«上一篇/Previous Article|本期目录/Table of Contents|下一篇/Next Article»

《内燃机学报》[ISSN:1006-6977/CN:61-1281/TN]

卷:

期数:

2020年05

页码:

457-463

栏目:

出版日期:

2020-09-25

文章信息/Info

Title:

Prediction of Diesel Engine NOx Emissions Based on Long-Short Term Memory Neural Network

作者:

戴金池1; 庞海龙2; 俞 妍2; 卜建国2; 资新运2

(1. 陆军军事交通学院研究生队，天津 300161；2. 陆军军事交通学院军用车辆工程系，天津 300161)

Author(s):

Dai Jinchi1; Pang Hailong2; Yu Yan2; Bu Jianguo2; Zi Xinyun2

(1. Postgraduate Team，Army Military Transportation University，Tianjin 300161，China；2. Military Vehicle Engineering Department，Army Military Transportation University，Tianjin 300161，China)

关键词:

柴油机; NOx 排放; 预测模型; 长短期记忆(LSTM)神经网络

Keywords:

diesel engine; nitrogen oxides emissions; prediction model; long short-term memory neural network

分类号:

TK421.5

DOI:

10.16236/j.cnki.nrjxb.202005059

文献标志码:

A

摘要:

柴油机NOx 排放是机动车排放污染物的主要来源，有效的NOx 排放预测模型是选择性催化还原技术(SCR)控制和车载诊断系统(OBD)完成SCR 监测的基础．利用长短期记忆(LSTM)神经网络预测某柴油机的NOx 排放，LSTM 神经网络能够记忆时间序列先前的输入并将其用于当前的预测．将稳态工况与瞬态工况整合成新的混合工况，并在划分的测试集和全球统一瞬态试验循环(WHTC)工况上验证模型精度，结果表明：LSTM 神经网络模型能够同时在稳态过程与瞬态过程取得较高的预测精度和稳定性，整合工况测试集的预测误差均方根为55.33×10-6，并且具备较强的泛化能力．

Abstract:

Diesel engine is the main source of NOx emissions in motor vehicles. An effective NOx emission prediction model takes an important role in control and on-board diagnosis(OBD)of the selective catalytic reduction(SCR)in order to reduce NOx emissions. The long-short term memory neural network(LSTM NN)，which can remember previous inputs in time series and then use them for current input predictions，was used to predict NOx emissions of a diesel engine. The prediction accuracy of the LSTM NN model was verified by various tests including the steady cycle，the transient cycle，the integrated cycle from the above cycles and the world harmonized transient cycle(WHTC)as well. The results show that the LSTM NN model has a good generalization ability. It can give a high prediction accuracy and a good data stability in both steady and transient operating processes，in which the root mean square error is 55.33×10-6.

常用功能

更新日期/Last Update: 2020-09-25