The buffered optimization methods for online transfer function identification employed on DEAP actuator
Identification plays an important role in relation to control objects and processes as it enables the control system to be properly tuned. The identification methods described in this paper use the Stochastic Gradient Descent algorithms, which have so far been successfully presented in machine learn...
| Main Authors: | , |
|---|---|
| Format: | Article |
| Language: | English |
| Published: |
Polish Academy of Sciences
2023-09-01
|
| Series: | Archives of Control Sciences |
| Subjects: | |
| Online Access: | https://journals.pan.pl/Content/128383/PDF/art05_int.pdf |
| _version_ | 1797682260678279168 |
|---|---|
| author | Jakub Bernat Jakub Kołota |
| author_facet | Jakub Bernat Jakub Kołota |
| author_sort | Jakub Bernat |
| collection | DOAJ |
| description | Identification plays an important role in relation to control objects and processes as it enables the control system to be properly tuned. The identification methods described in this paper use the Stochastic Gradient Descent algorithms, which have so far been successfully presented in machine learning. The article presents the results of the Adam and AMSGrad algorithms for online estimation of the Dielectric Electroactive Polymer actuator (DEAP) parameters. This work also aims to validate the learning by batch methodology, which allows to obtain faster convergence and more reliable parameter estimation. This approach is innovative in the field of identification of control systems. The researchwas supplemented with the analysis of the variable amplitude of the input signal. The dynamics of the DEAP parameter convergence depending on the normalization process was presented. Our research has shown how to effectively identify parameters with the use of innovative optimization methods. The results presented graphically confirm that this approach can be successfully applied in the field of control systems. |
| first_indexed | 2024-03-11T23:57:10Z |
| format | Article |
| id | doaj.art-6eda7c34f5234dc1aaf9a4df479a80b6 |
| institution | Directory Open Access Journal |
| issn | 1230-2384 |
| language | English |
| last_indexed | 2024-03-11T23:57:10Z |
| publishDate | 2023-09-01 |
| publisher | Polish Academy of Sciences |
| record_format | Article |
| series | Archives of Control Sciences |
| spelling | doaj.art-6eda7c34f5234dc1aaf9a4df479a80b62023-09-18T10:54:20ZengPolish Academy of SciencesArchives of Control Sciences1230-23842023-09-01vol. 33No 3https://doi.org/10.24425/acs.2023.146960The buffered optimization methods for online transfer function identification employed on DEAP actuatorJakub Bernat0https://orcid.org/0000-0001-8890-7157Jakub Kołota1https://orcid.org/0000-0002-2177-1555Institute of Automatic Control and Robotics, Poznan University of Technology, Poznan, PolandInstitute of Automatic Control and Robotics, Poznan University of Technology, Poznan, PolandIdentification plays an important role in relation to control objects and processes as it enables the control system to be properly tuned. The identification methods described in this paper use the Stochastic Gradient Descent algorithms, which have so far been successfully presented in machine learning. The article presents the results of the Adam and AMSGrad algorithms for online estimation of the Dielectric Electroactive Polymer actuator (DEAP) parameters. This work also aims to validate the learning by batch methodology, which allows to obtain faster convergence and more reliable parameter estimation. This approach is innovative in the field of identification of control systems. The researchwas supplemented with the analysis of the variable amplitude of the input signal. The dynamics of the DEAP parameter convergence depending on the normalization process was presented. Our research has shown how to effectively identify parameters with the use of innovative optimization methods. The results presented graphically confirm that this approach can be successfully applied in the field of control systems.https://journals.pan.pl/Content/128383/PDF/art05_int.pdfstochastic gradient descentadamamsgraddeapsystem identification |
| spellingShingle | Jakub Bernat Jakub Kołota The buffered optimization methods for online transfer function identification employed on DEAP actuator Archives of Control Sciences stochastic gradient descent adam amsgrad deap system identification |
| title | The buffered optimization methods for online transfer function identification employed on DEAP actuator |
| title_full | The buffered optimization methods for online transfer function identification employed on DEAP actuator |
| title_fullStr | The buffered optimization methods for online transfer function identification employed on DEAP actuator |
| title_full_unstemmed | The buffered optimization methods for online transfer function identification employed on DEAP actuator |
| title_short | The buffered optimization methods for online transfer function identification employed on DEAP actuator |
| title_sort | buffered optimization methods for online transfer function identification employed on deap actuator |
| topic | stochastic gradient descent adam amsgrad deap system identification |
| url | https://journals.pan.pl/Content/128383/PDF/art05_int.pdf |
| work_keys_str_mv | AT jakubbernat thebufferedoptimizationmethodsforonlinetransferfunctionidentificationemployedondeapactuator AT jakubkołota thebufferedoptimizationmethodsforonlinetransferfunctionidentificationemployedondeapactuator AT jakubbernat bufferedoptimizationmethodsforonlinetransferfunctionidentificationemployedondeapactuator AT jakubkołota bufferedoptimizationmethodsforonlinetransferfunctionidentificationemployedondeapactuator |