Name
Title | ||
|---|---|---|
Data-Driven Feedforward Learning Using Non-Causal Rational Basis Functions: Application To An Industrial Flatbed Printer |
Abstract | ||
|---|---|---|
Data-driven feedforward learning enables high performance for industrial motion systems based on measured data from previous motion tasks. The key aspect herein is the chosen feedforward parametrization, which should parsimoniously model the inverse system. At present, high performance comes at the cost of parametrizations that are nonlinear in the parameters and consequences thereof. A linear parametrization is proposed that enables parsimonious modeling of inverse systems for feedforward through the use of non-causal rational orthonormal basis functions. The benefits of the proposed parametrization are experimentally demonstrated on an industrial printer, including pre-actuation and cyclic pole repetition. |
Year | Venue | Field |
|---|---|---|
2018 | 2018 ANNUAL AMERICAN CONTROL CONFERENCE (ACC) | Inverse,Nonlinear system,Data-driven,Parametrization,Control theory,Computer science,Basis function,Control system,Inverse system,Feed forward |
DocType | ISSN | Citations |
Conference | 0743-1619 | 0 |
PageRank | References | Authors |
0.34 | 0 | 4 |
Name | Order | Citations | PageRank |
|---|---|---|---|
| Lennart Blanken | 1 | 0 | 1.35 |
| Goksan Isil | 2 | 0 | 0.34 |
| Sjirk H. Koekebakker | 3 | 8 | 3.06 |
| Oomen, T. | 4 | 95 | 17.42 |