TY - JOUR
T1 - Predicting octane number from species profiles
T2 - A deep learning model
AU - Wang, Yiru
AU - Dong, Wendi
AU - Liang, Wenkai
AU - Yang, Bin
AU - Law, Chung K.
N1 - Funding Information:
The work at Tsinghua University was supported by the National Natural Science Foundation of China (No. T2241003 and 91841301 ), and by the Seed Fund of Shanxi Research Institute for Clean Energy.
Publisher Copyright:
© 2022 The Combustion Institute
PY - 2023/1
Y1 - 2023/1
N2 - Recognizing that the calibration of octane number (ON) of a fuel by standard experimental testings is often challenging due to the lack of samples and the complexity of the experimental operating conditions, we propose herein the use of convolutional neural network (CNN) method for its prediction based on the time-resolved information contained in the profiles of some small combustion species (e.g., OH, HO2, CH2O) involved in constant volume autoignition. The approach first pre-processes the species profiles obtained from experiments or simulations as input parameters and then uses convolutional neural networks for feature extraction. The obtained features are concatenated with the corresponding temperature, pressure, and ignition delay time and fed into a multilayer perceptron neural network for ON prediction. The method is validated on data sets consisting of fuel blends and various single components, including alkanes, esters, alcohols, etc. Results show that the method exhibits a high accuracy for predicting the ON of not only single component fuels but also fuel mixtures with a mean absolute error of less than 2, and that parameter sharing allows the neural network to use few parameters while extracting some high-level semantic features. Furthermore, since the input information is some common small species, the method can make predictions for almost any fuel, especially for fuel blends whose information on physical parameters and molecular structure is not available.
AB - Recognizing that the calibration of octane number (ON) of a fuel by standard experimental testings is often challenging due to the lack of samples and the complexity of the experimental operating conditions, we propose herein the use of convolutional neural network (CNN) method for its prediction based on the time-resolved information contained in the profiles of some small combustion species (e.g., OH, HO2, CH2O) involved in constant volume autoignition. The approach first pre-processes the species profiles obtained from experiments or simulations as input parameters and then uses convolutional neural networks for feature extraction. The obtained features are concatenated with the corresponding temperature, pressure, and ignition delay time and fed into a multilayer perceptron neural network for ON prediction. The method is validated on data sets consisting of fuel blends and various single components, including alkanes, esters, alcohols, etc. Results show that the method exhibits a high accuracy for predicting the ON of not only single component fuels but also fuel mixtures with a mean absolute error of less than 2, and that parameter sharing allows the neural network to use few parameters while extracting some high-level semantic features. Furthermore, since the input information is some common small species, the method can make predictions for almost any fuel, especially for fuel blends whose information on physical parameters and molecular structure is not available.
KW - Convolutional neural network
KW - Deep learning
KW - Fuel blends
KW - Octane number
KW - Species profile
UR - http://www.scopus.com/inward/record.url?scp=85139181972&partnerID=8YFLogxK
UR - http://www.scopus.com/inward/citedby.url?scp=85139181972&partnerID=8YFLogxK
U2 - 10.1016/j.proci.2022.08.015
DO - 10.1016/j.proci.2022.08.015
M3 - Article
AN - SCOPUS:85139181972
SN - 1540-7489
VL - 39
SP - 5269
EP - 5277
JO - Proceedings of the Combustion Institute
JF - Proceedings of the Combustion Institute
IS - 4
ER -