Recent developments in the field of process engineering and manufacturing sciences enable a new level of process understanding. However, extracting this understanding from increasing amounts of information is challenging. The aim of this study was to create a process vector from a model process describing all relevant information and, by that means, create a tool for combining and visualizing this information. Physical (impeller torque and temperature) and chemical (near-infrared spectroscopy) information from a small-scale high-shear granulation was used in the process vector. The vectors created were visualized by two different methods: principal component analysis (PCA) and the self-organizing map (SOM). None of the individual measurement techniques were able to describe the state of the process alone, although they provided important information about the process. By combining the data and visualizing it, an overview could be achieved. The SOM approach had two advantages over the PCA: it presented the results in terms of the original variables and enabled the analysis of nonlinear responses. However, both visualization methods could be used to describe the progress of the process and to increase the level of process understanding.