Gaussian Process Position-Dependent Feedforward: With Application to a Wire Bonder

Max van Haren; Maurice  Poot; Dragan Kostic; Robin  van Es; Jim  Portegies; T.A.E. Oomen

doi:10.1109/AMC51637.2022.9729327

Gaussian Process Position-Dependent Feedforward: With Application to a Wire Bonder

Max van Haren, Maurice Poot, Dragan Kostic, Robin van Es, Jim Portegies, T.A.E. Oomen

Team Jan-Willem van Wingerden

Research output: Chapter in Book/Conference proceedings/Edited volume › Conference contribution › Scientific › peer-review

41 Downloads (Pure)

Abstract

Mechatronic systems have increasingly stringent performance requirements for motion control, leading to a situation where many factors, such as position-dependency, cannot be neglected in feedforward control. The aim of this paper is to compensate for position-dependent effects by modeling feedforward parameters as a function of position. A framework to model and identify feedforward parameters as a continuous function of position is developed by combining Gaussian processes and feedforward parameter learning techniques. The framework results in a fully data-driven approach, which can be readily implemented for industrial control applications. The framework is experimentally validated and shows a significant performance increase on a commercial wire bonder.

Original language	English
Title of host publication	Proceedings of the IEEE 17th International Conference on Advanced Motion Control (AMC 2022)
Publisher	IEEE
Pages	268-273
ISBN (Print)	978-1-7281-7711-3
DOIs	https://doi.org/10.1109/AMC51637.2022.9729327
Publication status	Published - 2022

Bibliographical note

Green Open Access added to TU Delft Institutional Repository 'You share, we take care!' - Taverne project https://www.openaccess.nl/en/you-share-we-take-care
Otherwise as indicated in the copyright section: the publisher is the copyright holder of this work and the author uses the Dutch legislation to make this work public.

Access to Document

10.1109/AMC51637.2022.9729327

Gaussian_Process_Position-Dependent_Feedforward_With_Application_to_a_Wire_BonderFinal published version, 1.32 MB

Cite this

@inproceedings{d5950450447541dda9d65c2cb75abd9f,

title = "Gaussian Process Position-Dependent Feedforward: With Application to a Wire Bonder",

abstract = "Mechatronic systems have increasingly stringent performance requirements for motion control, leading to a situation where many factors, such as position-dependency, cannot be neglected in feedforward control. The aim of this paper is to compensate for position-dependent effects by modeling feedforward parameters as a function of position. A framework to model and identify feedforward parameters as a continuous function of position is developed by combining Gaussian processes and feedforward parameter learning techniques. The framework results in a fully data-driven approach, which can be readily implemented for industrial control applications. The framework is experimentally validated and shows a significant performance increase on a commercial wire bonder.",

author = "{van Haren}, Max and Maurice Poot and Dragan Kostic and {van Es}, Robin and Jim Portegies and T.A.E. Oomen",

note = "Green Open Access added to TU Delft Institutional Repository 'You share, we take care!' - Taverne project https://www.openaccess.nl/en/you-share-we-take-care Otherwise as indicated in the copyright section: the publisher is the copyright holder of this work and the author uses the Dutch legislation to make this work public.",

year = "2022",

doi = "10.1109/AMC51637.2022.9729327",

language = "English",

isbn = "978-1-7281-7711-3",

pages = "268--273",

booktitle = "Proceedings of the IEEE 17th International Conference on Advanced Motion Control (AMC 2022)",

publisher = "IEEE",

address = "United States",

}

Gaussian Process Position-Dependent Feedforward: With Application to a Wire Bonder. / van Haren, Max; Poot, Maurice ; Kostic, Dragan et al.
Proceedings of the IEEE 17th International Conference on Advanced Motion Control (AMC 2022). IEEE, 2022. p. 268-273.

Research output: Chapter in Book/Conference proceedings/Edited volume › Conference contribution › Scientific › peer-review

TY - GEN

T1 - Gaussian Process Position-Dependent Feedforward: With Application to a Wire Bonder

AU - van Haren, Max

AU - Poot, Maurice

AU - Kostic, Dragan

AU - van Es, Robin

AU - Portegies, Jim

AU - Oomen, T.A.E.

N1 - Green Open Access added to TU Delft Institutional Repository 'You share, we take care!' - Taverne project https://www.openaccess.nl/en/you-share-we-take-care Otherwise as indicated in the copyright section: the publisher is the copyright holder of this work and the author uses the Dutch legislation to make this work public.

PY - 2022

Y1 - 2022

N2 - Mechatronic systems have increasingly stringent performance requirements for motion control, leading to a situation where many factors, such as position-dependency, cannot be neglected in feedforward control. The aim of this paper is to compensate for position-dependent effects by modeling feedforward parameters as a function of position. A framework to model and identify feedforward parameters as a continuous function of position is developed by combining Gaussian processes and feedforward parameter learning techniques. The framework results in a fully data-driven approach, which can be readily implemented for industrial control applications. The framework is experimentally validated and shows a significant performance increase on a commercial wire bonder.

AB - Mechatronic systems have increasingly stringent performance requirements for motion control, leading to a situation where many factors, such as position-dependency, cannot be neglected in feedforward control. The aim of this paper is to compensate for position-dependent effects by modeling feedforward parameters as a function of position. A framework to model and identify feedforward parameters as a continuous function of position is developed by combining Gaussian processes and feedforward parameter learning techniques. The framework results in a fully data-driven approach, which can be readily implemented for industrial control applications. The framework is experimentally validated and shows a significant performance increase on a commercial wire bonder.

U2 - 10.1109/AMC51637.2022.9729327

DO - 10.1109/AMC51637.2022.9729327

M3 - Conference contribution

SN - 978-1-7281-7711-3

SP - 268

EP - 273

BT - Proceedings of the IEEE 17th International Conference on Advanced Motion Control (AMC 2022)

PB - IEEE

ER -

Gaussian Process Position-Dependent Feedforward: With Application to a Wire Bonder

Abstract

Bibliographical note

Access to Document

Fingerprint

Cite this