A data-driven probabilistic learning approach for the prediction of controllable pitch propellers performance
Document typeConference report
Rights accessOpen Access
All rights reserved. This work is protected by the corresponding intellectual and industrial property rights. Without prejudice to any existing legal exemptions, reproduction, distribution, public communication or transformation of this work are prohibited without permission of the copyright holder
The multi-ﬁdelity machine learning framework proposed in this paper leverages a probabilistic approach based on Gaussian Process modeling for the formulation of stochas- tic response surfaces capable of describing propeller performance for diﬀerent mission proﬁles. The proposed multi-ﬁdelity techniques will help coping with the scarcity of high-ﬁdelity measure- ments by using lower-ﬁdelity numerical predictions. The existing correlation of the multi-ﬁdelity data sets is used to infer high-ﬁdelity measurements from lower ﬁdelity numerical predictions. The probabilistic formulations embedded in Gaussian Process regressions gives the unique op- portunity to learn the target functions describing propeller performance at diﬀerent operating conditions, while quantifying the uncertainty associated to that speciﬁc prediction. While the multi-ﬁdelity autoregressive scheme allows to construct high accurate response surfaces using only few experimental data, Uncertainty Quantiﬁcation (UQ) provides an important metric to asses the quality of the learning process. We demonstrate the capability of the proposed frame- work to predict the performance of a controllable pitch propeller using few experimental data coming from towing tank experiments and many medium-ﬁdelity predictions obtained using an in-house developed BEM, validated and veriﬁed in many previous studies.
CitationGaggero, S. [et al.]. A data-driven probabilistic learning approach for the prediction of controllable pitch propellers performance. A: MARINE VIII. "MARINE VIII : proceedings of the VIII International Conference on Computational Methods in Marine Engineering". CIMNE, 2019, p. 544-555. ISBN 978-84-949194-3-5.