Modeling of the nonlinear flame response of a Bunsen-type flame via multi-layer perceptron
| Autor: | Nguyen Anh Khoa Doan, Nils Thuerey, Camilo F. Silva, Nilam Tathawadekar |
|---|---|
| Rok vydání: | 2021 |
| Předmět: |
Premixed flame
Physics 020209 energy Mechanical Engineering General Chemical Engineering Fluid Dynamics (physics.flu-dyn) Describing function FOS: Physical sciences Physics - Fluid Dynamics 02 engineering and technology Mechanics Overfitting Perceptron 01 natural sciences 010305 fluids & plasmas law.invention Physics::Fluid Dynamics Nonlinear system law Multilayer perceptron Bunsen burner 0103 physical sciences 0202 electrical engineering electronic engineering information engineering Physical and Theoretical Chemistry Dropout (neural networks) |
| Zdroj: | Proceedings of the Combustion Institute |
| ISSN: | 1540-7489 |
| Popis: | This paper demonstrates the ability of neural networks to reliably learn the nonlinear flame response of a laminar premixed flame, while carrying out only one unsteady CFD simulation. The system is excited with a broadband, low-pass filtered velocity signal that exhibits a uniform distribution of amplitudes within a predetermined range. The obtained time series of flow velocity upstream of the flame and heat release rate fluctuations are used to train the nonlinear model using a multi-layer perceptron. Several models with varying hyperparameters are trained and the dropout strategy is used as a regularizer to avoid overfitting. The best performing model is subsequently used to compute the flame describing function (FDF) using mono-frequent excitations. In addition to accurately predicting the FDF, the trained neural network model also captures the presence of higher harmonics in the flame response. As a result, when coupled with an acoustic solver, the obtained neural network model is better suited than a classical FDF model to predict limit cycle oscillations characterized by more than one frequency. The latter is demonstrated in the final part of the present study. We show that the RMS value of the predicted acoustic oscillations, together with the associated dominant frequencies are in excellent agreement with CFD reference data. |
| Databáze: | OpenAIRE |
| Externí odkaz: |
|
Full Text from ScienceDirect