Local thermodynamic models are practical alternatives to computationally expensive rigorous models that involve implicit computational procures and often complement them to accelerate computation for run time optimization and control. Human-centered strategies for development of these models are based on approximation of theoretical models, are case based, and used limited data. This paper describes a fully data driven automatic self-evolving algorithm that builds appropriate approximating formulae for local model using genetic programming. No a priori information on the type of mixture (ideal/non ideal etc.) or assumption is necessary. At the end, the reliability of the model built by GP is tested.