Different empirical and hybrid modelling techniques were evaluated in order to improve the modelling compared with the present situation in the plate rolling mill at Rautaruukki, Raahe. Logged data from the production were used to develop new models and to compare them with each other and with the present model. The data describe the chemical composition and various process parameters of the rolling process, including thermal, geometric and kinematic parameters. Various neural networks and multivariate models were evaluated in order to take non-linear effects into account. Hybrid methods use a combination of physically based models and empirical models. The simple physically based formula, force = area x yield strength factor, proved useful. A more advanced model solving von Karman's differential equation was evaluated as a stand-alone model and as part of a hybrid model. The measured force of the previous rolling pass was tested as an additional input variable. Various aspects of the different modelling techniques are discussed and compared. Simple but improved models are described as suitable candidates to replace the present on-line model. © Blackwell Munksgaard, 2002.