Improved Firefly Algorithm for Optimization of Aero-engine Controller Based on PIDNN

Zongting Jiang, Lingfeng Gou, Chujia Sun, Meng Zhang

Research output: Chapter in Book/Report/Conference proceedingConference contributionpeer-review

2 Scopus citations

Abstract

In this paper, a two-control variable controller based on the Proportional-Integral-Derivative Neural Network (PIDNN) is designed to control a certain type of mixed exhaust turbofan engine. According to the working principle of the aero-engine, a two-variable small deviation state model of the aero-engine is firstly established. Then PIDNN including an input layer, a hidden layer and an output layer is used to design the controller of aero-engine states model. There are 4 nods in input layer, 6 in hide layer and 2 in output layer. To solve the problems of large steady-state error and long adjustment time of the PIDNN controller, this paper uses the improved firefly algorithm to dynamically adjust the initial connection weights of the PIDNN. The results show that the established aero-engine PIDNN controller based on the improved firefly algorithm has the characteristics of short adjustment time and high accuracy, which meets the requirements of aero-engine controller design.

Original languageEnglish
Title of host publicationProceedings of the 40th Chinese Control Conference, CCC 2021
EditorsChen Peng, Jian Sun
PublisherIEEE Computer Society
Pages7921-7926
Number of pages6
ISBN (Electronic)9789881563804
DOIs
StatePublished - 26 Jul 2021
Event40th Chinese Control Conference, CCC 2021 - Shanghai, China
Duration: 26 Jul 202128 Jul 2021

Publication series

NameChinese Control Conference, CCC
Volume2021-July
ISSN (Print)1934-1768
ISSN (Electronic)2161-2927

Conference

Conference40th Chinese Control Conference, CCC 2021
Country/TerritoryChina
CityShanghai
Period26/07/2128/07/21

Keywords

  • Aero-engine
  • Improved Firefly Algorithm
  • PIDNN

Fingerprint

Dive into the research topics of 'Improved Firefly Algorithm for Optimization of Aero-engine Controller Based on PIDNN'. Together they form a unique fingerprint.

Cite this