收藏切换
Research on diesel vehicle NH3 emission prediction method based on CNN-Transformer fusion framework
收藏切换
PDF
Xiao-xin BAI1, *, Xiang-yang GUO1, Chun-ling WU1, 2, Feng-bin WANG1, Xu LI1, Wei-lin LIU1
China Environmental Science | 2025, 45(3) : 1231 - 1240
Less
收藏切换
China Environmental Science | 2025, 45(3): 1231-1240
Air Pollution Control
Research on diesel vehicle NH3 emission prediction method based on CNN-Transformer fusion framework
Full
Xiao-xin BAI1, *, Xiang-yang GUO1, Chun-ling WU1, 2, Feng-bin WANG1, Xu LI1, Wei-lin LIU1
Affiliations
  • 1.CATARC Automotive Test Center (Tianjin) Co., Ltd., Tianjin 300300, China
  • 2.School of Mechanical Engineering, Tianjin University, Tianjin 300072, China
Published: 2025-03-20
Outline
收藏切换

In this study, a diesel vehicle NH3 emission prediction model based on the fusion framework of Convolutional Neural Network(CNN)and Transformer is proposed. The model was developed by integrating the local feature extraction capability of CNN with the global dependency modeling capability of Transformer, enabling the highly accurate prediction of NH3 emissions from diesel vehicles under real road driving conditions. The study was conducted based on the actual on-road emissions test data of an N3-class diesel vehicle. Feature screening was performed using the Pearson correlation coefficient method, and the key hyperparameters of the model were optimized through the application of the Bayesian algorithm, which enhanced its performance. Additionally, the SHapley Additive exPlanations(SHAP)algorithm was utilized to identify the pivotal factors influencing NH3 emissions. The results indicated that the proposed model achieved highly accurate predictions of NH3 emissions from diesel vehicles in real road driving conditions when tested on an independent dataset. The R2, MAE, and MSE values of the predicted NH3 concentration compared to the actual measured values were 0.986, 0.663, and 2.285, respectively, which were significantly superior to those obtained by the traditional Random Forest(RF)model, the Long Short-Term Memory(LSTM)neural network model, and the Transformer model. This study provided an efficient and reliable method for monitoring NH3 emissions from in-use diesel vehicles and offered a novel perspective for elucidating the principal factors influencing NH3 emissions from diesel vehicles on the road.

diesel vehicles  /  emission  /  NH3  /  convolutional neural network  /  transformer
Xiao-xin BAI, Xiang-yang GUO, Chun-ling WU, Feng-bin WANG, Xu LI, Wei-lin LIU. Research on diesel vehicle NH3 emission prediction method based on CNN-Transformer fusion framework[J]. China Environmental Science, 2025 , 45 (3) : 1231 -1240 .
Year 2025 volume 45 Issue 3
PDF
43
19
Cite this Article
BibTeX
Article Info
  • Receive Date:2024-08-20
  • Online Date:2026-03-18
  • Published:2025-03-20
Article Data
Affiliations
History
  • Received:2024-08-20
Funding
Affiliations
    1.CATARC Automotive Test Center (Tianjin) Co., Ltd., Tianjin 300300, China
    2.School of Mechanical Engineering, Tianjin University, Tianjin 300072, China
References
Share
https://castjournals.cast.org.cn/joweb/zghjkx/EN/
Share to
QR

Scan QR to access full text

Cite this article
BibTeX
Citations
表12种不同金属材料的力学参数

Family
属数
Number of
genus
种数
Number of
species
占总种数比例
Percentage of
total species (%)

Genus
种数
Number of
species
占总种数比例
Percentage of total
species (%)
鹅膏菌科Amanitaceae 2 11 5.26 鹅膏菌属 Amanita 10 4.78
小菇科 Mycenaceae 2 12 5.74 丝盖伞属 Inocybe 5 2.39
多孔菌科 Polyporaceae 8 14 6.70 蜡蘑属 Laccaria 5 2.39
红菇科 Russulaceae 3 23 11.00 小皮伞属 Marasmius 6 2.87
小菇属 Mycena 11 5.26
光柄菇属 Pluteus 5 2.39
红菇属 Russula 17 8.13
栓菌属 Trametes 5 2.39
关闭全屏
  • BibTeX
  • EndNote
  • RefWorks
  • TxT