Deep Learning Applied to Data-driven Dynamic Characterization of Hysteretic Piezoelectric Micromanipulators
| Autor: | Matheus Patrick Soares Barbosa, Helon Vicente Hultmann Ayala, Micky Rakotondrabe |
|---|---|
| Přispěvatelé: | Pontifical Catholic University of Rio de Janeiro (PUC), Laboratoire Génie de Production (LGP), Ecole Nationale d'Ingénieurs de Tarbes, Institut National Polytechnique de Toulouse - Toulouse INP (FRANCE), Pontifícia Universidade Católica do Rio de Janeiro - PUC (BRAZIL) |
| Rok vydání: | 2020 |
| Předmět: |
0209 industrial biotechnology
Computer science 02 engineering and technology Compensation (engineering) Data-driven 020901 industrial engineering & automation 0202 electrical engineering electronic engineering information engineering Electronique [SPI.NANO]Engineering Sciences [physics]/Micro and nanotechnologies/Microelectronics Piezoeletric micromanipulators Perception and sensing Artificial neural networks Nonlinear system identification Artificial neural network business.industry Deep learning 020208 electrical & electronic engineering System identification Control engineering Piezoeletricmicromanipulators [SPI.TRON]Engineering Sciences [physics]/Electronics System dynamics Identification (information) Micro et nanotechnologies/Microélectronique Hysteresis modeling Control and Systems Engineering Identification and control methods Artificial intelligence Micro and nano mechatronic systems business |
| Zdroj: | Proceedings of IFAC-World Congress 2020 IFAC-World Congress 2020 IFAC-World Congress 2020, Jul 2020, Berlin, Germany. pp.1-6 |
| ISSN: | 2405-8963 |
| DOI: | 10.1016/j.ifacol.2020.12.566 |
| Popis: | International audience; The presence of nonlinearities such as hysteresis and creep increases the difficulty in the dynamic modeling and control of piezoelectric micromanipulators, in spite of the fact that the application of such devices requires high accuracy. Moreover, sensing in the microscale is expensive, making model feedback the only viable option. On the other hand, data-driven dynamic models are powerful tools within system identification that may be employed to construct models for a given plant. Recently, considerable effort has been devoted in extending the huge success of deep learning models to the identification of dynamic systems. In the present paper, we present the results of the successful application of deep learning based black-boxmodels for characterizing the dynamic behavior of micromanipulators. The excitation signal is a multisine spanning the frequency band of interest and the selected model is validated with semi static individual sinusoidal curves. Various architectures are tested to achieve a reasonable result and we try to summarize the best approach for the fine tuning required for such application. The results indicate the usefulness and predictive power for deep learning based models inthe field of system identification and in particular hysteresis modeling and compensation in micromanipulation applications. |
| Databáze: | OpenAIRE |
| Externí odkaz: |
|