|
|
基于二型模糊神经网络的NOx排放预测
|
Abstract:
为提高柴油机NOx排放预测精度及减少试验成本，本文提出了二型模糊神经网络(Type-2 Fuzzy Neural Networks, T2FNNs)的柴油机NOx排放预测方法。首先利用随机森林算法进行了输入变量的重要性分析并约简优化了输入变量，然后对本文提出T2FNNs预测模型的参数分别采用梯度下降法和递推最小二乘进行训练寻优，基于寻优后的最优预测模型进行了训练和验证，并取得了较好的预测效果。在训练集和验证集上NOx的回归决定系数(R2)分别为0.985和0.962。最后对T2FNNs预测模型进行了泛化性测试，并与其他神经网络预测模型进行了对比。结果表明在测试集上其R2值为0.961，相较于训练集和验证集仅分别下降了2.4%和0.1%，说明T2FNNs预测模型具有极强的泛化能力。在与其他预测模型的对比中，T2FNNs预测模型也表现出了更好的性能特性。
To improve the accuracy of diesel engine NOx emission prediction and reduce the cost of testing, a Type-2 Fuzzy Neural Networks (T2FNNs) method for predicting diesel engine emission characteristics was proposed. Firstly, the importance analysis of input variables was conducted using the random forest algorithm, and the input variables were reduced and optimized. Then, the parameters of the T2FNNs prediction model proposed in this paper were trained and optimized using gradient descent method and recursive least squares. Based on the optimized optimal prediction model, training and validation were conducted, and good prediction results were achieved. The regression determination coefficients (R2) of NOx on the training and validation sets are 0.985 and 0.962, respectively. Finally, a generalization test was conducted on the T2FNNs prediction model, and it was compared with other neural network prediction models. The results showed that the R2 value on the test set was 0.961, which decreased by only 2.4% and 0.1% compared to the training and validation sets, respectively, indicating that the T2FNNs prediction model has strong generalization ability. In comparison with other prediction models, the T2FNNs prediction model also showed better performance characteristics.
| [1] | E, J., Zuo, W., Gao, J., Peng, Q., Zhang, Z. and Hieu, P.M. (2016) Effect Analysis on Pressure Drop of the Continuous Regeneration-Diesel Particulate Filter Based on NO2 Assisted Regeneration. Applied Thermal Engineering, 100, 356-366. https://doi.org/10.1016/j.applthermaleng.2016.02.031 |
| [2] | Meng, Z., Li, J., Fang, J., Tan, J., Qin, Y., Jiang, Y., et al. (2020) Experimental Study on Regeneration Performance and Particle Emission Characteristics of DPF with Different Inlet Transition Sections Lengths. Fuel, 262, Article ID: 116487. https://doi.org/10.1016/j.fuel.2019.116487 |
| [3] | Fang, J., Meng, Z., Li, J., Pu, Y., Du, Y., Li, J., et al. (2017) The Influence of Ash on Soot Deposition and Regeneration Processes in Diesel Particular Filter. Applied Thermal Engineering, 124, 633-640. https://doi.org/10.1016/j.applthermaleng.2017.06.076 |
| [4] | 王志坚, 王晓华, 郭圣刚, 等. 满足重型柴油机超低排放法规的后处理技术现状与展望[J]. 环境工程, 2020, 38(9): 159-167. |
| [5] | Hu, S., Deng, B., Wu, D. and Hou, K. (2021) Energy Flow Behavior and Emission Reduction of a Turbo-Charging and EGR Non-Road Diesel Engine Equipped with DOC and DPF under NRTC (Non-Road Transient Cycle). Fuel, 305, Article ID: 121571. https://doi.org/10.1016/j.fuel.2021.121571 |
| [6] | Xu, G., Shan, W., Yu, Y., et al. (2021) Advances in Emission Control of Diesel Vehicles in China. Journal of Environmental Sciences, 123, 15-29. |
| [7] | Joshi, A. (2022) Review of Vehicle Engine Efficiency and Emissions. SAE International Journal of Advances and Current Practices in Mobility, 4, 1704-1733. https://doi.org/10.4271/2022-01-0540 |
| [8] | Veza, I., Afzal, A., Mujtaba, M.A., Tuan Hoang, A., Balasubramanian, D., Sekar, M., et al. (2022) Review of Artificial Neural Networks for Gasoline, Diesel and Homogeneous Charge Compression Ignition Engine. Alexandria Engineering Journal, 61, 8363-8391. https://doi.org/10.1016/j.aej.2022.01.072 |
| [9] | 胡松, 王贺春, 王银燕, 等. 多次喷射柴油机实时预测模型参数映射关系辨识[J]. 内燃机学报, 2022, 40(2): 153-161. |
| [10] | 王天田, 颜伏伍, 胡杰, 等. 利用NOx传感器的NH3交叉敏感实现SCR系统闭环控制[J]. 内燃机学报, 2015, 33(2): 178-185. |
| [11] | Yin, X., Li, Z., Yang, B., Sun, T., Wang, Y. and Zeng, K. (2021) Experimental Study of the Combustion Characteristics Prediction Model for a Sensor-Less Closed-Loop Control in a Heavy-Duty NG Engine. Fuel, 300, Article ID: 120945. https://doi.org/10.1016/j.fuel.2021.120945 |
| [12] | Shin, S., Lee, Y., Lee, Y., Park, J., Kim, M., Lee, S., et al. (2022) Designing a Steady-State Experimental Dataset for Predicting Transient NOx Emissions of Diesel Engines via Deep Learning. Expert Systems with Applications, 198, Article ID: 116919. https://doi.org/10.1016/j.eswa.2022.116919 |
| [13] | Fu, J., Yang, R., Li, X., Sun, X., Li, Y., Liu, Z., et al. (2022) Application of Artificial Neural Network to Forecast Engine Performance and Emissions of a Spark Ignition Engine. Applied Thermal Engineering, 201, Article ID: 117749. https://doi.org/10.1016/j.applthermaleng.2021.117749 |
| [14] | 王彦岩, 杨建国, 宋宝玉. 小波结合模糊聚类和神经网络的汽油机爆震诊断方法[J]. 内燃机学报, 2010, 28(2): 155-159. |
| [15] | 谢丽萍, 卢炽华, 刘志恩, 等. 基于脑功能网络的内燃机汽车声品质评价模型[J]. 内燃机学报, 2022, 40(4): 378-383. |
| [16] | 丁伟奇, 王金秋, 胡宗杰, 等. 基于离子电流与LSTM神经网络的汽油机早燃判断[J]. 内燃机学报, 2022, 40(2): 171-178. |
| [17] | Rahimi molkdaragh, R., Jafarmadar, S., Khalilaria, S. and Soukht Saraee, H. (2018) Prediction of the Performance and Exhaust Emissions of a Compression Ignition Engine Using a Wavelet Neural Network with a Stochastic Gradient Algorithm. Energy, 142, 1128-1138. https://doi.org/10.1016/j.energy.2017.09.006 |
| [18] | Aliramezani, M., Norouzi, A. and Koch, C.R. (2020) Support Vector Machine for a Diesel Engine Performance and NOx Emission Control-Oriented Model. IFAC-PapersOnLine, 53, 13976-13981. https://doi.org/10.1016/j.ifacol.2020.12.916 |
| [19] | Castresana, J., Gabiña, G., Martin, L. and Uriondo, Z. (2021) Comparative Performance and Emissions Assessments of a Single-Cylinder Diesel Engine Using Artificial Neural Network and Thermodynamic Simulation. Applied Thermal Engineering, 185, Article ID: 116343. https://doi.org/10.1016/j.applthermaleng.2020.116343 |
| [20] | Zhang, H., Ji, Y., Huang, W. and Liu, L. (2018) Sitcom-Star-Based Clothing Retrieval for Video Advertising: A Deep Learning Framework. Neural Computing and Applications, 31, 7361-7380. https://doi.org/10.1007/s00521-018-3579-x |
| [21] | Zhang, H., Sun, Y., Liu, L., Wang, X., Li, L. and Liu, W. (2018) Clothingout: A Category-Supervised GAN Model for Clothing Segmentation and Retrieval. Neural Computing and Applications, 32, 4519-4530. https://doi.org/10.1007/s00521-018-3691-y |
| [22] | Castillo, O., Castro, J.R., Melin, P. and Rodriguez-Diaz, A. (2013) Universal Approximation of a Class of Interval Type-2 Fuzzy Neural Networks in Nonlinear Identification. Advances in Fuzzy Systems, 2013, Article ID: 136214. https://doi.org/10.1155/2013/136214 |
| [23] | Castro, J.R., Castillo, O., Melin, P. and Rodríguez-Díaz, A. (2009) A Hybrid Learning Algorithm for a Class of Interval Type-2 Fuzzy Neural Networks. Information Sciences, 179, 2175-2193. https://doi.org/10.1016/j.ins.2008.10.016 |
| [24] | Castillo, O., Castro, J.R., Melin, P. and Rodriguez-Diaz, A. (2013) Application of Interval Type-2 Fuzzy Neural Networks in Non-Linear Identification and Time Series Prediction. Soft Computing, 18, 1213-1224. https://doi.org/10.1007/s00500-013-1139-y |
| [25] | Kayacan, E., Kayacan, E. and Ahmadieh Khanesar, M. (2015) Identification of Nonlinear Dynamic Systems Using Type-2 Fuzzy Neural Networks—A Novel Learning Algorithm and a Comparative Study. IEEE Transactions on Industrial Electronics, 62, 1716-1724. https://doi.org/10.1109/tie.2014.2345353 |
| [26] | Lin, C., Le, T. and Huynh, T. (2018) Self-Evolving Function-Link Interval Type-2 Fuzzy Neural Network for Nonlinear System Identification and Control. Neurocomputing, 275, 2239-2250. https://doi.org/10.1016/j.neucom.2017.11.009 |
| [27] | Han, M., Zhong, K., Qiu, T. and Han, B. (2019) Interval Type-2 Fuzzy Neural Networks for Chaotic Time Series Prediction: A Concise Overview. IEEE Transactions on Cybernetics, 49, 2720-2731. https://doi.org/10.1109/tcyb.2018.2834356 |
| [28] | Mohammadzadeh, A. and Kayacan, E. (2019) A Non-Singleton Type-2 Fuzzy Neural Network with Adaptive Secondary Membership for High Dimensional Applications. Neurocomputing, 338, 63-71. https://doi.org/10.1016/j.neucom.2019.01.095 |
| [29] | Gregorutti, B., Michel, B. and Saint-Pierre, P. (2016) Correlation and Variable Importance in Random Forests. Statistics and Computing, 27, 659-678. https://doi.org/10.1007/s11222-016-9646-1 |
| [30] | Genuer, R., Poggi, J. and Tuleau-Malot, C. (2010) Variable Selection Using Random Forests. Pattern Recognition Letters, 31, 2225-2236. https://doi.org/10.1016/j.patrec.2010.03.014 |
