Modeling cheese fabrication process helps experts to check their assumption on the domain such as finding which parameters (de-noted as control parameters) can explain the final products and its properties. This modeling is however complex as it involves various parameters and a reasoning over different steps. Our previous work presents a method to learn a probabilistic relational model in order to check a user's (an expert on the considered domain) assumption on a transformation process domain, using a knowledge base of this domain and his expert knowledge. However this method did not include temporal information, and thus the learned model is not enough to reason on the cheese fabrication process. In this article we present an extension of our previous work that allows a user to integrate causal and temporal information represented by precedence constraints in order to model a cheese fabrication process. This allows the user to check his assumption to identify the transformation process control parameters.