The following project deals with the optimization of simulation parameters such as the injection location and pitch angle of polyurethane foaming simulations using artificial neural networks. The model's target is to predict quality variables based on the process parameters and the geometry features. Through several evaluations of the model, good parameter combinations can be found which in turn can be used as good initial guesses by high fidelity optimization tools. For handling different mould geometries, a meshing tool has been programmed which transforms variable-sized surface meshes into voxel meshes. Cross-section images of the meshes are then passed together with a series of simulation settings to the neural network which processes the data streams into one set of predictions. The model has been implemented using the TensorFlow interface and trained with a custom generated data set of roughly 10000 samples. The results show well-matching prediction and simulation profiles for the validation cases. The magnitudes of the quality parameters often differ, but the especially relevant areas of optimal injection points are well covered. Good results together with a small model size provide evidence for a feasible and successful extension towards a full 3D application.

A Regional Climate Model (RCM) is a comprehensive tool to
simulate high-resolution climatic factors. A RCM is driven
by low resolution data obtained from a Global Climate Model
(GCM). In the one-way nested method, is the GCM data fed
into the RCM as a Lateral Boundary Condition (LBC) in certain
updates in time, the boundary data interval resolution.
The necessary information in between these updates is obtained
by using linear interpolation techniques. The ability
to reproduce high-resolution RCM output with low-resolution
GCM data depends on the accuracy of this LBC. This thesis
investigates whether third order interpolation methods lead to
a more accurate approximation than the linear method. This is
investigated in combination with lowering the boundary data
interval resolution.
The conclusion is that a third order interpolation method does
not lead to a more accurate approximation for a high boundary
data interval resolution. But when the resolution is lowered,
the linear interpolation method looses its accuracy earlier
than the third order method. This results in a boundary data
interval resolution of 1.5 hours for the linear method compared
to 7.5 hours for the third order method. Implementing
a lower boundary data interval resolution in combination with
the third order method lead to significant gain in computational
time and storage for the RCMs.