USING CMA-ES FOR TUNING COUPLED PID CONTROLLERS WITHIN MODELS OF COMBUSTION ENGINES

Kód výsledku v IS VaVaI

<a href="https://www.isvavai.cz/riv?ss=detail&h=RIV%2F68407700%3A21340%2F19%3A00374186" target="_blank" >RIV/68407700:21340/19:00374186 - isvavai.cz</a>

Výsledek na webu

<a href="https://doi.org/10.14311/NNW.2019.29.020" target="_blank" >https://doi.org/10.14311/NNW.2019.29.020</a>

DOI - Digital Object Identifier

<a href="http://dx.doi.org/10.14311/NNW.2019.29.020" target="_blank" >10.14311/NNW.2019.29.020</a>

Jazyk výsledku

angličtina

Název v původním jazyce

USING CMA-ES FOR TUNING COUPLED PID CONTROLLERS WITHIN MODELS OF COMBUSTION ENGINES

Popis výsledku v původním jazyce

Proportional integral derivative (PID) controllers are important and widely used tools of system control. Tuning their gains is a laborious task, especially for complex systems such as combustion engines. To minimize the time an engineer spends tuning the gains in a simulation software, we propose to formulate a part of the problem as a black-box optimization task. In this paper, we summarize the properties and practical limitations of gain tuning in this particular application. We investigate the latest methods of black-box optimization and conclude that the Covariance Matrix Adaptation Evolution Strategy (CMA-ES) with bi-population restart strategy, elitist parent selection and active covariance matrix adaptation is best suited for this task. Details of the algorithm's experiment-based calibration are explained as well as derivation of a suitable objective function. The method's performance is compared with that of PSO and SHADE. Finally, its usability is verified on six models of real engines.

Název v anglickém jazyce

USING CMA-ES FOR TUNING COUPLED PID CONTROLLERS WITHIN MODELS OF COMBUSTION ENGINES

Popis výsledku anglicky

Proportional integral derivative (PID) controllers are important and widely used tools of system control. Tuning their gains is a laborious task, especially for complex systems such as combustion engines. To minimize the time an engineer spends tuning the gains in a simulation software, we propose to formulate a part of the problem as a black-box optimization task. In this paper, we summarize the properties and practical limitations of gain tuning in this particular application. We investigate the latest methods of black-box optimization and conclude that the Covariance Matrix Adaptation Evolution Strategy (CMA-ES) with bi-population restart strategy, elitist parent selection and active covariance matrix adaptation is best suited for this task. Details of the algorithm's experiment-based calibration are explained as well as derivation of a suitable objective function. The method's performance is compared with that of PSO and SHADE. Finally, its usability is verified on six models of real engines.

Druh

J_imp - Článek v periodiku v databázi Web of Science

CEP obor

—

OECD FORD obor

10103 - Statistics and probability

Projekt

—

Návaznosti

S - Specificky vyzkum na vysokych skolach

Rok uplatnění

2019

Kód důvěrnosti údajů

S - Úplné a pravdivé údaje o projektu nepodléhají ochraně podle zvláštních právních předpisů

Název periodika

Neural Network World

ISSN

1210-0552

e-ISSN

—

Svazek periodika

29

Číslo periodika v rámci svazku

5

Stát vydavatele periodika

CZ - Česká republika

Počet stran výsledku

20

Strana od-do

325-344

Kód UT WoS článku

000497700600003

EID výsledku v databázi Scopus

2-s2.0-85077063705