In this contribution a dynamic model of maize breakage in hammer mills of different scales is proposed through a population balance approach. The results of the pilot-scale experiments were used to fit the parameters of the breakage and classification functions, considering the effects of rotor speed and screen opening size. The model was validated with both pilotand industrialscales steady-state data, which also included variations in feed rates. The developed model was used to predict the dynamic behavior of the product mass geometric mean diameter and mill hold-up as a function of disturbances in the feed rate and the rotor speed. These results are highly valuable since they indicate the feasibility of using the fitted model to predict with confidence new operating points, study industrial milling performance and optimize hammer mill operation reducing the need to carry out expensive and time-consuming experimental tests. (C) 2020 Elsevier B.V. All rights reserved.