Predictive models for flame evolution using machine learning: A priori assessment in turbulent flames without and with mean shear

Abstract

Accurate prediction of temporal evolution of turbulent flames represents one of the most challenging problems in the combustion community. In this work, predictive models for turbulent flame evolution were proposed based on machine learning with long short-term memory (LSTM) and convolutional neural network-long short-term memory (CNN-LSTM). Two configurations without and with mean shear are considered, i.e., turbulent freely propagating premixed combustion and turbulent boundary layer premixed combustion, respectively. The predictions of the LSTM and CNN-LSTM models were validated against the direct numerical simulation (DNS) data to assess the model performance. Particularly, the statistics of the fuel (CH4 for the freely propagating flames and H2 for the boundary layer flames) mass fraction and reaction rate were examined in detail. It was found that generally the performance of the CNN-LSTM model is better than that of the LSTM model. This is because that the CNN-LSTM model extracts both the spatial and temporal features of the flames while the LSTM model only extracts the temporal feature of the flames. The errors of the models mainly occur in regions with large scalar gradients. The correlation coefficient of the mass fraction from the DNS and that from the CNN-LSTM model is larger than 0.99 in various flames. The correlation coefficient of the reaction rate from the DNS and that from the CNN-LSTM model is larger than 0.93 in the freely propagating flames and 0.99 in the boundary layer flames. Finally, the profiles of the DNS values and predictions conditioned on axial distance were examined, and it was shown that the predictions of the CNN-LSTM model agree well with the DNS values. The LSTM model failed to accurately predict the evolution of boundary layer flames while the CNN-LSTM model could accurately predict the evolution of both freely propagating and boundary layer flames. Overall, this study shows the promising performance and the applicability of the proposed CNN-LSTM model, which will be applied to turbulent flames a posteriori in future work.

A novel hybrid model for six main pollutant concentrations forecasting based on improved LSTM neural networks

“…The pooling layer is mainly used to pool the data after the sniper operation. Its main function is to compress the data, remove unnecessary information, effectively improve the generalization ability of the network, and increase the calculation speed 38 , 39 . Each node of the fully connected layer is connected to all nodes of the upper layer, which is used to integrate the comprehensive features extracted from the front and aid in the prediction of the subsequent LSTM layer 40 .…”

Recent developments in DNS of turbulent combustion

“…Models were discussed from DNS within RANS [64,112,113,128,189,233] and LES context [32,37,46,51,65,67,77,94,103,112,119,123,140,143,149,157,163,164,166,167,169,173,179,187,190,193,195,197,203,210,212,213,221,222,[233][234][235][236][237]. Finally, DNS for machine learning related method is rapidly emerging [51,110,139,140,146,173,…”

A Priori Modeling of NO Formation with Principal Component Analysis and the Convolutional Neural Network in the Context of Large Eddy Simulation

“…The simulation details were given in our previous studies ,,, and are briefly introduced in this section. Three-dimensional DNS of methane/air freely propagating premixed flame with different turbulent intensities is performed.…”

“…The simulation details were given in our previous studies 29,33,34,49 and are briefly introduced in this section. Three- 1a shows a schematic of the DNS configuration.…”

“…Therefore, machine learning could potentially capture the characteristics of combustion systems with good accuracy and high efficiency. So far, machine learning has been employed for various aspects of turbulent combustion. − For example, Wan et al , developed a method to simplify chemical mechanism using convolutional neural network (CNN) and artificial neural network (ANN) models. The nonlinear relationship between the reaction source terms and the temperature/species mass fractions was established by the machine learning models and was applied to a turbulent nonpremixed flame.…”