TY - CHAP N2 - Autoinjector (AJ) devices are medical devices that enable subcutaneous selfadministration of medicines. A key challenge for AJs is the evaluation of injection time because in can impact on the usability of the autoinjector. Several models have been presented in literature to describe the injection time in AJs with different grade of complexity and accuracy. The limitation of the existing models is that they depend only on geometrical properties of the AJs, rheology of the fluid injected and the speed of the plunger. However, these models do not consider the dependence of friction on the distance travelled by the piston. In this paper a new hybrid model is developed to describe the injection time in AJs, integrating physics-based elements from the literature with data driven components. Results show that the proposed model is able to predict in an accurate way the experimentally measured friction force acting on the plunger. T3 - Computer Aided Chemical Engineering M1 - 53 ID - discovery10194425 N1 - This version is the author accepted manuscript. For information on re-use, please refer to the publisher?s terms and conditions. EP - 162 AV - restricted UR - https://doi.org/10.1016/B978-0-443-28824-1.50027-2 SP - 157 KW - Mathematical modelling KW - hybrid models KW - Gaussian processes TI - On the development of hybrid models to describe delivery time in autoinjectors Y1 - 2024/// A1 - Friso, A A1 - Palmer, M A1 - Bano, G A1 - Galvanin, F PB - Elsevier T2 - Computer Aided Chemical Engineering ER -