The increase of the performance of ultrafine coal flotation by using emulsified kerosene and the prediction of the flotation parameters by random forest and genetic algorithm

• Autorzy: Oney Ozcan

Identyfikatory

DOI

10.24425/ams.2019.126275

Warianty tytułu

PL

Poprawa efektywności flotacji węgla drobnoziarnistego przy wykorzystaniu emulsji naftowej oraz prognozowanie parametrów procesu flotacji przy użyciu metody lasów losowych oraz algorytmu genetycznego

• Języki publikacji: EN

Abstrakty

EN

In this study, emulsified kerosene was investigated to improve the flotation performance of ultrafine coal. For this purpose, NP-10 surfactant was used to form the emulsified kerosene. Results showed that the emulsified kerosene increased the recovery of ultrafine coal compared to kerosene. This study also revealed the effect of independent variables (emulsified collector dosage (ECD), frother dosage (FD) and impeller speed (IS)) on the responses (concentrate yield (γC %), concentrate ash content (%) and combustible matter recovery (ε %)) based on Random Forest (RF) model and Genetic Algorithm (GA). The proposed models for γC %, % and ε% showed satisfactory results with R2. The optimal values of three test variables were computed as ECD = 330.39 g/t, FD = 75.50 g/t and IS = 1644 rpm by using GA. Responses at these experimental optimal conditions were γC % = 58.51%, % = 21.7% and ε % = 82.83%. The results indicated that GA was a beneficial method to obtain the best values of the operating parameters. According to results obtained from optimal flotation conditions, kerosene consumption was reduced at the rate of about 20% with using the emulsified kerosene.

PL

W pracy zbadano możliwość wykorzystania emulsji naftowej do poprawy efektywności flotacji węgla drobnoziarnistego. W tym celu wykorzystano środek powierzchniowo czynny NP.-10 do utworzenia emulsji naftowej. Badania wykazały, że zastosowanie nafty w formie emulsji poprawiło wskaźniki odzysku węgla w porównaniu do procesów z wykorzystaniem nafty. W pracy badano także wpływ zmiennych zależnych (dozowanie emulsji w kolektorze ECD, dozowanie środka pianotwórczego FD, prędkość wirnika IS na wyniki procesu (uzysk koncentratu (γC %), zawartość popiołów (%) i stopień odzysku materii palnej (ε%), w oparciu o metodę lasów losowych i algorytm genetyczny. Proponowane modele pozwoliły na uzyskanie zadawalających wyników dla wskaźników γC %, %, ε %, w odniesieniu do współczynnika R2. Optymalne wartości badanych zmiennych ECD = 330.39 g/t, FD = 75.50 g/t and IS = 1644 obrotów na minutę obliczono przy wykorzystaniu algorytmu genetycznego. Wyniki procesu prowadzonego w wa-runkach optymalnych, określonych eksperymentalnie to γC % = 58.81 %; % = 21.7 %; ε % = 82.83 %. Uzyskane wyniki wskazują, że wykorzystanie algorytmu genetycznego jest metodą umożliwiającąotrzymanie najkorzystniejszych wartości parametrów pracy. Na podstawie wyników flotacji uzyskanych w najkorzystniejszych warunkach stwierdzono, że zużycie nafty obniżone zostało o ok. 20% dzięki zastosowaniu nafty w postaci emulsji.

Słowa kluczowe

EN

ultrafine coal flotation; emulsified kerosene; random forest; genetic algorithm

PL

flotacja węgla drobnoziarnistego; emulsja naftowa; metoda lasów losowych; algorytm genetyczny

• Wydawca: Instytut Mechaniki Górotworu PAN
• Czasopismo: Archives of Mining Sciences
• Rocznik: 2019
• Tom: Vol. 64, no. 1
• Strony: 119--130
• Opis fizyczny: Bibliogr. 46 poz., rys., tab., wykr.

Twórcy

autor

Oney Ozcan

• Usak University, Faculty of Engineering, Mining Engineering Department, 1 Eylul Campus, 64200, Usak, Turkey

Bibliografia

• [1] Aktas Z., Woodburn E., 1995. The effect of non-ionic reagent adsorption on the froth structure and flotation performance of two low rank British coals. Powder Technology 83, 149-158.
• [2] Asplin R., Sadr-Kazemi N., Cilliers J., 1998. The effect of surfactant concentration on batch flotation mineral flux and froth structure. Minerals Engineering 11, 257-269.
• [3] Biau G., Scornet E., 2016. A random forest guided tour. Test 25 (2), 197-227.
• [4] Bokany L., 2016. Three parameter phenomenological coal flotation model. XVII Int. Coal Preparation Congress, 28 June-01 July ,Saint-Petersburg, Russia, Editor: Vladimir Litvinenko, 1059-1064.
• [5] Bontempi G., Taieb S.B., Le Borgne Y.A., 2013. Machine learning strategies for time series forecasting. In Business Intelligence (Lecture Notes in Business Information Processing); Aufaure, M.A., Zimányi, E., Eds.; Springer: Berlin/Heidelberg, Germany 138, 62-77.
• [6] Boussaï I., Lepagnot J., Siarry P., 2013. A survey on optimization metaheuristics. Inf. Sci. 237, 82-117.
• [7] Breiman L., 2001. Random forests. Mach. Learn. 45, 5-32.
• [8] Brown D.J., 1962. Coal flotation, Froth flotation. 50th Anniversary Volume (D.W. Fuerstenau, Ed.) AIME, New York, 518-538.
• [9] Bulatovic S.M., 2007. Handbook of flotation reagents chemistry, theory and practice: Flotation of Sulfide Ores 1. Elsevier Science and Technology, Amsterdam, ISBN: 978-0-444-53082-0.
• [10] Cebeci Y., 2002. The investigation of the floatability improvement of Yozgat Ayrıdam lignite using various collectors. Fuel 81, 281-289.
• [11] Chaves A.P., 1983. Flotação de Carvão de Santa Catarina (Região do Alto Metalúrgico). PhD Thesis, Escola Politécnica, Universidade de São Paulo, São Paulo.
• [12] Chaves A.P., Rui A.S., 2009. Considerations on the kinetics of froth flotation of ultrafine coal contained in tailing. International Journal of Coal Preparation and Utilization 29, 289-297.
• [13] Chelgani S.C., Matin S.S. Makaremi S., 2016. Modeling of free swelling index based on variable importance measurements of parent coal properties by random forest method. Measurement 94, 416-422.
• [14] Duong C., Choung J., Xu Z., Szymanski J. 2000. A novel process for recovering clean coal and water from coal tailings. Minerals Engineering 13, 173-18.
• [15] Eiben E., Smith J.E., 2003. Introduction to evolutionary computing. Springer Science & Business Media.
• [16] Elyan E., Gaber M.M., 2017. A genetic algorithm approach to optimizing random forests applied to class engineered data. Information Sciences 384, 220-234.
• [17] Genuer R., Poggi J.M., Tuleau-Malot C., 2010. Variable selection using random forests. Pattern Recognit. Lett. 31, 2225-2236.
• [18] Ghobadi P., Yahyaei M., Banisi S., 2011. Optimization of the performance of flotation circuits using a genetic algorithm oriented by process-based rules. International Journal of Mineral Processing 98, 174-181.
• [19] Huang B., Sun X., Hu Z., 2009. Applied research on new emulsified floatation agent to Matou mineral processing plant. Coal Technol. 4, 58-60.
• [20] Jia R., Harris G.H., Fuerstenau D.W., 2002. Chemical reagents for enhanced coal flotation. Coal Preparation 22, 123-149.
• [21] Kucukyildiz G., Ocak H., Karakaya S., Sayli O., 2017. Design and implementation of a multi sensor based brain computer interface for a robotic wheelchair. J. In. Tell. Robot Syst. 87, 247-263.
• [22] Laskowski J., 1992. Oil assisted fine particle processing. Developments in Mineral Processing 12, 361-394.
• [23] Laskowski J.S., Yu Z., 1998. Fine coal particle aggregation in coal preparation circuits. 13 th Int. Coal Prep. Congress 2, 591-599.
• [24] Li L., Lu X., Qiu J., Liu D., 2013. Effect of micro emulsified collector on froth flotation of coal. The Journal of The Southern African Institute of Mining and Metallurgy 113, 877-880.
• [25] McCall J., 2005. Genetic algorithms for modelling and optimization. Journal of Computational and Applied Mathematics 184, 205-222.
• [26] Mehrang S., Pietilä J., Korhonen I., 2018. An activity recognition framework deploying the random forest classifier and a single optical heart rate monitoring and tri axial accelerometer wrist-band. Sensors 18, 613, 1-13.
• [27] Menze B.H., Kelm B.M., Masuch R., Himmelreich U., Bachert P., Petrich W., Hamprecht F.A., 2009. A comparison of random forest and its Gini importance with standard chemo metric methods for the feature selection and classification of spectral data. BMC Bio Inform. 10, 213.
• [28] Nakhaei F., Irannajad M., Yousefikhoshbakht M., 2016. Simultaneous optimization of flotation column performance using genetic evolutionary algorithm. Physicochem. Probl. Miner. Process. 52 (2), 874-893.
• [29] Oney O., Samanli S., Niedoba T., Pięta P., Surowiak A. (Article in press). Determination of the Important Operating Variables on Cleaning Fine Coal by Knelson Concentrator and Evaluation of the Performance through Upgrading Curves, International Journal of Coal Preparation and Utilization, http://dx.doi.org/10.1080/1939 2699.2017.1397641.
• [30] Oshiro T.M., Perez P.S., Baranauskas J.A., 2012. How many trees in a random forest? In Machine Learning and Data Mining in Pattern Recognition (Lecture Notes in Computer Science); Perner, P., Ed.; Springer: Berlin/Heidelberg, Germany, 154-168.
• [31] Polat M., Polat H., Chander S., 2003. Physical and chemical interactions in coal flotation. International Journal of Mineral Processing 72, 199-213.
• [32] Probst P., Boulesteix A.L., 2017. To tune or not to tune the number of trees in random forest? https://arxiv.org/pdf/1705.05654.pdf.
• [33] Renhe J., Guy H., Douglas W. et al., 2000. An improved class of universal collectors for the flotation of oxidized and/or low-rank coal. Miner. Process. 58, 99-118.
• [34] Scornet E., Biau G., Vert J.P., 2015. Consistency of random forests. Ann. Stat. 43, 1716-1741.
• [35] Shahbazi B., Chelgani S.C., Matin S.S., 2017. Prediction of froth flotation responses based on various conditioning parameters by Random Forest method. Colloids and Surfaces A 529, 936-941.
• [36] Shi Q., Liang X., Feng O., Chen Y., Wu B., 2015. The relationship between the stability of emulsified diesel and flotation of graphite. Minerals Engineering 78, 89-92.
• [37] Song S., Lopez-Valdivieso A., Ding Y., 1999. Effects of nonpolar oil on hydrophobic flocculation of hematite and rhodochrosite fines. Powder Technology 101, 73-80.
• [38] Tyralis H., Papacharalampous G., 2017. Variable selection in time series forecasting using random forests. Algorithms 10, 114, 1-25.
• [39] Vazifeh Y., Jorjanil E., Bagherian A., 2010. Optimization of reagent dosages for copper flotation using statistical technique. Trans. Nonferrous Met. Soc. China 20, 2371-2378.
• [40] Verikas A., Gelzinis A., Bacauskiene M., 2011. Mining data with random forests: A survey and results of new tests. Pattern Recognit 44, 330-349.
• [41] Wang Y., Xing Y., Gui X., Cao Y., Xuehong Xu X. (Article in press). The characterization of flotation selectivity of different size coal fractions. International Journal of Coal Preparation and Utilization, http://dx.doi.org/10.1080/19392699.2016.1256875.
• [42] Weiwei X., Kaiwu H., Donghui W., Yuran Z., Xiu L., 2012. Study on flotation properties of emulsified diesel oil. Energy Procedia 14, 750-755.
• [43] Ye G., Ma L., Li L., Liu J., Yuan S., Gen Huang G. (Article in press). Application of Box-Behnken design and response surface methodology for modeling and optimization of batch flotation of coal. International Journal of Coal Preparation and Utilization, https://doi.org/10.1080/19392699.2017.1350657.
• [44] Yoon R.H., Lultrell G.H., Asmatulu R., 2002. Extending the upper particle size limit for coal flotation. J. South-Afr. Inst. Min. Metall. 102 (7), 411-416.
• [45] Yu Q., Ye Y., Miller J.D., 1990. A Study of surfactant/oil emulsion for fine coal flotation, advances in fine particle processing. Elsevier Science, Newyork, USA, 345-355.
• [46] Zhang B., 2008. Performance optimization of a compound spiral for fine and ultrafine coal cleaning. MSc Thesis, Southern Illinois University, Department of Mining and Mineral Resources Engineering.

Uwagi

PL

Opracowanie rekordu w ramach umowy 509/P-DUN/2018 ze środków MNiSW przeznaczonych na działalność upowszechniającą naukę (2019)