• 综合
  • 标题
  • 关键词
  • 摘要
  • 学者
  • 期刊-刊名
  • 期刊-ISSN
  • 会议名称
搜索

作者:

Wang, Huaiyu (Wang, Huaiyu.) | Ji, Changwei (Ji, Changwei.) (学者:纪常伟) | Shi, Cheng (Shi, Cheng.) | Ge, Yunshan (Ge, Yunshan.) | Meng, Hao (Meng, Hao.) | Yang, Jinxin (Yang, Jinxin.) | Chang, Ke (Chang, Ke.) | Wang, Shuofeng (Wang, Shuofeng.)

收录:

EI Scopus SCIE

摘要:

In order to improve the performance, reduce the emissions and enhance the calibration efficiency of a gasoline Wankel rotary engine (WRE), three advanced machine learning (ML) methods, including artificial neural network (ANN), support vector machine (SVM), and Gaussian process regression (GPR), were applied to develop the prediction model of the torque, fuel flow, nitrogen oxide, carbon monoxide, and hydrocarbon. The effect of feature numbers was examined using the recommended parameters of the ANN, SVM, and GPR models. It was concluded that using speed, manifold absolute pressure, and air fuel ratio as input parameters to build the prediction model performed best. The generalization ability of the three ML models was compared on the interpolative and extrapolative data sets using the extended recommendation parameters. The results showed that the GPR model performed the best generalization ability in scarce data sets and was simpler to train compared with ANN and SVM. The response surfaces constructed using the GPR model were very smooth and accurate, in which the coefficient of determination for all the predicted parameters was more than 0.99. It is strongly proposed that the GPR approach is a universal approach which will be an essential direction for WRE system control and surrogate model modeling.

关键词:

Gasoline Wankel rotary engines Advanced machine learning methods Performance and emissions prediction Scarce data sets

作者机构:

  • [ 1 ] [Wang, Huaiyu]Beijing Inst Technol, Sch Mech Engn, Beijing 100081, Peoples R China
  • [ 2 ] [Ge, Yunshan]Beijing Inst Technol, Sch Mech Engn, Beijing 100081, Peoples R China
  • [ 3 ] [Ji, Changwei]Beijing Univ Technol, Coll Energy & Power Engn, Beijing Lab New Energy Vehicles, Beijing 100124, Peoples R China
  • [ 4 ] [Meng, Hao]Beijing Univ Technol, Coll Energy & Power Engn, Beijing Lab New Energy Vehicles, Beijing 100124, Peoples R China
  • [ 5 ] [Yang, Jinxin]Beijing Univ Technol, Coll Energy & Power Engn, Beijing Lab New Energy Vehicles, Beijing 100124, Peoples R China
  • [ 6 ] [Chang, Ke]Beijing Univ Technol, Coll Energy & Power Engn, Beijing Lab New Energy Vehicles, Beijing 100124, Peoples R China
  • [ 7 ] [Wang, Shuofeng]Beijing Univ Technol, Coll Energy & Power Engn, Beijing Lab New Energy Vehicles, Beijing 100124, Peoples R China
  • [ 8 ] [Ji, Changwei]Beijing Univ Technol, Key Lab Reg Air Pollut Control, Beijing 100124, Peoples R China
  • [ 9 ] [Meng, Hao]Beijing Univ Technol, Key Lab Reg Air Pollut Control, Beijing 100124, Peoples R China
  • [ 10 ] [Yang, Jinxin]Beijing Univ Technol, Key Lab Reg Air Pollut Control, Beijing 100124, Peoples R China
  • [ 11 ] [Chang, Ke]Beijing Univ Technol, Key Lab Reg Air Pollut Control, Beijing 100124, Peoples R China
  • [ 12 ] [Wang, Shuofeng]Beijing Univ Technol, Key Lab Reg Air Pollut Control, Beijing 100124, Peoples R China
  • [ 13 ] [Shi, Cheng]Yanshan Univ, Sch Vehicle & Energy, Qinhuangdao 066004, Hebei, Peoples R China
  • [ 14 ] [Wang, Huaiyu]Collaborat Innovat Ctr Elect Vehicles Beijing, Beijing 100081, Peoples R China
  • [ 15 ] [Ji, Changwei]Collaborat Innovat Ctr Elect Vehicles Beijing, Beijing 100081, Peoples R China
  • [ 16 ] [Ge, Yunshan]Collaborat Innovat Ctr Elect Vehicles Beijing, Beijing 100081, Peoples R China

通讯作者信息:

查看成果更多字段

相关关键词:

来源 :

ENERGY

ISSN: 0360-5442

年份: 2022

卷: 248

9 . 0

JCR@2022

9 . 0 0 0

JCR@2022

ESI学科: ENGINEERING;

ESI高被引阀值:49

JCR分区:1

中科院分区:1

被引次数:

WoS核心集被引频次: 68

SCOPUS被引频次: 72

ESI高被引论文在榜: 1 展开所有

  • 2023-5

万方被引频次:

中文被引频次:

近30日浏览量: 1

归属院系:

在线人数/总访问数:327/4977183
地址:北京工业大学图书馆(北京市朝阳区平乐园100号 邮编:100124) 联系我们:010-67392185
版权所有:北京工业大学图书馆 站点建设与维护:北京爱琴海乐之技术有限公司