Radial Basis Function Neural Network based on Growing Neural Gas Network applied for evaluation of oil agglomeration process efficiency

• Autorzy: Marcin Kamiński , Stanisławski Radosław , Bastrzyk Anna

Identyfikatory

DOI

10.37190/ppmp/128533

• Języki publikacji: EN

Abstrakty

EN

In this study, the neural model for modeling of oil agglomeration of dolomite in the presence of anionic and cationic surfactants (sodium oleate and dodecylammonium hydrochloride) was implemented. The effect of surfactants concentration, oil dosage, time of mixing, pH, and mixing speed of the impeller in the process recovery were investigated using Radial Basis Function Neural Network (RBFNN). A significant problem in this modeling, was the selection of the structure of the neural network. In algorithms based on the RBFNN, the issue mentioned relates to the number of nodes in the determination of the hidden layer. Also, the distribution of functions in data space is significant. In the proposed solution, at this stage of the neural model design, the Growing Neural Gas Network (GNGN) was implemented. Such a procedure introduced automation of the calculation process. The centers were obtained from the GNGN and the structure (number of radial neurons) can be approximated based on a simple searching algorithm. The idea of the data calculations was implemented as an original algorithm that can be easily transferred to Matlab, Python, or Octave software. The values predicted from the neural networks model were in good agreement with the experimental data. Thus, the RBFNN-GNGN model used in this study, can be employed as a reliable and accurate method to predict, and in the future to optimize the performance of oil agglomeration process.

Słowa kluczowe

EN

oil agglomeration modeling; dolomite; Radial Basis Function Neural Network; Growing Neural Gas Network

• Wydawca: Oficyna Wydawnicza Politechniki Wrocławskiej
• Czasopismo: Physicochemical Problems of Mineral Processing
• Rocznik: 2020
• Tom: Vol. 56, iss. 6
• Strony: 194--205
• Opis fizyczny: Bibliogr. 45 poz., rys., tab., wykr., wz.

Twórcy

autor

Marcin Kamiński

• Faculty of Electrical Engineering, Wroclaw University of Science and Technology, Janiszewskiego 8, 50-377 Wroclaw, Poland

autor

Stanisławski Radosław

• Faculty of Electrical Engineering, Wroclaw University of Science and Technology, Janiszewskiego 8, 50-377 Wroclaw, Poland

autor

Bastrzyk Anna

• Faculty of Chemistry, Wroclaw University of Science and Technology, Norwida 4/6, 50-373 Wroclaw, Poland

Bibliografia

• ALLAHKARAMI, E., SALMANI NURI, O., ABDOLLAHZADEH, A., REZAI, B., MAGHSOUDI, B., 2017. Improvin estimation accuracy of metallurgical performance of industrial flotation process by using hybrid genetic algorithm – artificial neural network (GA-ANN). Physicochem. Probl. Miner. Process. 53, 366−378.
• ASMOLOV, T., GALIN, R., Study of the effectiveness of combinatorial protection algorithms based on the hardware and software of the electronic storage of corporate information systems. IOP Conf. Ser.: Mater. Sci. Eng. 537, 052027, 1-6.
• BASTRZYK, A., POLOWCZYK, I., SADOWSKI, Z., SIKORA, A., 2011. Relationship between properties of oil/water emulsion and agglomeration of carbonate minerals. Sep. Purif. Technol. 77, 325-330.
• BISHOP, C.M., 1994. Neural networks and their applications. Rev. Sci. Instrum. 65, 1803-1832.
• CECATI, C., KOLBUSZ, J., RÓŻYCKI, P., SIANO P., WILAMOWSKI, B. M., 2015. A novel RBF training algorithm for short-term electric load forecasting and comparative studies. IEEE Trans. Ind. Electron. 62, 6519-6529.
• CHAKLADAR, S., BANERJEE, R., MOHANTY, A., CHAKRAVATRY, S., KUMAR PATAR, P., 2019. Turpentine oil: a novel and natural bridging liquid for oil agglomeration of coal fines of high ash coal. Int. J. Coal Prep. Util. DOI:10.1080/19392699.2020.1789976 (in press).
• CISTERNAS, L.A., LUCAY, F.A., BOTERO, Y.L., 2020. Trends in modeling, design, and optimization of multiphase systems in minerals processing, Minerals 10, 1-28.
• DIAS, W.P.S., POOLIYADDA, S.P., 2001. Neural networks for predicting properties of concretes with admixtures. Constr. Build. Mater. 15, 371-379.
• DRZYMALA, J., 2007. Mineral processing. Foundations of theory and practice of minerallurgy. Ofic. Wyd. PWr, Wroclaw, Poland.
• DUZYOL, S., OZKAN, A., 2010. Role of hydrophobicity and surface tension on shear flocculation and oil agglomeration of magnesite. Sep. Purif. Technol. 72, 7-12.
• FAHLMAN, S., LEBIERE, C., 1997. The cascade-correlation learning architecture. Adv. Neur. Inf. Process. Syst. 2, 524-532.
• FAUSETT, L.V., 1994. Fundamentals of neural networks: architectures, algorithms and applications. Prentice-Hall, United States.
• FRITZKE, B., 1995. A growing neural gas network learns topologies. Adv. Neur. Inf. Process. Syst. 7, 625-632.
• FRITZKE, B., 1994. Fast learning with incremental RBF networks. Neural Process. Lett. 1, 2-5.
• GUAN, W., SHA, J., LIU, P., PENG, Y., XIE, G., 2018. Effect of stirring time on oil agglomeration of fine coal. J. S. Afr. I. Min. Metall. 8, 89-94.
• HASSIBI, B., STORK, D.G., WOLF, G.J., 1993. Optimal brain surgeon and general network pruning. IEEE International Conference on Neural Networks, San Francisco, CA, USA, 1, 293-299.
• HUAN, A.Y., BERG, J.C., 2003. Gelation of liquids bridges in spherical agglomeration. Colloid. Surf. A: Physicochem. Eng. Aspect. 215, 241-252.
• KAMINSKI, M., 2019. Neural network training using Particle Swarm Optimization - a case study. 24th International Conference on Methods and Models in Automation and Robotics (MMAR), Międzyzdroje, Poland, 115-120.
• KAMINSKI, M., BASTRZYK, A., 2018. Modelling of oil agglomeration of dolomite by the use of an artificial neural network optimized using Optimal Brain Damage algorithm. IOP Conf. Ser.: Mater. Sci. Eng. 427, 012012, 1-9.
• KAMINSKI, M., ORLOWSKA-KOWALSKA, T., 2015. Adaptive neural speed controllers applied for a drive system with an elastic mechanical coupling – a comparative study. Eng. Appl. Artif. Intell. 45, 152-167.
• KAYA, Ö., ARI, M., 2019. The effect of novel bridging liquid mixtures on lignite enrichment using the oil agglomeration process. Int. J. Coal. Prep. Util. 39(6), 293-301.
• LASKOWSKI, J., ZHU, Z., 2000. Oil agglomeration and its effect on beneficiation and filtration of low-rank/oxidized coals. Int. J. Miner. Process. 58, 237-252.
• MARTINETZ, T., SCHULTEN, K., 1991. A "neural gas" network learns topologies. Artificial Neural Networks, 397–402.
• MENG, X., ROZYCKI, P., QIAO, J., WILAMOWSKI, B.M., 2018. Nonlinear system modeling using RBF Networks for industrial application. IEEE Trans. Industr. Inform. 14, 931-940.
• MOLINA, C.G., ZERUBIA, J., 2000. Regularisation by convolution in probability density estimation is equivalent to jittering. Neural Networks for Signal Processing X. Proceedings of the 2000 IEEE Signal Processing Society Workshop (Cat. No.00TH8501), Sydney, NSW, Australia, 1, 204-210.
• JAMRÓZ, D., NIEDOBA, T., PIĘTA, P., SUROWIAK, A., 2020. The use of neural networks in combination with evolutionary algorithms to optimize the copper flotation enrichment process. Appl. Sci. 10(9), 3119.
• OZKAN, A., AYDOGAN, M., YEKELER, M., 2005. Critical solution surface tension for oil agglomeration. Int. J. Miner. Process. 76, 83-91.
• PIETSCH, W., 2005. Agglomeration in Industry. Occurrence and Application. Willey-Vch Verlag GmbH&Co. KGaA, Weinhein.
• POLOWCZYK, I., KRUSZELNICKI, M., KOWALCZUK, P.B., 2018. Oil agglomeration of metal-bearing shale in the presence of mixed cationic-anionic surfactants. Physicochem. Probl. Miner. Process. 54(4), 1052-1059.
• QIN, A.K., SUGANTHAN, P.N., 2004. Robust growing neural gas algorithm with application in cluster analysis. Neural Networks 17, 1135–1148.
• RIBEIRO, T.S., GROSSI, C.D., MERMA, A.G., DOS SANTOS, B.F., TOREM, M.L., 2019. Removal of boron from mining wastewaters by electrocoagulation method: modelling experimental data using artificial neural networks. Miner. Eng. 131, 8-13.
• SADOWSKI, Z., 1995. Selective spherical agglomeration of fine salt-type mineral particles in aqueous solution. Colloid. Surf. A: Physicochem. Eng. Aspect. 96, 277-285.
• SADOWSKI, Z., 2000. The role of surfactant salts on the spherical agglomeration of hematite suspension. Colloid. Surf. A: Physicochem. Eng. Aspect. 173, 211-217.
• SARIMVEIS, H., ALEXANDRIDIS, A., BAFAS, G., 2003. A fast training algorithm for RBF networks based on subtractive clustering. Neurocomputing 51, 501-505.
• SHOKRY, A., ESPUÑA, A., 2018. The ordinary kriging in multivariate dynamic modelling and multistep-ahead prediction. Comput. Aided Chem. Eng. 43, 265-270.
• SHUKLA, D.; VENUGOPAL, R., 2019. Optimization of the process parameters for fine coal-oil agglomeration process using waste mustard oil. Powder. Technol. 346, 316-325.
• SUN, Q., LIU, H., HARADAC, T., 2017. Online growing neural gas for anomaly detection in changing surveillance scenes. Pattern Recognit. 64, 187-201.
• SÖNMEZ, İ., CEBECI, Y., 2003. A study on spherical oil agglomeration of barite suspensions. Int. J. Miner. Process. 71, 219-232.
• VACHKOV, G., 2004. Growing model algorithm for process identification based on neural-gas learning and local linear mapping. Fourth International Conference on Hybrid Intelligent Systems (HIS'04), Kitakyushu, Japan, 222-227.
• VAN NETTEN, K., BORROW, D.J., GALVIN, K.P., 2020. Ultrafast plug flow agglomeration – exploiting hydrophobic interactions via a concentrated water-in-oil-emulsion binder. Minerals 10, 506.
• WU, X., LIU, J., 2009. A new early stopping algorithm for improving neural network generalization. 2009 Second International Conference on Intelligent Computation Technology and Automation, Changsha, Hunan, 15-18.
• YANG, P., ZHU, Q., ZHONG, X., 2009. Subtractive clustering based RBF neural network model for outlier detection. J. Comput. 4, 755-762.
• YASAR, O., USLU, T., 2019. Use of agglomeration for fine coal recovery from washery tailings. Int. J. Coal Prep. Util. DOI:10.1080/19392699.2019.1705287 (in press).
• YU, H., REINER, P. D., XIE, T., BARTCZA, T., WILAMOWSKI, B.M., 2014. An incremental design of radial basis function networks. IEEE Trans. Neural Netw. Learn. Syst 25, 1793-1803.
• ZHANG, P., ZHOU, X., PELLICCIONE, P., LEUNG, H., 2017. RBF-MLMR: a multi-label metamorphic relations prediction approach using RBF neural network. IEEE Access 5, 21791-21805.

Uwagi

The work was funded by subsidy from the Polish Ministry of Science and Higher Education for the Faculty of Chemistry (A.B.) and Faculty of Electrical Engineering (M.K.) of Wroclaw University of Science and Technology.