuzzy-DEVS) model from data using process mining. However, this approach lacks of modularity. In this paper, the objective is to propose a new method for Fuzzy-DEVS coupled model. This method extends discrete event simulation model construction by integrating fuzzy clustering. This later is implemented as a plugin in the Process Mining Framework (ProM). In order to evaluate the relevance, a case study is presented. In this case study, a real life data of business process is inferred and the SimStudio tool is used for its simulation.