Emphasis in recent years has been focused on improving processes which lead to enhanced phosphate recovery. This paper studies the precipitation features of calcium phosphate in a fluidized bed reactor in a concentration range between 4 and 50 mg l(-1) and establishes the conditions for optimum phosphate removal efficiency For this purpose, two models are coupled for predicting the pellet reactor efficiency. First, a thermodynamical model is used for predicting calcium phosphate precipitation vs. initial conditions (pH, [P], [Ca], temperature). The second one IS reactor network model. Its parameters are identified by an optimization procedure based on simulated annealing and quadratic programming. The efficiency is computed by coupling a simple agglomeration model with a combination of elementary systems representing basic ideal flow patterns (perfect mixed flow, plug flow, etc.). More precisely, the superstructure represents the hydrodynamical conditions in the fluidized bed. The observed results show that a simple combination of ideal flow patterns is involved in pellet reactor modelling, which seems interesting for a future control. The experimental prototype used for validation purpose is first described. Then, the thermochemical model is presented for calcium phosphate precipitation. The third part is devoted to the reactor network-oriented model. The approach presented is finally validated with experimental runs.