Prediction method of engine performance and emission based on PSO-GPR

被引：0

作者：

Qin J. ^{[1
,2
]}

Zheng D. ^{[1
,2
]}

Pei Y.-Q. ^{[2
]}

Lyu Y. ^{[3
]}

Su Q.-P. ^{[2
,3
]}

Wang Y.-B. ^{[2
]}

机构：

[1] Internal Combustion Engine Research Institute, Tianjin University, Tianjin

[2] State Key Laboratory of Engines, Tianjin University, Tianjin

[3] GAC Automotive Research & Development Center, Guangzhou

来源：

Jilin Daxue Xuebao (Gongxueban)/Journal of Jilin University (Engineering and Technology Edition) | 2022年 / 52卷 / 07期

关键词：

emission prediction; Gaussian process regression; internal-combustion engine engineering; particle swarm optimization;

D O I：

10.13229/j.cnki.jdxbgxb20210111

中图分类号：

学科分类号：

摘要：

Aiming to overcome the problems of high cost and long development cycle of engine calibration test，a Gaussian Process Regression model based on Particle Swarm Optimization （PSO-GPR） is proposed to deal with nonlinear and complex engine performance and emission prediction for improving test efficiency. Working with calibration tests to the ignition angle of a gasoline engine and combined with the test design of gap filling，engine operating parameters such as torque，fuel consumption，IMEPcov，HC，NOx and CO emissions have been predicted by using the model with a small amount of test data. R2，RAAE and RMAE were introduced to evaluate the model generalization ability. On this basis，the influence of different number of training sets on the generalization ability of the model was studied，and the universality of the model has been verified with three different engines. The results show that the PSO-GPR model can predict the engine performance and emission parameters with expected accuracy which is better than traditional GPR model and Multivariate Polynomial Regression （MPR） model. The study suggests that the model is universal，which provides a reference for reducing the workload of engine calibration. © 2022 Editorial Board of Jilin University. All rights reserved.

引用

页码：1489 / 1498

页数：9

共 23 条

[1] Zhang Wen, Research on basic engine calibration based on operating conditions, (2019)
[2] Li Zhi-hui, Model-based electronic-controlled engine calibration technology, Internal Combustion Engine & Parts, 21, pp. 71-72, (2020)
[3] Du Le, Research on model-based calibration of GDI engine, (2013)
[4] Martinez M, Palacios H, Velazquez C., Modeling engine fuel consumption and NO<sub>x</sub> with RBF neural network and MOPSO algorithm[J], International Journal of Automotive Technology, 16, 6, pp. 1041-1049, (2015)
[5] Francesco D N, Giovanni G, Alfredo G, Et al., Volumetric efficiency estimation based on neural networks to reduce the experimental effort in engine base calibration, Fuel, 244, pp. 31-39, (2019)
[6] Rask E, Sellnau M., Simulation-based engine calibration: tools, techniques, and applications[J], SAE Transactions, 113, pp. 821-832, (2004)
[7] Gao J, Shen T., Online calibration of spark advance for combustion phase control of gasoline SI engines [C], Seventh International Conference on Intelligent Control and Information Processing (ICICIP), (2016)
[8] Carvalho R, Machado G B, Colaco M, Et al., Estimating gasoline performance in internal combustion engines with simulation metamodels, Fuel, 193, pp. 230-240, (2017)
[9] Zutta E, Acosta D, Andres D, Et al., Development of simulation metamodels to predict the performance and exhaust emission parameters of a spark ignition engine [J], International Journal on Interactive Design and Manufacturing (IJIDeM), 14, 1, pp. 1-12, (2020)
[10] Hou Xian-jun, Gao Han, Xi Guang-wei, Et al., Optimization analysis of engine ignition advance angle MAP based on BP neural network, Journal of Wuhan University of Technology (Traffic Science and Engineering Edition), 42, 3, pp. 353-356, (2018)

← 1 2 3 →