Neural Network-Based Prediction of NH3 Leakage from SCR Systems for Diesel Engines

다국어 초록 (Multilingual Abstract)

In selective catalytic reduction (SCR) systems, the urea injection control strategy is central to the control of NO x emissions.
When urea is over-injected, ammonia leakage will occur downstream of the SCR. A neural network-based NH 3 leakage prediction model for diesel engine SCR systems is proposed in order that the dosing control unit (DCU) can reduce the corresponding urea injection volume according to the NH 3 leakage when calculating the urea injection volume. Back propagation (BP) neural network model and gated recurrent unit (GRU) model are developed respectively by code compilation software to predict the NH 3 leakage. The genetic algorithm (GA) is used to fi nd the optimal parameters of the two diff erent models. Bench tests are conducted to evaluate the model accuracy. Under historical test data, the root mean square errors of the fi nal GA-BP and GA-GRU models are 3.142 ppm and 2.378 ppm, respectively. The percentage of cumulative NH 3 leakage prediction error of GA-BP and GA-GRU are 4.808% and 3.745%, respectively. The results show that the method of using neural network for NH 3 leakage prediction is feasible, and GA-GRU model is better than GA-BP model in predicting NH 3 leakage. This provides the basis for developing DCU to reduce NH 3 leakage.

참고문헌 (Reference)

1 Twigg, M. V., "urea-scr technology for denox after treatment of diesel exhausts" 59 (59): 221-232, 2015

2 Zhang, Y., "The prediction of spark-ignition engine performance and emissions based on the svr algorithm" 10 (10): 15-, 2022

3 Resitoglu, I. A., "The eff ects of fe2o3 based doc and scr catalyst on the exhaust emissions of diesel engines" 262 : 8-, 2020

4 Chen, Y. J., "Study of reducing deposits formation in the urea-scr system : Mechanism of urea decomposition and assessment of infl uential parameters" 164 : 311-323, 2020

5 Pla, B., "Simultaneous nox and nh3 slip prediction in a scr catalyst under real driving conditions including potential urea injection failures" 23 (23): 1213-1225, 2022

6 Wei, L., "Simultaneous estimation of ammonia injection rate and state of diesel urea-scr system based on high gain observer" 126 : 679-690, 2022

7 Tang, Y. D., "Question detection from acoustic features using recurrent neural network with gated recurrent unit" 6125-6129, 2016

8 Shin, S., "Predicting transient diesel engine nox emissions using time-series data preprocessing with deep-learning models" 235 (235): 3170-3184, 2021

9 Kang, W., "Pm and nox reduction characteristics of lnt/dpf plus scr/dpf hybrid system" 143 : 439-447, 2018

10 Wang, W., "Optimization of thermal performance of the parabolic trough solar collector systems based on ga-bp neural network model" 14 (14): 819-830, 2017

11 Pla, B., "Nox sensor cross sensitivity model and simultaneous prediction of nox and nh3 slip from automotive catalytic converters under real driving conditions" 22 (22): 3209-3218, 2021

12 Cho, C., "Nitric oxide and nitrous oxide from selective oxidation in a vanadium-based catalytic diesel after-treatment system" 46 (46): 15816-15823, 2022

13 Pla, B., "Model-based simultaneous diagnosis of ammonia injection failure and catalyst ageing in denox engine after-treatment systems" 343 : 13-, 2023

14 Zheng, T. X., "Luenberger-sliding mode observer based backstepping control for the scr system in a diesel engine" 12 (12): 19-, 2019

15 Wardana, M. K. A., "Investigation of ammonia homogenization and nox reduction quantity by remodeling urea injector shapes in heavy-duty diesel engines" 323 : 17-, 2022

16 Kulkarni, A. P., "Insights on the morphology of air-assisted breakup of urea-water-solution sprays for varying surface tension" 133 : 11-, 2020

17 Jiang, K., "Hydrothermal aging factor estimation for two-cell diesel-engine scr systems via a dual time-scale unscented kalman fi lter" 67 (67): 442-450, 2020

18 Liu, Y. S., "Experimental study on solid scr technology to reduce nox emissions from diesel engines" 8 : 151106-151115, 2020

19 Jia, H. K., "Effects of scrinjection system parameters on uws atomization and mixing characteristics at low exhaust temperature" 46 (46): 13-, 2021

20 Farhan, S. M., "Eff ect of post-injection strategies on regulated and unregulated harmful emissions from a heavy-duty diesel engine" 23 (23): 169-179, 2022

21 Strots, V. O., "Deposit Formation in Urea-SCR Systems" 2 (2): 283-289, 2009

22 Khalife, E., "Comparative of various bioinspired meta-heuristic optimization algorithms in performance and emissions of diesel engine fuelled with b5 containing water and cerium oxide additive blends" 46 (46): 21266-21280, 2022

23 Bonfi ls, A., "Closed-loop control of a scr system using a nox sensor cross-sensitive to nh3" 24 (24): 368-378, 2014

24 신달호 ; 조성인 ; 김형준 ; 박수한, "Application of physical model test-based long short-term memory algorithm as a virtual sensor for nitrogen oxide prediction in diesel engines" 24 (24): 585-593, 2023

25 Owoyele, O., "Application of deep artifi cial neural networks to multidimensional fl amelet libraries and spray fl ames" 21 (21): 151-168, 2020

26 Kozina, A., "Analysis of methods towards reduction of harmful pollutants from diesel engines" 262 : 20-, 2020

27 Jiang, K., "An extended kalman filter for input estimations in diesel-engine selective catalytic reduction applications" 171 : 569-575, 2016

28 Zheng, B. W., "An ann-pso-based method for optimizing agricultural tractors in fi eld operation for emission reduction" 12 (12): 16-, 2022

29 Wang, X., "A nox emission model incorporating temperature for heavy-duty diesel vehicles with urea-scr systems based on fi eld operating modes" 10 (10): 17-, 2019

30 Yu, Y., "A novel deep learning approach to predict the instantaneous nox emissions from diesel engine" 9 : 11002-11013, 2021

31 Savci, I. H., "A methodology to assess mixer performance for selective catalyst reduction application in hot air gas burner" 61 (61): 6621-6633, 2022