Konferensartikel

Safe Active Learning of a High Pressure Fuel Supply System

Mark Schillinger
Bosch Engineering GmbH, Germany

Benedikt Ortelt
Bosch Engineering GmbH, Germany

Benjamin Hartmann
Bosch Engineering GmbH, Germany

Jens Schreiter
Robert Bosch GmbH, Germany

Mona Meister
Robert Bosch GmbH, Germany

Duy Nguyen-Tuong
Robert Bosch GmbH, Germany

Oliver Nelles
Automatic Control, Mechatronics, Department of Mechanical Engineering, University of Siegen, Germany

Ladda ner artikelhttp://dx.doi.org/10.3384/ecp17142286

Ingår i: Proceedings of The 9th EUROSIM Congress on Modelling and Simulation, EUROSIM 2016, The 57th SIMS Conference on Simulation and Modelling SIMS 2016

Linköping Electronic Conference Proceedings 142:41, s. 286-292

Visa mer +

Publicerad: 2018-12-19

ISBN: 978-91-7685-399-3

ISSN: 1650-3686 (tryckt), 1650-3740 (online)

Abstract

When modeling technical systems as black-box models, it is crucial to obtain as much and as informative measurement data as possible in the shortest time while employing safety constraints. Methods for an optimized online generation of measurement data are discussed in the field of Active Learning. Safe Active Learning combines the optimization of the query strategy regarding model quality with an exploration scheme in order to maintain user defined safety constraints. In this paper, the authors apply an approach for Safe Active Learning based on Gaussian process models (GP models) to the high pressure fuel supply system of a gasoline engine. For this purpose, several enhancements of the algorithm are necessary. An online optimization of the GP models’ hyperparameters is implemented, where special measures are taken to avoid a safety-relevant overestimation. A proper risk function is chosen and the trajectory to the sample points is taken into account regarding the estimation of the samples feasibility. The algorithm is evaluated in simulation and at a test vehicle.

Nyckelord

machine learning, system identification, active learning, Gaussian process models, automotive applications

Referenser

Inga referenser tillgängliga

Citeringar i Crossref