Tissue engineering and regenerative medicine use information and technologies from various fields to restore or replace damaged tissues and organs. Ultimately, polymeric nanofibers have been the subject of intense research due to their applications in biomedicine, tissue engineering, compounds, filters, and energy storage. Although there are promising methods for the large-scale production of nanofibers, processes that guarantee high production at a low cost for industrialization have not yet been found. In this context, rotor spinning has emerged as a viable alternative, potentially producing nanofibers efficiently, but further studies are needed for its industrial application. Determining the optimal combination of rotation settings for large-scale production is a challenge, as it requires physicochemical knowledge of the polymer properties and control of variables such as rotation speed, collector distance, and rotating vessel temperature. There is a growing interest in computational models and machine learning algorithms to optimize manufacturing processes, where in this study, the production of polyvinyl alcohol (PVA) nanofibers using the rotor spinning technique was evaluated. Scanning electron microscopy analyzed the nanofibers obtained to determine their average diameter. Next, an unsupervised neural network, known as self-organizing maps, was used to categorize and group similar structures based on control data, also allowing the identification of optimized component modifications to develop biomaterials for specific applications.