Recycling technology has the characteristics of high efficiency, recyclability and reuse. At the same time, it can be widely used in industrial production as an environment-friendly technology. At present, the waste gas treatment methods adopted in China mainly include mechanical (heat treatment) or chemical methods. These methods do great harm to the environment. In order to improve the environmental protection of diesel engines, this paper intends to study the application of machine learning in exhaust gas recirculation technology, and propose the method of exhaust gas recirculation technology. This paper mainly uses the experimental method of EGR scheme design and changes the variables to compare the data difference to realize the research on the influence of internal EGR on emission performance and combustion characteristics. The experimental results show that the NOx emissions of the internal EGR scheme are lower than 10/g•h-1 at 2200r/min and 10% load conditions. The internal exhaust gas recirculation technology has great potential to improve the harmful exhaust gas and total fuel emissions of diesel engines.

Vempaty Saini. Diesel Engine Exhaust Gas Recirculation Technology Based on Machine Learning. Kinetic Mechanical Engineering (2021), Vol. 2, Issue 4: 40-48. https://doi.org/10.38007/KME.2021.020405.

[1] Anzheng Huang, Binbin Bao, Nanyang Zhao, Jinjie Zhang, Zhinong Jiang, Zhiwei Mao: Decoupling Identification Method of Continuous Working Conditions of Diesel Engines Based on a Graph Self-Attention Network. IEEE Access 10: 36649-36661 ( 2021). 

[2] Daniel Jörss, Bert Henrik Herrmann, Christian Fink: Modeling the Operating Behavior of an Industrial Diesel Engine used as an Electrical Power Generator. Simul. Notes Eur. 32(2): 55-61 ( 2021). https://doi.org/10.11128/sne.32.tn.10601

[3] Daniel Bergmann, Karsten Harder, Jens Niemeyer, Knut Graichen: Nonlinear MPC of a Heavy-Duty Diesel Engine With Learning Gaussian Process Regression. IEEE Trans. Control. Syst. Technol. 30(1): 113-129 ( 2021). https://doi.org/10.1109/TCST.2021.3054650

[4] Mehmet Ilter Ozmen, Abdurrahim Yilmaz, Cemal Baykara, Osman Azmi Ozsoysal: Modelling Fuel Consumption and NOₓ Emission of a Medium Duty Truck Diesel Engine with Comparative Time-Series Methods. IEEE Access 9: 81202-81209 (2021). https://doi.org/10.1109/ACCESS.2021.3082030

[5] Chakib Ben Njima, Anouar Benamor, Hassani Messaoud: A New Robust Adaptive Sliding Mode Control for Discrete-Time Systems with Time-Varying State Delay: Application to Diesel Engine Control. Int. J. Serv. Sci. Manag. Eng. Technol. 12(2): 132-153 (2021). https://doi.org/10.4018/IJSSMET.2021030108

[6] Seong-Man Choi, Jeong Seok Lee, Rho Shin Myong, Ha Na Jo, Jae Won Kim: Schlieren Visualization of Micro Gas Turbine Exhaust Plume with Different Shapes of Nozzle. J. Vis. 23(4): 565-576 (2020). https://doi.org/10.1007/s12650-020-00648-9

[7] Akira Mizobuchi, Takeshi Hamada, Atsuyoshi Tashima, Keita Horimoto, Tohru Ishida: Polishing Performance of a Recycled Grinding Wheel Using Grinding Wheel Scraps for the Wet Polishing of Stainless-Steel Sheets. Int. J. Autom. Technol. 16(1): 60-70 ( 2021). 

[8] Udaya Shankar Santhana Krishnan, Kalpana Palanisamy: Recycled Integrated Circuit Detection Using Reliability Analysis and Machine Learning Algorithms. IET Comput. Digit. Tech. 15(1): 20-35 (2021). https://doi.org/10.1049/cdt2.12005

[9] Dmitry V. Vinogradov: Algebraic Machine Learning: Emphasis on Efficiency. Autom. Remote. Control. 83(6): 831-846 ( 2021). https://doi.org/10.1134/S0005117922060029

[10] Abdallah M. H. Abbas, Khairil Imran Bin Ghauth, Choo-Yee Ting: User Experience Design Using Machine Learning: A Systematic Review. IEEE Access 10: 51501-51514 ( 2021). 

[11] Abdallah Abdellatif, Hamdan Abdellatef, Jeevan Kanesan, Chee-Onn Chow, Joon Huang Chuah, Hassan Muwafaq Gheni: An Effective Heart Disease Detection and Severity Level Classification Model Using Machine Learning and Hyperparameter Optimization Methods. IEEE Access 10: 79974-79985 ( 2021). 

[12] Mohamed Saleh Abouelyazid, Sherif Hammouda, Yehea Ismail: Fast and Accurate Machine Learning Compact Models for Interconnect Parasitic Capacitances Considering Systematic Process Variations. IEEE Access 10: 7533-7553 ( 2021). 

[13] Murad A. Abusubaih, Sundous Khamayseh: Performance of Machine Learning-Based Techniques for Spectrum Sensing in Mobile Cognitive Radio Networks. IEEE Access 10: 1410-1418 ( 2021). 

[14] Muhammad Adel, Sabah M. Ahmed, Mohamed Fanni: End-Effector Position Estimation and Control of a Flexible Interconnected Industrial Manipulator Using Machine Learning. IEEE Access 10: 30465-30483 ( 2021). 

[15] Fawad Ahmad, Waqas bin Abbas, Salman Khalid, Farhan Khalid, Muhammad Ibrar Khan, Fahad Aldosari: Performance Enhancement of mmWave MIMO Systems Using Machine Learning. IEEE Access 10: 73068-73078 ( 2021). 

[16] Ghulab Nabi Ahmad, Hira Fatima, Shafi Ullah, Abdelaziz Salah Saidi, Asghar Imdadullah: Efficient Medical Diagnosis of Human Heart Diseases Using Machine Learning Techniques With and Without GridSearchCV. IEEE Access 10: 80151-80173 ( 2021). 

[17] Dina Bousdar Ahmed, Estefania Munoz Diaz: Survey of Machine Learning Methods Applied to Urban Mobility. IEEE Access 10: 30349-30366 ( 2021). 

[18] Usama Ahmed, Ghassan F. Issa, Muhammad Adnan Khan, Shabib Aftab, Muhammad Farhan Khan, Raed A. Said, Taher M. Ghazal, Munir Ahmad: Prediction of Diabetes Empowered With Fused Machine Learning. IEEE Access 10: 8529-8538 ( 2021).