تعهد نامه

نوع مقاله : مقالات پژوهشى اصیل کمی و کیفی

نویسندگان

1 دانشجوی کارشناسی ارشد مهندسی محیط زیست دانشکده منابع طبیعی، دانشگاه یزد، ایران.

2 دانشیار گروه مهندسی محیط زیست، دانشکده منابع طبیعی، دانشگاه یزد، ایران.

3 استادیار، گروه علوم کامپیوتر، دانشکده ریاضی و علوم کامپیوتر، دانشگاه حکیم سبزواری، ایران.

چکیده

چکیده
زمینه و هدف: مدل­سازی گردو‌غبار می­تواند به عنوان یک ابزار مناسب برای پیش­بینی گردو‌غبار صنایع در آینده و تعیین استراتژی­های کنترل انتشار آلاینده­ها تلقی شود. در این مطالعه از شبکه­های عصبی پرسپترون (MLP) و پایه شعاعی (RBF) به عنوان ابزاری برای پیش­بینی گردو‌غبار خروجی از دودکش اصلی کارخانه سیمان سبزوار واقع در استان خراسان رضوی استفاده شد.
مواد و روش‌ها: در محدوده مطالعاتی مورد نظر، ابتدا میزان غلظت گردو‌غبار خروجی از دودکش اصلی کارخانه سیمان به وسیله اندازه­گیری­های میدانی به‌دست آمد. سپس با به‌کار­گیری پارامتر­های خط تولید (درجه حرارت، سرعت گاز خروجی، ولتاژ، سوخت، مواد خام و مدت زمان نمونه­برداری)، به عنوان داده­های ورودی به شبکه­های عصبی، جهت پیش­بینی میزان غلظت گردو‌غبار استفاده شد. مقادیر حاصل از اجرای مدل­ها، با نتایج اندازه­گیری­های میدانی به‌عنوان انتخاب مدل برتر، مورد مقایسه قرار گرفت.
یافته­ها: دربررسی نمودار­ها و پارامتر­های آماری، مقادیر میانگین مربعات خطا برای دو مدل شبکه­های عصبی پرسپترون و پایه شعاعی به‌ترتیب برابر 1/787 و 21/263 و مقادیر ضریب همبستگی به‌ترتیب برابر 0/99693 و 0/95811 بود که نشانگر خطای کمتر و همبستگی بیشتر مدل شبکه­های عصبی پرسپترون نسبت به مدل پایه شعاعی در پیش­بینی میزان غلظت گردو‌غبار بود.
نتیجه­گیری: به دلیل قابلیت بالای شبکه عصبی پرسپترون در پیش­بینی میزان غلظت گردو‌غبار، این مدل می­تواند یک راه‌حل مناسب و سریع در پیش­بینی میزان گردو‌غبار صنایع باشد.
نوع مقاله:مقاله پژوهشی
کلید واژهها: کارخانه سیمان، گردو‌غبار، شبکه­های عصبی مصنوعی، آلودگی هوا

کلیدواژه‌ها

عنوان مقاله [English]

Estimation of Artificial Neural Networks (MLP and RBF) Accuracy in Anticipation of the Dust of the Sabzevar Cement Factory

نویسندگان [English]

  • Seyed Saeed Keykhosravi 1
  • Farhad Nejadkoorki 2
  • Mahmood Amintoosi 3

1 Graduate student, Department of Environmental Engineering, Yazd University of Iran

2 Faculty member of the Department of Environmental Engineering, Yazd University of Iran

3 Assistant Professor, Department of Computer Science, Faculty of Mathematics and, Hakim Sabzevari i University, Iran.

چکیده [English]

Background and Objective: Dust modeling can be considered as an appropriate tool for predicting future industrial dust and identifying pollutant emission control strategies. Perceptron (MLP) and radial base (RBF) neural networks were used as a means for predicting the outflow dust from the main cogeneration of Sabzevar cement factory located in Khorasan Razavi Province.
Method: the concentration of dust from the main cement chimney in the study area was measured through field measurements. Then, the parameters of the production line (temperature, speed of gas output, voltage, fuel, raw materials, and time of sampling) were used as input data to the nerve networks to predict the concentration of dust. The values obtained from the implementation of the models were compared with the results of field measurements as a superior model selection.
Results: The analysis of figures and statistical parameters showed that the mean squared errors for the two MLP and RBF models were as much as 1.787 and 21.263, respectively, and the correlation coefficients were as much as 0.99693 and 0.95811, respectively, which indicates a lower error and greater correlation between the MLP and RBF model in predicting the concentration of dust.
Conclusion: Because of the high ability of perceptron nervous networks to predict dust concentration, this model can be a convenient and fast solution to predict the amount of dust in the industry.

کلیدواژه‌ها [English]

  • Cement Factory
  • Dust
  • Artificial Neural Networks
  • Air Pollution
References:
1.             Perez P, Reyes J. An integrated neural network model for PM10 forecasting. Atmospheric Environment. 2006;40(16):2845-51.
2.             Mwaiselage J, Moen B, Bråtveit M. Acute respiratory health effects among cement factory workers in Tanzania: an evaluation of a simple health surveillance tool. International archives of occupational and environmental health. 2006;79(1):49-56.
3.             Huang CYYCC, Chiu HFCJF, Ko SJLYC. Effects of occupational dust exposure on the respiratory health of Portland cement workers. Journal of Toxicology and Environmental Health Part A. 1996;49(6):581-8.
4.             Al‐Neaimi Y, Gomes J, Lloyd O. Respiratory illnesses and ventilatory function among workers at a cement factory in a rapidly developing country. Occupational Medicine. 2001;51(6):367-73.
5.             Neghab M, Choobineh A. Work-related respiratory symptoms and ventilatory disorders among employees of a cement industry in Shiraz, Iran. Journal of occupational health. 2007;49(4):273-8.
6.             Mwaiselage J, Bråtveit M, Moen B, Yost M. Variability in dust exposure in a cement factory in Tanzania. Annals of occupational hygiene. 2005;49(6):511-9.
7.             Zeleke ZK, Moen BE, Bråtveit M. Cement dust exposure and acute lung function: a cross shift study. BMC pulmonary medicine. 2010;10(1):19.
8.             Fell AKM, Notø H, Skogstad M, Nordby K-C, Eduard W, Svendsen MV, et al. A cross-shift study of lung function, exhaled nitric oxide and inflammatory markers in blood in Norwegian cement production workers. Occup Environ Med. 2011;68(11):799-805.
9.             Laraqui CH, Laraqui OH, Rahhali A, Tripodi D, Caubet A, Belamallem I, et al. Respiratory symptoms and ventilatory disorders among a group of cement workers in Morocco. Revue des maladies respiratoires. 2002;19(2 Pt1):183-9.
10.          Abrons H, Petersen M, Sanderson W, Engelberg A, Harber P. Symptoms, ventilatory function, and environmental exposures in Portland cement workers. Occupational and Environmental Medicine. 1988;45(6):368-75.
11.           Rasmussen F, Borchsenius L, Holstein B, Sølvsteen P. Lung function and long-term exposure to cement dust. Scandinavian journal of respiratory diseases. 1977;58(5):252-64.
12.          Mwaiselage J, Bråtveit M, Moen B, Yost M. Variability in dust exposure in a cement factory in Tanzania. Annals of occupational hygiene. 2005;49(6):511-9.
13.          Baroutian S, Mohebbi A, Goharrizi AS. Measuring and modeling particulate dispersion: A case study of Kerman Cement Plant. Journal of hazardous materials. 2006;136(3):468-74.
14.          Arditsoglou A, Samara C. Levels of total suspended particulate matter and major trace elements in Kosovo: a source identification and apportionment study. Chemosphere. 2005;59(5):669-78.
15.          Abdul-Wahab SA. Impact of fugitive dust emissions from cement plants on nearby communities. Ecological Modelling. 2006;195(3-4):338-48.
16.          Ehrlich C, Noll G, Kalkoff W-D, Baumbach G, Dreiseidler A. PM10, PM2. 5 and PM1. 0—emissions from industrial plants—results from measurement programmes in Germany. Atmospheric Environment. 2007;41(29):6236-54.
17.          Bignal KL, Langridge S, Zhou JL. Release of polycyclic aromatic hydrocarbons, carbon monoxide and particulate matter from biomass combustion in a wood-fired boiler under varying boiler conditions. Atmospheric Environment. 2008;42(39):8863-71.
18.          Lee SW, Herage T, He I, Young B. Particulate characteristics data for the management of PM2. 5 emissions from stationary combustion sources. Powder Technology. 2008;180(1-2):145-50.
19.          Eslamloueyan R, Khademi M. Estimation of thermal conductivity of pure gases by using artificial neural networks. International Journal of Thermal Sciences. 2009;48(6):1094-101.
20.          McKendry IG. Evaluation of artificial neural networks for fine particulate pollution (PM10 and PM2. 5) forecasting. Journal of the Air & Waste Management Association. 2002;52(9):1096-101.
21.          Marengo E, Bobba M, Robotti E, Liparota MC. Modeling of the polluting emissions from a cement production plant by partial least-squares, principal component regression, and artificial neural networks. Environmental Science & Technology. 2006 Jan 1;40(1):272-80.
22.          Mohebbi A, Baroutian S. Estimation of particle concentration emitted from the stacks of Kerman Cement Plant using artificial neural networks. Chemical Engineering Communications. 2008;195(7):821-33.
23.          Haykin S, Network N. A comprehensive foundation. Neural networks. 2004;2(2004):41.
24.          Zarghi H, Ezi J. Comparison of regression models and artificial neural networks in predicting the yield of egg laying hens. Iranian Journal of Animal Science Research. 2015; 7(1): 58-65.
25.          Theodoridis S, Koutroumbas K. Pattern Recognition & Matlab Intro: Academic Press, Inc.; 2010.
26.          Iran Environmental Protection Agency. Decree on the determination of the emission limit of air pollutants. 1397; [26 screens] Availabel at: URL: http://www.dastour.ir/brows/?lid=420073. Accessed October 1, 2018.
27.          Alizadehdakhel A, Ghavidel A, Panahandeh M. CFD modeling of particulate matter dispersion from Kerman cement plant. Iranian Journal of Health and Environment. 2010;3(1):67-74. (in Persian)
28.          Akbari A, editor Borhan diani S, an Evaluation of pollutant gases outlet cement factory behbahan And compared with the standard. 1th National Conference on Planning and Environmental Hamadan-Islamic Azad University; 2011:1-8. (in Persian)
29.          Bonankhah A. Application of Artificial Neural Networks in Estimating Particulate Particles Caused by Industries (A Case study: Shiraz Cement Factory). [Masters Thesis]. Iran. Faculty of Natural Resources and the Environment of Yazd University; 2012. (in Persian)
30.          Nezamparvar S. Modeling the dust output of Flue using Neural network and Study the performance of Electro-filter (A Case Study of Zaveh Cement Factory). [Masters Thesis]. Iran. Faculty of Geography and Environmental of Hakim Sabzevari University; 2015. (in Persian)
31.          NOURI RE, Ashrafi K, Azhdarpour A. Comparison of ANN and PCA based multivariate linear regression applied to predict the daily average concentration of CO: A case study of Tehran. 2008. (in Persian)