The growing concern with environmental impact is a major drive for the tighter emissions imposed on combustion engines. The compliance with those restrictions is pushing new hardware and software solutions that, nevertheless, increase system complexity leading to more iterations and hence longer development time, a risk to profitability. In this context, it is paramount to reach optimum catalytic conversion temperature earlier through calibration strategies. This is challenging though, requiring heavy efforts in terms of time and use of resources/facilities.A promising approach to increase efficiency is the concept of virtualization via data-based engine modeling and model based calibration. This paper presents the combined automation and virtualization in vehicle for catalyst heating calibration. Firstly, a small number of test conditions were automatically measured based on a "Design of Experiment"(DoE). The acquired data was then fed into ASCMO, a Gaussian process regression algorithm implementation by ETAS, resulting in a model used for calibration optimization with respect to emission and engine stability targets. The use of this novel method anchored on automation, machine learning and virtualization aims to improve process efficiency and the robustness of the calibration data.
scite is a Brooklyn-based organization that helps researchers better discover and understand research articles through Smart Citations–citations that display the context of the citation and describe whether the article provides supporting or contrasting evidence. scite is used by students and researchers from around the world and is funded in part by the National Science Foundation and the National Institute on Drug Abuse of the National Institutes of Health.