Modeling the Throughput of Horizontal Shaft Impact Crushers Using Regression Analyses, Artificial Neural Networks and Multivariate Adaptive Regression Spline

Year 2022, , 1193 - 1203, 27.10.2022

Ekin Köken

https://doi.org/10.35414/akufemubid.1116702

Cited By: 1

Abstract

In this study, the throughput (Q) of horizontal shaft impact (HSI) crushers was investigated using regression analyses, artificial neural networks (ANN) and multivariate adaptive regression spline (MARS). For this purpose, 32 different HSI-type crushers, which operated in the secondary crushing processes of various rock quarries in Turkey, were considered. Various quantitative data (i.e., rotor width (Rw), rotor diameter (Rd), rotor speed (Vr), characterized feed size (d80), operating energy (Oe), and Los Angeles abrasion value (LAAV) of the crushed stone) were collected from each crushing-screening plant. Linear and nonlinear regression analyses were first conducted using the above-mentioned collected data. Then, different ANN and MARS analyses were carried out to estimate the Q of these crushers. As a result, strong predictive models were developed to estimate the Q of HSI-type crushers. The correlation of determination (R2) of the proposed models (M6‒M10) ranged from 0.91 to 0.98, indicating the relative success of the established models. Therefore, the proposed models can reliably be used to estimate the Q of investigated HSI-type crushers. Nevertheless, the number of case studies should be increased to investigate other factors affecting the Q of HSI-type crushers.

Keywords

Horizontal shaft impact crusher, Crushed stone, Rock quarry, Regression analysis, Artificial neural networks

Thanks

The corresponding author is greatly indebted to anonymous mining companies in Turkey who provided their facilities during data gathering.

Yatay Milli Kırıcılarda Kırma Kapasitesinin Regresyon, Yapay Sinir Ağları ve Çok Değişkenli Uyarlamalı Regresyon Analizi Kullanılarak Modellenmesi

Abstract

Bu çalışmada, yatay milli darbeli kırıcıların (HSI) kırma kapasitesinin (Q), regresyon analizleri, yapay sinir ağları (ANN) ve çok değişkenli uyarlamalı regresyon analizi (MARS) kullanılarak araştırılmıştır. Bu amaçla, Türkiye'deki çeşitli taş ocaklarında ikincil kırma işlemlerinde kullanılan 32 farklı HSI tipi kırıcı ele alınmıştır. Çeşitli sayısal veriler (rotor genişliği (Rw), rotor çapı (Rd), rotor hızı (Vr), karakterize edilen besleme boyutu (d80), çalışma enerjisi (Oe) ve kırmataşın Los Angeles aşınma değeri (LAAV)) her bir kırma–eleme tesisinden elde edilmiştir. Öncelikle, toplanan veriler kullanılarak doğrusal ve doğrusal olmayan regresyon analizleri gerçekleştirilmiştir. Daha sonra ise, bu kırıcıların Q değerini tahmin etmek için farklı ANN ve MARS analizleri yapılmıştır. Sonuç olarak, kırıcıların Q değerini tahmin etmek için güçlü tahmin modelleri geliştirilmiştir. Önerilen modellerin (M6–M10) belirleme katsayısı (R2) 0.91 ile 0.98 arasında değişmekte olup, söz konusu yüksek R2 değerleri geliştirilen modellerin göreceli başarısını göstermektedir. Bu nedenle, önerilen modeller, araştırılan HSI tipi kırıcıların Q değerini tahmin etmek için güvenilir bir şekilde kullanılabilir. Bununla birlikte, HSI tipi kırıcıların Q değerini etkileyen diğer faktörleri araştırmak için örnek çalışmalarının sayısı arttırılmalıdır.

Keywords

Yatay milli kırıcı, Kırmataş, Taş ocağı, Regresyon analizi, Yapay sinir ağları

References

• Babele, V., 2016. A Review Study on the Proposed Model for a Multilevel Horizontal Shaft Impact Crusher. International Journal of Engineering Technology and Applied Science, 2(7), 7.
• Barrios, G.K., Jimenez-Herrera, N., Natalia, F.T., Tavares, L.M., 2020. DEM simulation of laboratory-scale jaw crushing of a gold-bearing ore using a particle replacement model. Minerals, 10(8), 717.
• Chen Z. Wang G. Xue D. and Bi Q., 2020. Simulation and optimization of gyratory crusher performance based on the discrete element method. Powder Technology, 376, 93 – 103.
• Das, S.K., 2013. Artificial neural networks in geotechnical engineering: modeling and application issues. Metaheuristics in Water, Geotechnical and Transport Engineering, 5, 231-267.
• Djordjevic, N., Shi, F.N., Morrison, R.D., 2003. Applying discrete element modelling to vertical and horizontal shaft impact crushers. Minerals Engineering, 16, 983–991.
• Duthoit, V. 2000 Crushing and grinding aggregates, Chapter. 9, (Ed. Louis Primel and Claud Tourenq). Balkema, Rotterdam.
• Faradonbeh, R.S., Monjezi, M. 2017. Prediction and minimization of blast-induced ground vibration using two robust meta-heuristic algorithms. Engineering with Computers, 33, 835–851.
• Friedman, J., H., 1991. Multivariate adaptive regression splines, The Annals of Statistics, 19(1), 1–67.
• Grunditz S., 2015. Modeling and optimization of a vertical shaft impactor for production of artificial sand, Master Thesis, Chalmers University of Technology, 54.
• Hosseini, S.A.; Tavana, A.; Abdolahi, S.M.; Darvishmaslak, S. 2019. Prediction of blast-induced ground vibrations in quarry sites: A comparison of GP, RSM and MARS. Soil Dynamics and Earthquake Engineering, 119: 118–129.
• Kahraman S., Toraman O.Y., and Cayirli S., 2018. Predicting the strength and brittleness of rocks from a crushability index, Bulletin of Engineering Geology and the Environment, 77(4), 1639 – 1645.
• Korman, T., Bedekovic, G., Kujundzic, T., & Kuhinek, D., 2015. Impact of physical and mechanical properties of rocks on energy consumption of jaw crusher, Physicochemical Problems of Mineral Processing, 51(2), 461 – 475.
• Köken, E., Özarslan, A., 2018. New testing methodology for the quantification of rock crushability, compressive crushing value (CCV). International Journal of Minerals Metallurgy and Materials, 25(11), 1227–1236.
• Köken, E., 2020. Evaluation of size reduction process for rock aggregates in cone crusher, Bulletin of Engineering Geology and the Environment, 79, 4933 – 4946.
• Köken, E. and Jili, Q., 2020. “Comparison of secondary crushing operations through cone and horizontal shaft impact crushers”, In: 20th International Multidisciplinary Scientific Geoconference, SGEM 2020, pp 789 – 796.
• Li, H. McDowell, G.R., Lowndes, I.S. 2014. Discrete element modelling of a rock cone crusher, Powder Technology, 63, 151 – 158.
• Mayorga, R.V., Arriaga, M., 2007. Non-linear global optimization via parameterization and inverse function approximation: An artificial neural networks approach. International Journal of Neural Systems. 17(5), 353-368.
• Momeni, E.; Nazir, R.; Armaghani, D.J.; Maizir, H., 2014. Prediction of pile bearing capacity using a hybrid genetic algorithm-based ANN. Measurement, 57: 122–131.
• Saravanan, K., Sasithra, S., 2014. Review on classification based on artificial neural networks. International Journal of Ambient Systems and Applications, 2(4), 11-18.
• Sinnott, M.D. Cleary P.W. 2015. Simulation of particle flows and breakage in crushers using DEM: Part 2– Impact crushers, Minerals Engineering, 74: 163–177.
• Quist J. and Evertsson C.M., 2016, “Cone crusher modelling and simulation using DEM”, Minerals Engineering, 85: 92 – 105.