Kernel-based regression of non-causal systems for inverse model feedforward estimation

L.L.G. Blanken; J.W.A. van den Meijdenberg; T.A.E. Oomen

doi:10.1109/AMC.2019.8371137

Kernel-based regression of non-causal systems for inverse model feedforward estimation

L.L.G. Blanken, J.W.A. van den Meijdenberg, T.A.E. Oomen

Research output: Chapter in Book/Report/Conference proceeding › Conference contribution › Academic › peer-review

1 Citation (Scopus)

8 Downloads (Pure)

Abstract

Inversion-based feedforward control enables high performance for industrial motion systems. To this end, accurate knowledge of the inverse system is required, and non-causal control actions must be enabled. The aim of this paper is to accurately identify non-causal inverse models in view of high feedforward control performance. The developed method employs kernel-based regularization to minimize the mean squared error of the estimate. The performance benefits of the presented approach are demonstrated on an industrial printing system, including non-causal feedforward control actions.

Original language	English
Title of host publication	Proceedings - 2018 IEEE 15th International Workshop on Advanced Motion Control, AMC 2018
Place of Publication	Piscataway
Publisher	Institute of Electrical and Electronics Engineers
Pages	461-466
Number of pages	6
ISBN (Electronic)	9781538619469
DOIs	https://doi.org/10.1109/AMC.2019.8371137
Publication status	Published - 1 Jun 2018
Event	15th IEEE International Workshop on Advanced Motion Control, AMC 2018 - Shibaura Institute of Technology, Tokyo, Japan Duration: 9 Mar 2018 → 11 Mar 2018 Conference number: 15 http://ewh.ieee.org/conf/amc/2018/

Conference

Conference	15th IEEE International Workshop on Advanced Motion Control, AMC 2018
Abbreviated title	AMC 2018
Country/Territory	Japan
City	Tokyo
Period	9/03/18 → 11/03/18
Other	AMC2018 is the 15th in a series of biennial workshops that brings together researchers active in the field of advanced motion control to discuss current developments and future perspectives on motion control technology and applications. The workshop will be held at Shibaura Institute of Technology, Tokyo, Japan, during March 9-11, 2018.
Internet address	http://ewh.ieee.org/conf/amc/2018/

Keywords

Feedforward control
Gaussian process regression
Motion control
Regularization
System identification

Access to Document

10.1109/AMC.2019.8371137

Cite this

@inproceedings{cf6d5171c61743c9a3e1feda38a65ad1,

title = "Kernel-based regression of non-causal systems for inverse model feedforward estimation",

abstract = "Inversion-based feedforward control enables high performance for industrial motion systems. To this end, accurate knowledge of the inverse system is required, and non-causal control actions must be enabled. The aim of this paper is to accurately identify non-causal inverse models in view of high feedforward control performance. The developed method employs kernel-based regularization to minimize the mean squared error of the estimate. The performance benefits of the presented approach are demonstrated on an industrial printing system, including non-causal feedforward control actions.",

keywords = "Feedforward control, Gaussian process regression, Motion control, Regularization, System identification",

author = "L.L.G. Blanken and {van den Meijdenberg}, J.W.A. and T.A.E. Oomen",

year = "2018",

month = jun,

day = "1",

doi = "10.1109/AMC.2019.8371137",

language = "English",

pages = "461--466",

booktitle = "Proceedings - 2018 IEEE 15th International Workshop on Advanced Motion Control, AMC 2018",

publisher = "Institute of Electrical and Electronics Engineers",

address = "United States",

note = "15th IEEE International Workshop on Advanced Motion Control, AMC 2018, AMC 2018 ; Conference date: 09-03-2018 Through 11-03-2018",

url = "http://ewh.ieee.org/conf/amc/2018/",

}

Blanken, LLG, van den Meijdenberg, JWA & Oomen, TAE 2018, Kernel-based regression of non-causal systems for inverse model feedforward estimation. in Proceedings - 2018 IEEE 15th International Workshop on Advanced Motion Control, AMC 2018. Institute of Electrical and Electronics Engineers, Piscataway, pp. 461-466, 15th IEEE International Workshop on Advanced Motion Control, AMC 2018, Tokyo, Japan, 9/03/18. https://doi.org/10.1109/AMC.2019.8371137

Kernel-based regression of non-causal systems for inverse model feedforward estimation. / Blanken, L.L.G.; van den Meijdenberg, J.W.A.; Oomen, T.A.E.
Proceedings - 2018 IEEE 15th International Workshop on Advanced Motion Control, AMC 2018. Piscataway: Institute of Electrical and Electronics Engineers, 2018. p. 461-466.

Research output: Chapter in Book/Report/Conference proceeding › Conference contribution › Academic › peer-review

TY - GEN

T1 - Kernel-based regression of non-causal systems for inverse model feedforward estimation

AU - Blanken, L.L.G.

AU - van den Meijdenberg, J.W.A.

AU - Oomen, T.A.E.

N1 - Conference code: 15

PY - 2018/6/1

Y1 - 2018/6/1

N2 - Inversion-based feedforward control enables high performance for industrial motion systems. To this end, accurate knowledge of the inverse system is required, and non-causal control actions must be enabled. The aim of this paper is to accurately identify non-causal inverse models in view of high feedforward control performance. The developed method employs kernel-based regularization to minimize the mean squared error of the estimate. The performance benefits of the presented approach are demonstrated on an industrial printing system, including non-causal feedforward control actions.

AB - Inversion-based feedforward control enables high performance for industrial motion systems. To this end, accurate knowledge of the inverse system is required, and non-causal control actions must be enabled. The aim of this paper is to accurately identify non-causal inverse models in view of high feedforward control performance. The developed method employs kernel-based regularization to minimize the mean squared error of the estimate. The performance benefits of the presented approach are demonstrated on an industrial printing system, including non-causal feedforward control actions.

KW - Feedforward control

KW - Gaussian process regression

KW - Motion control

KW - Regularization

KW - System identification

UR - http://www.scopus.com/inward/record.url?scp=85048754415&partnerID=8YFLogxK

U2 - 10.1109/AMC.2019.8371137

DO - 10.1109/AMC.2019.8371137

M3 - Conference contribution

AN - SCOPUS:85048754415

SP - 461

EP - 466

BT - Proceedings - 2018 IEEE 15th International Workshop on Advanced Motion Control, AMC 2018

PB - Institute of Electrical and Electronics Engineers

CY - Piscataway

T2 - 15th IEEE International Workshop on Advanced Motion Control, AMC 2018

Y2 - 9 March 2018 through 11 March 2018

ER -

Kernel-based regression of non-causal systems for inverse model feedforward estimation

Abstract

Conference

Keywords

Access to Document

Other files and links

Fingerprint

Cite this