Experimental study on the spray characteristics of octanol diesel and prediction of spray tip penetration by ANN model

In this paper, the effects of octanol addition on the spray characteristics of diesel are investigated through experiments of five blended fuels under different working conditions. Furthermore, the artificial neural network is introduced to predict spray tip penetration to avoid the prediction error...

Full description

Saved in:
Bibliographic Details
Published in:Energy (Oxford) 2022-01, Vol.239, p.121920, Article 121920
Main Authors: Tian, Junjian, Liu, Yu, Bi, Haobo, Li, Fengyu, Bao, Lin, Han, Kai, Zhou, Wenliang, Ni, Zhanshi, Lin, Qizhao
Format: Article
Language:English
Subjects:
ANN
Artificial neural networks
Diesel
Diesel fuels
Mathematical models
Neural networks
Octanol
Penetration
Predictions
Spray characteristics
Working conditions
Citations: Items that this one cites
Items that cite this one
Online Access:Get full text
Tags: Add Tag
No Tags, Be the first to tag this record!
Description
Summary:In this paper, the effects of octanol addition on the spray characteristics of diesel are investigated through experiments of five blended fuels under different working conditions. Furthermore, the artificial neural network is introduced to predict spray tip penetration to avoid the prediction errors of the existing mathematical models, and the optimal model is determined to facilitate future prediction of the spray tip penetration of the fuel. The results show that the spray tip penetration, spray cone angle, and spray area decrease first and then increase with the growth of the octanol ratio. The spray tip penetration of the 40% octanol blended fuel is the longest and the spray cone angle is similar to that of diesel. The spray area of blended fuel with octanol proportion greater than 20% is closer to that of diesel. Fifteen artificial neural network models are established and the predicted results of model 15 with a R2 of 0.99901 are in good agreement with the experimental results of the 20% octanol blended fuel. These indicate that the appropriate proportion of octanol can improve the spray characteristics of diesel, and the artificial neural network can be utilized to predict the spray characteristics and get better prediction results. ●ANN model is used to predict the spray tip penetration in high-pressure common rail.●Prediction results of ANN model and Mathematical model are compared with each other.●Spray tip penetration and angle vary inversely parabolic with increase of octanol.
ISSN:0360-5442
1873-6785
DOI:10.1016/j.energy.2021.121920