Intelligent Visual Data Exploration and Analytics for Automotive Engineering

The project aims to create a visual analytic tool facilitating the exploration of tremendous volumes of automotive engineering experimental data (e.g. filtering data sets and examining statistics), integrated with a machine learning approach, thereby enhancing the productivity of engineers or researchers. As a specific timely and vitally important application, it will propose a predictive model of low-speed pre-ignition, a recently identified abnormal combustion phenomena that predominantly affects state-of-the-art boosted, downsized, gasoline engines (that are currently seen as the most viable option for achieving emissions targets).