![Sample our Economics, Finance,Business & Industry journals, sign in here to start your access, latest two full volumes FREE to you for 14 days]({"type":"image" , "src" : "/sda/5931/TOC-Subject-Sample-2021-Economics-Finance-Business-Industry.jpg"})
ABSTRACT
High-performance and low-cost emission characteristic prediction is very crucial for diesel engine design optimization and emission aftertreatment control and diagnosis. In this paper, a novel hybrid model that combines Convolutional Neural Network (CNN) and Gated Recurrent Unit Network (GRU) was proposed to predict the emission characteristic from diesel engines, encompassing CO, THC, CO2, NOx, exhaust temperature and exhaust pressure. Nine operating parameters from WHTC and WHSC cycles, including speed, torque, intake pressure, intake flow, intake temperature, oil pressure, fuel rate, oil temperature, water temperature, were considered as inputs. Firstly, the importance of each variable is evaluated by Random Forests algorithm to determine the optimal inputs for each emission characteristic parameter and reduce redundancy. Then the effect of different hyperparameters on the model performance was discussed in detail and PSO algorithm was used to obtain the optimal hyperparameters. Finally, the CNN-GRU hybrid model was assessed for its generalization and compared with ANN, LSTM and GRU models. The result demonstrates that the CNN-GRU hybrid model with PSO optimization has excellent prediction performance in either the training dataset or the validation dataset. The average value of R2 is 0.993 in the training dataset and 0.985 on the validation dataset. In the test dataset, the average R2 is 0.961, showing a minor decrease of 3.19% and 2.47% compared to the training and validation dataset, respectively. This indicates that the CNN-GRU hybrid model has strong generalization ability. Compared with other algorithms in the test dataset, the CNN-GRU hybrid model exhibits better comprehensive performance, with the average R2 value exceeding that of ANN, LSTM and only GRU by 5.96%, 2.69% and 3.23%, respectively.
HIGHLIGHT
A novel hybrid model that combines CNN and GRU was proposed and applied to the emission characteristic prediction of diesel engines.
The variable selection is performed based on Random Forests and PSO algorithm is used to identity optimal model hyperparameters.
CNN-GRU hybrid model shows strong generalization ability and better comprehensive performance compared with other algorithms.
Nomenclature
| ANFIS | = | Adaptive-Network-Based Fuzzy Inference System |
| ANN | = | Artificial Neural Network |
| BMEP | = | Brake Mean Effective Pressure |
| BSFC | = | Braked Specific Fuel Consumption |
| CEEMDAN | = | Complete Ensemble Empirical Mode Decomposition With Adaptive Noise |
| CNN | = | Convolutional Neural Network |
| CO | = | Carbon Monoxide |
| CO2 | = | Carbon Dioxide |
| GA | = | Genetic Algorithm |
| GRU | = | Gated Recurrent Unit |
| HC | = | Hydrocarbon |
| LSTM | = | Long Short-Term Memory |
| MAPE | = | Mean Absolute Percentage Error |
| NOx | = | Nitrogen Oxides |
| OBD | = | On-Board Diagnostics |
| PCA | = | Principal Component Analysis |
| PEMS | = | Portable Emissions Measurement System |
| PSO | = | Particle Swarm Optimization |
| RNN | = | Recurrent Neural Network |
| RSM | = | Response Surface Methodology |
| SVM | = | Support Vector Machine |
| SGA | = | Stochastic Gradient Algorithm |
| TDNN | = | Time Delay Neural Network |
| WHSC | = | World Harmonized Steady Cycle |
| WHTC | = | World Harmonized Transient Cycle |
| WNN | = | Wavelet Neural Network |
Disclosure statement
No potential conflict of interest was reported by the author(s).
Data availability statement
The datasets generated during and/or analyzed during the current study are available from the corresponding author on reasonable request.
Additional information
Funding
Notes on contributors
Jianxiong Liao
Jianxiong Liao is a master’s degree student at Wuhan University of Technology, Wuhan, China. His research focuses on emission prediction and control. E-mail: [email protected].
Jie Hu
Jie Hu is a professor at Wuhan University of Technology, Wuhan, China. His research focuses on big data prediction, emission control and diagnosis. E-mail: [email protected], [email protected].
Peng Chen
Peng Chen is a master’s degree student at Wuhan University of Technology, Wuhan, China. His research focuses on emission aftertreatment design and control. E-mail: [email protected].
Hanming Wu
Hanming Wu is a researcher at National Engineering Laboratory for Mobile Source Emission Control Technology, Tianjin, China. His research focuses on catalyst design and engine emission control. E-mail: [email protected]
Maoxuan Wang
Maoxuan Wang is a researcher at National Engineering Laboratory for Mobile Source Emission Control Technology, Tianjin, China. His research focuses on emission aftertreatment control and optimization. E-mail: [email protected]
Yuankai Shao
Yuankai Shao is a researcher at National Engineering Laboratory for Mobile Source Emission Control Technology, Tianjin, China. His research focuses on catalyst design and optimization. E-mail: [email protected]
Zhenguo Li
Zhenguo Li is a researcher at National Engineering Laboratory for Mobile Source Emission Control Technology, Tianjin, China. His research focuses on mobile source pollution control. E-mail: [email protected].