Eğimli Bant Konveyörlerde Kurulu Gücün Genetik Algoritma ve Yapay Sinir Ağları Kullanılarak Tahmini

Abstract

Bu çalışmada, madencilik endüstrisinde kullanılan bazı eğimli bant konveyörlerin kurulu gücü (Pinst, Kw) iki yapay zeka yöntemi (Genetik programlama (GEP) ve yapay sinir ağları (ANN) ile araştırılmıştır. Bu amaçla, 42 bant konveyöre ait en önemli bant (bant boyu, (L), bant genişliği (W), bant eğimi (α)), işletme (bant hızı, (Vb) ve taşıma kapasitesi (Q)) ve alt yapı (Bant ağırlığı (Wb), bant akış kasnak ağırlığı (Wid)) özelliklerine ait veriler toplanmıştır. Toplanan veriler yapay zeka analizleri için bir veri seti haline dönüştürülmüş olup, GEP ve ANN yöntemlerini temel alan ve Pinst değerini tahmin edebilen iki kuvvetli tahmin modeli önerilmiştir. Önerilen modellerin performansları bazı istatistiksel göstergerler kullanılarak değerlendirilmiş olup, istatisiksel değerlendirmeler modellerin belirleme katsayısı (R2) değerlerinin 0.95’ten yüksek olduğunu göstermiştir. Bununla birlikte, ANN yöntemini temel alan modelin Pinst değerlerini tahmin etmede hafif bir üstünlüğü mevcuttur. Sonuç olarak, önerilen modeller güvenilir bir biçimde Pinst değerlerini tahmin etmede kullanılabilir. Ayrıca çalışmada ifade edilen modellere ait matematiksel ifadeler kullanıcıların modelleri daha etkin bir şekilde kullanmaları adına bu çalışmada sunulmuştur.

Keywords

• Bant konveyörler
• Madencilik
• Kurulu güç
• Genetik programlama
• Yapay sinir ağları

ASSESSMENT OF INSTALLED POWER FOR INCLINED BELT CONVEYORS USING GENETIC ALGORITHM AND ARTIFICIAL NEURAL NETWORKS

Abstract

In this study, the installed power (Pinst, kW) of several inclined belt conveyors operating in the mining industry of Turkey was investigated through two soft computing algorithms (i.e., genetic expression programming (GEP) and artificial neural networks (ANN)). For this purpose, the most crucial belt (i.e., belt length (L), belt width (W), belt inclination (α)), operational (i.e., belt speed (Vb) and throughput (Q)) and infrastructural (belt weight (Wb) and idler weight (Wid)) features of 42 belt conveyors were collected for each investigated belt conveyor. The collected data was transformed into a comprehensive dataset for soft computing analyses. Based on the GEP and ANN analyses, two robust predictive models were proposed to estimate the Pinst. The performance of the proposed models was evaluated using several statistical indicators, and the statistical evaluations demonstrated that the models yielded a correlation of determination (R2) greater than 0.95. Nevertheless, the ANN-based model has slightly overperformed in predicting the Pinst values. In conclusion, the proposed models can be reliably used to estimate the Pinst for the investigated conveyor belts. In addition, the mathematical expressions of the proposed models were given in the present study to let users implement them more efficiently.

Keywords

• Belt conveyors
• Mining
• Installed power
• Gene expression programming
• Artificial neural networks

References

1. Ali A.R. 2018 Predicted speed control based on Fuzzy Logic for belt conveyors, Thesis research in Master’s Program in Electrical Engineering, Karlstad University, Sweden, 72 pp.
2. CEMA 2014 Conveyor Equipment Manufacturers Association Belt Conveyors for Bulk Materials, 7th, 2014. 978-1891171-44-4
3. DIN 22101 2002 German Institute for standardization: Continuous conveyors - Belt conveyors for loose bulk materials - Basis for calculation and dimensioning, 51 pp.
4. Dunlop–Fenner 2009 conveyor handbook: Conveyor belting Australia, 103 pp.
5. Espinosa O., Jose J. Vandewalle J.P.L, and Wertz V. 2005 Fuzzy Logic, Identification and Predictive Control. Advances in Industrial Control. Springer-Verlag, London, ISBN 978-1-84628-087-0
6. Ferreira C. 2001 Gene expression programming: A new adaptive algorithm for solving problems, Complex Syst, pp. 13
7. Jeftenic B., Risti¢ L., Bebi¢ M., and Statkic S. 2009 Controlled induction motor drives supplied by frequency converters on belt conveyors; modeling and commissioning. In 35th Annual Conference of IEEE Industrial Electronics, pp 1063-1068
8. Król R. Kaszuba D. and Kisielewski W. 2016 Determination of the mechanical power in belt conveyor’s drive system in industrial conditions, In IOP Conf. Series: Earth and Environmental Science 44, 042038

9. Köken E., Lawal A.I. Onifade M. and Özarslan A. 2022 A comparative study on power calculation methods for conveyor belts in mining industry, Int J. Min. Rec., 36: 26-45.
10. Lawal A.I., and Idris M.A., 2020 An artificial neural network-based mathematical model for the prediction of blast-induced ground vibrations. Int. J. Environ. Stud., 77(2): 318 – 334
11. Marx D.J.L. (2005) Energy audit methodology for belt conveyors, Master thesis, University of Pretoria, 123 pp. Masaki MS, Zhang LJ, Xia XH. 2017 A comparative study on the cost-effective belt conveyors for bulk material handling, In 9th International Conference on Applied Energy, ICAE2017. Cardiff, UK, 21–24 August. pp. 2754–2760.
12. Mhlongo I.N., Nnachi G.U., Nnachi A.F. and Adesola A.T. 2020 Modelling and simulation of conveyor belt for energy efficiency studies, IEEE PES/IAS PowerAfrica, DOI: 10.1109/PowerAfrica49420.2020.9219974
13. Middelberg A., Zhang J., and Xia X., 2009 An optimal control model for load shifting–With application in the energy management of a colliery, Appl. Energy. 86, 7–8, pp. 1266–1273.
14. Mushiri T. 2016 Design of a power saving industrial conveyor system, In Proceedings of the World Congress on Engineering and Computer Science 2016 Vol II WCECS 2016, October 19-21, 2016, San Francisco, USA
15. Singh R., Kainthola A., and Singh T.N., 2012 Estimation of elastic constant of rocks using an ANFIS approach, Appl. Soft Comput. J. 12: 40–45.
16. Xia X. and Zhang J., 2010 Energy efficiency and control systems–from a POET perspective, IFAC Proc. 43, 1, pp. 255–260. DOI:10.3182/20100329-3-PT-3006.00047
17. Yao Y. and Zhang B. 2020 Influence of the elastic modulus of a conveyor belt on the power allocation of multi-drive conveyors, Plos One, 15(7): e0235768, DOI: 10.1371/journal.pone.0235768