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.
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