Design of an Optimized GMV Controller Based on Data-Driven Approach

Authors
Liying Shi1, *, Zhe Guan2, Toru Yamamoto3
1Graduate School of Engineering, Hiroshima University, 1-4-1 Kagamiyama, HigashiHiroshima 739-8527, Japan
2KOBELCO Construction Machinery Dream-Driven Co-Creation Research Center, Hiroshima University, 1-4-1 Kagamiyama, HigashiHiroshima 739-8527, Japan
3Graduate School of Advanced Science and Engineering, Hiroshima, 1-4-1 Kagamiyama, HigashiHiroshima 739-8527, Japan
*Corresponding author. Email: [email protected]
Corresponding Author
Liying Shi
Received 14 November 2020, Accepted 21 August 2021, Available Online 9 October 2021.
DOI
https://doi.org/10.2991/jrnal.k.210922.006
Keywords
PID controller; GMV; Nelder–Mead method; data-driven approach
Abstract
This paper presents a data-driven scheme that can obtain the optimized Generalized Minimum Variance (GMV) control parameters by applying the Nelder–Mead (NM) method based on Proportional-Integral Derivative (PID) controller for linear system. An adjustable λ is included in the GMV-PID controller. In the existing GMV-PID controller, the PID parameters are calculated by simply changing λ manually. Therefore, it is hard to get desirable control performance. The NM method is introduced to improve the control performance. The application of NM method can optimize the calculation of λ. However, the objective function in NM method needs the output calculation. In other words, the model information is inevitably to obtain output. To achieve model-free design scheme, the estimation of closed-loop response method is introduced in database-driven approach. Using obtained closed-loop data can predict the output and then substitute it into the objective function without any model information of the process. The effectiveness is verified by experiment.
Copyright
© 2021 The Authors. Published by ALife Robotics Corp. Ltd.
Open Access
This is an open access article distributed under the CC BY-NC 4.0 license (http://creativecommons.org/licenses/by-nc/4.0/).

Download article (PDF)