Abstract
AbstractThe performance of model-based engine calibration is highly dependent on the type of modelling which is used. A problem for state of the art algorithms for engine calibration arises, if outliers occur in the measurement data. Since outliers are not considered in recent types of modelling for engine calibration, they have to be removed before model training, in order to get a good model quality and a good prediction. This has serious drawbacks because either manual interaction is needed to identify the outliers, or automatic detection of outliers is not very robust if there are many outliers in the measurement data. In contrast to state of the art algorithms, a gaussian process modelling is presented, which is robust to outliers. After an introduction, the state of the art of modelling in engine calibration is presented and the drawbacks regarding outliers are shown. This is followed by a robust gaussian process formulation. At the end a simple theoretical example and an application on a diesel engine are given.
Talk to us
Join us for a 30 min session where you can share your feedback and ask us any queries you have
Schedule a callDisclaimer: All third-party content on this website/platform is and will remain the property of their respective owners and is provided on "as is" basis without any warranties, express or implied. Use of third-party content does not indicate any affiliation, sponsorship with or endorsement by them. Any references to third-party content is to identify the corresponding services and shall be considered fair use under The CopyrightLaw.
