Development of a modular Knowledge-Discovery Framework based on Machine Learning for the interdisciplinary analysis of complex phenomena in the context of GDI combustion processes

In this work, a novel knowledge discovery framework able to analyze data produced in the Gasoline Direct Injection (GDI) context through machine learning is presented and validated. This approach is able to explore and exploit the investigated design spaces based on a limited number of observations, discovering and visualizing connections and correlations in complex phenomena. The extracted knowledge is then validated with domain expertise, revealing potential and limitations of this method.