Kristal Şeker üretiminde ÇDR, YSA ve ANFIS ile parametre tahmini

Year 2022, Volume: 28 Issue: 7, 987 - 992, 30.12.2022

Fatma Erdem

Abstract

Şeker üretim süreci, birçok değişkenin etkileşim içinde olduğu karmaşık bir süreçtir. Karmaşık süreçlerin maliyet ve zaman gereksinimleri, bilgisayar tabanlı modelleme teknikleri ile azaltılmakta ve elde edilen ürün kalitesi ile ilgili gerekli aksiyonlar zamanında alınabilmektedir. Bu çalışmada şeker üretimi için kalite kontrol kriterlerinden biri olan çözelti rengi, kristalizasyon aşaması için çoklu doğrusal regresyon (MLR), yapay sinir ağı (YSA) ve uyarlanabilir sinirsel bulanık çıkarım sistemi (ANFIS) ile tahmin edilmiştir. Üretim verileri (brix, saflık, pol, pH, kül, renk ve vakum sıcaklığı) Ankara Şeker Fabrikası Genel Müdürlüğü'nden alınmıştır. Duyarlılık analizi sonucunda kül, renk ve vakum sıcaklığının tahmin edilen çıktı üzerinde en etkili parametreler olduğu belirlenmiş ve model girdi değişkenleri olarak tanımlanmıştır. Model performans kriteri olarak R ve MSE değerleri kullanılmıştır. ANFIS, MLR ve ANN'den daha iyi tahmin performansı göstermiştir, R= 0.99.

Keywords

Şeker üretimi, Modelleme, yapay Sinir ağı, MLR, ANFIS

Parameter estimation in Crystal Sugar production with MLR, ANN and ANFIS

Abstract

The sugar production process is a complex process in which many variables interact. The cost and time requirements of complex processes are reduced by computer-based modeling techniques and necessary actions can be taken regarding the obtained product quality. In this study for the crystallization stage, solution color which is one of the quality control criteria for sugar production, was predicted by multiple linear regression (MLR), artificial neural network (ANN) and adaptive neural fuzzy inference system (ANFIS). Production data (brix, purity, pol, pH, ash, color and vacuum temperature) obtained from Ankara Sugar Factory General Directorate. As a result of the sensitivity analysis ash, color and vacuum temperature was determined to be the most effective parameters on the estimated output and used as a model input variables. R and MSE values were used as model performance criteria. ANFIS showed better prediction performance than MLR and ANN, R= 0.99.

Keywords

Sugar production, Modeling, Artificial neural network, MLR, ANFIS

References

• [1] Karabina K. “Sugar Annual Report”. U.S. Department of Agriculture (USDA), TR 9008, 2020.
• [2] Aremu MO, Araromi DO, Adeniran JA, Alamu OS. “Optimization of Process Variables for C-massecuite Exhaustion in a Nigerian Sugar Refinery”. Current Journal of Applied Science and Technology, 4(21), 3039-3052, 2014.
• [3] Li X, Dai Y, Cheng J. “Research on neural network quality prediction model based on genetic algorithm”. IOP Conference Series: Earth and Environmental Science Guangzhou, China, 8-10 March 2019.
• [4] Poul AK, Shourian M, Ebrahimi HA. “Comparative study of MLR, KNN, ANN and ANFIS models with wavelet transform in monthly stream flow prediction”. Water Resource Management, 33, 2907-2923, 2019.
• [5] Taşan S, Demir Y. “Comparative Analysis of MLR, ANN, and ANFIS Models for Prediction of Field Capacity and Permanent Wilting Point for Bafra Plain Soils”. Communications in Soil Science and Plant Analysis, 51(5), 604-621, 2020.
• [6] Adamowski J, Chan HF, Prasher SO, Sharda VN. “Comparison of multivariate adaptive regression splines with coupled wavelet transform artificial neural networks for runoff forecasting in Himalayan microwatersheds with limited data”. Journal Hydroinformatics,14(3), 731-744, 2012.
• [7] Tabriz SS, Hossen MS, Rahman MA, Amanullah ASM Arefin MS. “Juice extraction from sugar beet by pressing method”. Eco-friendly Agriculture Journal, 8(5), 67-69, 2015.
• [8] Gunawan, Bantacut T, Romli M, Noor E. “Biomass byproduct from crystal sugar production: A comparative study between Ngadirejo and Mauritius sugar mill”. IOP Conferences Series: Earth and Environmental Science Bogor, Indonesia, 04-25 July 2017.
• [9] Niu W, Lu J, Sun YA. “Production prediction method for shale gas wells based on multiple regression”. Energies, 14, 1461-1472, 2021.
• [10] Tumer A, Koc B, Kocer S. “Artificial neural network models for predicting the energy consumption of the process of crystallization syrup in konya sugar factory”. International Journal of Intelligent Systems and Applications in Engineering, 5(1), 18-21, 2017.
• [11] Jiang J, Trundle P, Ren J. “Medical ımaging analysis with artificial neural networks”. Computerized Medical Imaging and Graphics, 34(8), 617-631, 2010.
• [12] Abdelbary A. Wear of Polymers and Composites. Editor: Dowson D. Prediction of Wear in Polymers and Their Composites, 185-217, Holland, Elsevier, Woodhead Publishing, 2014.
• [13] Çelik Ö, Altunaydın SS. “A research on machine learning methods and ıts applications”. Journal of Educational Technology & Online Learning, 1(3), 25-40, 2018.
• [14] Salah AW, Hannan Qureshi A. Dynamic Data Assimilation. Editor: Harkut DG. Data Processing Using Artificial Neural Networks. Dynamic data Assimilation-Beating the Uncertainties, 83-86, London, United Kingdom, IntechOpen Press, 2020.
• [15] Sonmez AY, Kale S, Ozdemir RC, Kadak AE. “An adaptive neuro-fuzzy ınference system (ANFIS) to predict of cadmium (Cd) concentrations in the filyos river, Turkey”. Turkish Journal of Fisheries and Aquatic Sciences, 18, 1333-1343, 2018.
• [16] Mostafaeipour A, Qolipour M, Goudarzi H, Jahangiri M, Golmohammadi A, Rezaei M, Goli A, Sadeghikhorami L, Sadeghi Sedeh A, Khalifeh Soltani S. “Implementation of adaptive neuro-fuzzy ınference system (anfis) for performance prediction of fuel cell parameters”. Journal of Renewable Energy and Environment, 6(3), 7-15, 2019.
• [17] Kuyakhi HR, Boldaji RT. “Developing an adaptive neuro‐ fuzzy inference system based on particle swarm optimization model for forecasting Cr (VI) removal by NiO nanoparticles”. Environmental Progress & Sustainable Energy, 2021. https://doi.org/10.1002/ep.13597.
• [18] Fırat M, Yurdusev MA, Mermer M. “Uyarlamali sinirsel bulanik mantik yaklaşimi ıle aylik su tüketiminin tahmini”. Gazi Üniversitesi Mühendislik Mimarlık Fakültesi Dergisi, 23(2), 449-457, 2013.
• [19] Yavuz S, Deveci M. “İstatiksel normalizasyon tekniklerinin yapay sinir ağin performansina etkisi”. Erciyes Üniversitesi İktisadi ve İdari Bilimler Fakültesi Dergisi, 40, 167-187, 2012.
• [20] Hosseinpourtehrani M, Ghahraman B. “Optimal reservoir operation for ırrigation of multiple crops using fuzzy logic”. Asian Jornal of Applied Science, 4, 493-513, 2011.
• [21] Shi HVN, Szajman J. “Sensitivity analysis and optimisation to input variables using winGamma and ANN: A case study in automated residential property valuation”. International Journal of Advanced and Applied Sciences, 2, 19-24, 2015.
• [22] Al-Mukhtar M, Al-Yaseen F. “Modeling water quality parameters using data-driven models, a case study abuziriq marsh in South of Iraq”. Hydrology, 2019. https://doi.org/10.3390/hydrology6010024
• [23] Páliz Larrea P, Zapata-Ríos X, Campozano Parra L. “Application of neural network models and anfıs for water level forecasting of the salve faccha dam in the andean zone in northern ecuador”. Water, 2011. https://doi.org/10.3390/w13152011
• [24] Wong YJ, Arumugasamy SK, Chung CH, Selvarajoo A, Sethu V. “Comparative study of artificial neural network (ANN), adaptive neuro-fuzzy inference system (ANFIS) and multiple linear regression (MLR) for modeling of Cu (II) adsorption from aqueous solution using biochar derived from rambutan (Nephelium lappaceum) peel”. Environmental Monitoring Assessment, 2020. https://doi.org/10.1177/1847979018768
• [25] Rezaeianzadeh M, Tabari H, Arabi Yazdi A. “Flood flow forecasting using ANN, ANFIS and regression models”, Neural Computing Applications, 25, 25-37, 2014. [26] Caner M, Akarslan E. “Estimation of Specific Energy Factor in Marble Cutting Process Using ANFIS and ANN”. Pamukkale University Journal of Engineering Sciences, 15(2), 221-226, 2009.