In recent years, in many areas of civil engineering applications, fuzzy logic models have been used. The aim of this paper is to develop a fuzzy logic model to predict the adhesion stress in polymer concrete. Availability of experimental data was required to develop the relationship between the mixture variables of polymer concrete and its measured properties. The basic parameters considered in this study were epoxy resin, silica fume, aggregate sort I and aggregate sort II dosage. Using Mamdani fuzzy model, with the said parameters, we effectively predicted the adhesion stress in polymer concrete accurately by taking into account the parameters of the problem. In these circumstances, data can be acquired in a short period of time without wasting material, with decreased design cost, all this without attempting experiments and thus saving time. This study showed that the model used has a good prediction and generalization capacity with acceptable errors.