One of the basic issues in science and technology is modelling. The mathematical model can be developed on the basis of physical laws (analytical model) and as an approximation of the measured data (empirical model). The advantage of using analytical models is the ability to accurately understand the process mechanism. Most often, these processes are characterized by a high degree of complexity which makes it impossible to develop a model using only the process laws of physics. In such cases, empirical models are most frequently used, which, compared to analytical models, are easier to develop. However, the scope of their applicability is limited to the operating parameters for which the model was calibrated. Good results are obtained by combining analytical and empirical models. The prediction quality may be enhanced by the use of Advanced Data Validation and Reconciliation method (DVR) in order to increase the reliability of the measurements which were used for identification of model parameters. The article presents the examples of identification of the analytical empirical models on the basis of reconciled measure results. The identification of mathematical models was presented with example of double pressure HRSG and multi-fuel boiler. Appropriate conclusions have also been formulated. (C) 2019 Published by Elsevier Ltd.