Predictive Controller Based on Feedforward Neural Network with Rectified Linear Units

Doležel, Petr; Honc, Daniel; Štursa, Dominik

Digitální knihovna UPCE
→
Univerzita Pardubice
→
Publikační činnost akademických pracovníků UPCE / UPCE Research Outputs
→
Zobrazit záznam

Predictive Controller Based on Feedforward Neural Network with Rectified Linear Units

Doležel, Petr; Honc, Daniel; Štursa, Dominik

10.1007/978-3-030-30329-7_1

Soubory tohoto záznamu

URI: https://hdl.handle.net/10195/75124

Datum publikování: 2019

Typ dokumentu: ConferenceObject

ISSN: 2194-5357

Zdrojový dokument: Computational statistics and mathematical modeling methods in intelligent systems : proceedings of 3rd computational methods in systems and software 2019, Vol. 2

Název akce 3rd Computational Methods in Systems and Software, CoMeSySo 2019 (10.09.2019 - 12.09.2019, Zlín)

Abstrakt:

This paper deals with a nonlinear Model Predictive Control with a special form of the process model. Controller uses for the prediction purposes a locally valid linear sub-models. The sub-models are obtained from a neural model with the rectifier activation function in hidden neurons. Simulation example is given to demonstrate proposed solution - neural model design and predictive controller application.

Zobrazit celý záznam