مدلسازی و کاهش تولید NOx در بخارساز احتراق غوطه ور با استفاده از سیستم استنتاج فازی

نوع مقاله : مقاله شیمی

نویسندگان

1 دانشجوی کارشناسی ارشد مهندسی‌شیمی، دانشکده شیمی و مهندسی شیمی، دانشگاه تحصیلات تکمیلی صنعتی و فناوری پیشرفته، کرمان، ایران

2 استادیار، گروه مهندسی‌شیمی، دانشکده شیمی و مهندسی شیمی، دانشگاه تحصیلات تکمیلی صنعتی و فناوری پیشرفته، کرمان، ایران

3 استادیار، گروه مهندسی شیمی، دانشکده شیمی و مهندسی شیمی، دانشگاه تحصیلات تکمیلی صنعتی و فناوری پیشرفته، کرمان، ایران

چکیده

بخارسازهای احتراق غوطه ور از جمله تجهیزات صنعتی هستند که به میزان بسیار زیادی اکسیدهای نیتروژن (NOx) تولید می کنند. این تجهیزات در واقع مبدل های حرارتی هستند که در پایانه‌های گاز طبیعی مایع (LNG) برای تبخیر گاز طبیعی مایع و تبدیل آن به گاز استفاده می شوند. از آنجا که مطالعات پیشین نشان داده که شرایط عملیاتی این تجهیز بر میزان تولید NOx در آن موثر است، در این پژوهش از ابزارهای هوش مصنوعی جهت مدل سازی و سپس بهینه سازی انتشار NOx در این تجهیزات استفاده شد. به همین منظور تعداد 63 داده آزمایشگاهی از پژوهش های پیشین محققان استخراج شده و سپس از ترکیبی از سیستم استنتاج فازی عصبی تطبیقی و الگوریتم ژنتیک جهت مدل سازی داده ها استفاده شد. در سیستم توسعه یافته، غلظت اکسیژن، دما، غلظت آب اکسیژنه و pH محلول، به عنوان پارامترهای ورودی به مدل و درصد کاهش NOx بعنوان خروجی در نظر گرفته شد. تحلیل های آماری مدل ساخته شده نشان داد که این مدل با ضریب همبستگی 9714/0، میانگین مربعات خطا 0938/1 ، میانگین درصد خطای مطلق 9713/4 و ماکسیمم درصد خطای مطلق 2144/13 از دقت مناسبی در تخمین مقدار کاهش NOx برخوردار است. در گام بعد و پس از توسعه مدل، از الگوریتم ژنتیک و مدل ساخته شده برای بهینه سازی شرایط عملیاتی با کمترین نرخ انتشار NOx استفاده شد. نتایج این بخش از پژوهش نیز نشان داد که در صورت بهینه سازی شرایط عملیاتی، امکان کاهش میزان NOx منتشر شده تا 24/37 درصد وجود دارد.

کلیدواژه‌ها

موضوعات


عنوان مقاله [English]

Modeling and reduction of NOx production in submerged combustion vaporizer using fuzzy inference system

نویسندگان [English]

  • Hanieh Fani Maleki 1
  • Amir Ehsan Pheili Monfared 2
  • Mahmoud Rahmati 3
1 Master's student in Chemical Engineering, Department of Chemical Engineering, Graduate University of Advanced Technology, Kerman, Iran
2 Assistant Professor, Department of Chemical Engineering, Graduate University of Advanced Technology, Kerman, Iran
3 Assistant Professor, Department of Chemical Engineering, Graduate University of Advanced Technology, Kerman, Iran
چکیده [English]

Submerged combustion vaporizers are one of the industrial equipments that produce a large amount of nitrogen oxides (NOx). These equipments are actually heat exchangers that are used in liquefied natural gas (LNG) terminals to evaporate liquefied natural gas and convert it into gas. Since previous studies have shown that the operating conditions of this equipment are effective on the amount of NOx production in it, artificial intelligence tools were used in this research to model and then optimize NOx emission in this equipment. For this purpose, 63 laboratory data were extracted from the researchers' previous researches, and then a combination of adaptive neural fuzzy inference system and genetic algorithm was used to model the data. In the developed system, oxygen concentration, temperature, water-oxygen concentration and solution pH were considered as input parameters to the model and NOx reduction percentage as output. The statistical analysis of the built model showed that this model with correlation coefficient of 0.9714, mean square error of 1.0938, average absolute error percentage of 4.9713 and maximum absolute error percentage of 13.2144 has a good accuracy in estimating the amount of NOx reduction. In the next step after the development of the model, the genetic algorithm and the built model were used to optimize the operating conditions with the lowest NOx emission rate. The results of this part of the research also showed that if the operating conditions are optimized, it is possible to reduce the amount of NOx released up to 37.24%

کلیدواژه‌ها [English]

  • Artificial intelligence
  • genetic algorithm
  • adaptive neural fuzzy inference system
  • air pollution
  • modeling
  • nitrogen oxides
]1] Robert J Blaszczak. "Nitrogen Oxides(NOx), Why And How They Are Controlled:. EPA-456/F-99-006R " 1999.
[2] Jeongeun Son, Huicheon Yang, Geonjoong Kim, Sungwon Hwang, and Hyunseok You. "Technology development for the reduction of NOx in flue gas from a burner-type vaporizer and its application". Korean J. Chem. Eng., vol. 34, no. 6, (2017):1619-1629.
[3] Young Sun Mok and Heon Ju Lee. "Removal of sulfur dioxide and nitrogen oxides by using ozone injection and absorption-reduction technique". Fuel Process Technol, vol. 87, no. 7, (2006):591-597.
[4] Xveyoung Zhang, Rui Wang, Hongjian Zhu, and Yongliang Chen. "Performance of NOx capture with Dawson polyoxometalate H6P2W18O62·28H2O". Chem Eng J, vol. 400, 2020.
[5] Dongpeng Yue, Qing Chang, Lei Liu, Weng Zhang, Shaosho Chen, and Zhijun li Zhijun Li. "Reduce NOx Emissions by Adsorber-Reduction Catalyst on Lean Burn Engine". TELKOMNIKA (Telecommunication Comput Electron Control, vol. 11, no. 3, (2013):481-488.
[6] Sang Hee Jo. "A study on additives to improve electron beam technology for NOx and SO2 reduction".Radiat Phys Chem, vol. 183, 2021.
[7] Shimizu atsushi, Ohno hirokazu ,Koizumi yosuke, Maeda kazuyuki, and Yamanishi day. "Development of a Nitrogen-enrichment/Humidification Membrane System for NOx Emission Reduction in a Marine Diesel Engine". Mar Eng, vol. 48, no. 3, 2013.
[8] Souvik Bhattacharyya and Randip K. Das. "Catalytic control of automotive NOx: A review". International Journal of Energy Research, vol. 23, no. 4. 1999.
[9] Kemal Masera and Abul K Hossain. "Modified selective non-catalytic reduction system to reduce NOx gas emission in biodiesel powered engines". Fuel, vol. 298, 2021.
[10] Igor S Anufriev, Evgeny P Kopyev, Ivan S. Sadkin, and Mariia A Mukhina. "NOx reduction by steam injection method during liquid fuel and waste burning". Process Saf Environ Prot, vol. 152 (2021):240-248.
[11] Enso Ikonen, Kaddour Najim, and Urpo Kortela. "Neuro-fuzzy modelling of power plant flue-gas emissions". Eng Appl Artif Intell, vol. 13, no. 6, (2000):705-717.
[12] J. Mohammadhassani, S. Khalilarya, M. Solimanpur, and A. Dadvand. "Prediction of NOx emissions from a direct injection diesel engine using artificial neural network". Model Simul Eng, Vol. 2012.
[13] Michael Fischer. "Transient NOx estimation using artificial neural networks". in IFAC Proceedings Volumes (IFAC-PapersOnline), vol. 7, no. PART 1, 2013.
[14] Hamid Taghavifar, Hadi Taghavifar, Aref Mardani, and Arash Mohebbi. "Modeling the impact of in-cylinder combustion parameters of di engines on soot and NOx emissions at rated EGR levels using ANN approach". Energy Convers. Manag., vol. 87, 2014.
[15] Taizo Anan, Hiroyuki Higuchi, and Naoki Hamada. "New artificial intelligence technology improving fuel efficiency and reducing CO2 emissions of ships through use of operational big data". Fujitsu Sci Tech J, vol. 53, no. 6, 2017.
[16] Yeonju Shin, Ziehyun Kim, Jihye. Yu, Geonjung. Kim, and Sungwon. Hwang. "Development of NOx reduction system utilizing artificial neural network (ANN) and genetic algorithm (GA) ". J Clean Prod., vol. 232, 2019.
[17] Vinicius Y Valera, Milene C Codolo, and Tiago D Martins. "Artificial neural network for prediction of SO2 removal and volumetric mass transfer coefficient in spray tower". Chem. Eng. Res. Des., vol. 170, 2021.
[18] Farhoud, Dariush, and Haniyeh Purkelher. "Artificial intelligence and genetics". Quarterly Journal of Laboratory and Diagnosis,50,(1390):70-73 (inPersian).
[19] Obodeh O. and Ajuwa C. I. "Evaluation of artificial neural network performance in predicting diesel engine Nox emissions". Res J Appl Sci Eng Technol. vol. 1, no. 3, 2009.
[20] Ivan Arsie, Dario Marra, Cesare Pianese, and Marco Sorrentino. "Real-time estimation of engine nox emissions via recurrent neural networks". in IFAC Proceedings Volumes (IFAC-PapersOnline), vol. 43, no. 7, 2010.
[21] Jessica O. B. Lira, Humberto G. Riella, Natan Padoin, and Cintia Soares. "Computational fluid dynamics (CFD), artificial neural network (ANN) and genetic algorithm (GA) as a hybrid method for the analysis and optimization of micro-photocatalytic reactors: NOx abatement as a case study" Chem Eng J, vol. 431, 2022.
[22] Ghaemi, Zainab, Mohammad Talei, Mehdi Farnaghi and Qasim Javadi. "Prediction of air pollution in Tehran using the combination of fuzzy-adaptive neural network and principal component analysis". Iran's remote sensing and GIS, 9, 3,(1396):21-39 (inPersian).
[23] Chao Qi, Wen Wang, Bojie Wang, Yiwu Kuang, and Jiawei Xu. "Performance analysis of submerged combustion vaporizer". J Nat Gas Sci Eng, vol. 31 (2016): 313–319.
[24] Golshani, Alireza, and Mohammadreza Quaidi. "Fuzzy method in research, a bridge between quantitative and qualitative research methods". Psychological methods and models, 4, 14 (1392):45-65 (inPersian).
[25] L. A. Zadeh. "Outline of a New Approach to the Analysis of Complex Systems and Decision Processes". IEEE Trans Syst Man Cybern, vol. SMC-3, no. 1 (1973): 28–44.
[26] P. C. Nayak, K. P. Sudheer, D. M. Rangan, and K. S. Ramasastri. "A neuro-fuzzy computing technique for modeling hydrological time series".           Journal of hydrology, vol. 291 (2004): 52–66.
[27] J.-S. Roger Jang. "ANFIS : Adap tive-Network-Based Fuzzy Inference System". IEEE Transactions On Systems, Man, And Cybernetics, vol. 23, no. 3 (1993): 665­-685.
[28] Waheed Ahmad. "Thyroid Diseases Forecasting Using a Hybrid Decision Support System Based on ANFIS, k-NN and Information Gain Method". J. Appl Environ Biol Sci, vol. 7, no. 10 (2017): 78–85.
[29] Shams Javi, Mohammad. Implementation and solution of practical problems with genetic algorithm. Aria project,1390 (inPersian).