Control of Combustion Instabilities on a Rijke Tube by a Neural Network

Abstract

Combustion instabilities still constitute a major problem for powerplant development. In this paper a Rijke tube which presents for some operating conditions instabilities with pressure level up to 145 dB/Hz is considered. In order to control instabilities an Internal Model Control System for nonlinear plants that uses two neural networks has been developed. The first one is an Internal Model which approximates the plant forward dynamic (the learning process). The second one gives the adaptive control input. The capacity of approximating the noisy signals of instabilities (microphone or photomultiplier for OH emission proportional to heat release) with a good precision is demonstrated. Attenuation of instabilities for fixed or variable operating conditions with pressure level attenuation up to 60 dB/Hz has been obtained.

Open PDF

Document Details

Document Type
Technical Report
Publication Date
Jun 01, 2001
Accession Number
ADP011164

Entities

People

  • A. Laverdant
  • R. Blonbou

Organizations

  • Office National d'Études et de Recherches Aérospatiales

Tags

Communities of Interest

  • Energy and Power Technologies
  • Materials and Manufacturing Processes
  • Space

DTIC Thesaurus Topics

  • Acoustic Waves
  • Algorithms
  • Chambers
  • Combustion
  • Computer Programs
  • Control Systems
  • Data Acquisition
  • Flame Holders
  • Flow Rate
  • Frequency
  • Heat Of Combustion
  • Heat Transfer
  • Ignition
  • Microphones
  • Military Aircraft
  • Neural Networks
  • Signal Processing

Fields of Study

  • Physics

Readers

  • Electrical Engineering
  • Neural Network Machine Learning.
  • Structural Dynamics.

Technology Areas

  • AI & ML
  • AI & ML - Autonomous Systems
  • AI & ML - Bayesian Inference
  • AI & ML - Machine Learning Algorithms
  • AI & ML - Machine Translation
  • AI & ML - Neural Networks