人工神经网络在浮选工艺中的应用

doi:10.12034/j.issn.1009-606X.216338

摘要/Abstract

摘要： 人工神经网络作为一门新的技术科学，已成为世界各国的研究热点，得到了非常广泛的应用，在浮选测中也起着重要作用. 本工作总结了神经网络在浮选中的应用情况，介绍了浮选中常用的神经网络，分别对神经网络在浮选中的浮选参数预测、浮选柱系统等方面的应用进行综述，指出神经网络在浮选中应用的研究方向应该包括神经网络与多种算法结合、神经网络的改进和新的神经网络应用3个方面.

关键词: 人工神经网络, 浮选, 参数预测, 建模

Abstract: Artificial neural networks (ANN) as a new scientific technology has become a hot topic around the world. ANN has been extensively applied in technical fields related to the flotation model predictions. This paper summarizes the application of neural networks in flotation process, briefly presented common case which used the method of neural network, then summarized cases from the prediction the flotation parameters in flotation, flotation column system and ect. The paper suggested that the neural network combined with a variety of algorithms, the improvement of neural network and the new application of neural networks application of neural network in flotation will be new research direction in application of flotation.

Key words: Artificial neural network, Flotation, Parameter prediction, Modeling

赵敏捷方建军张琳代宗尧章伟. 人工神经网络在浮选工艺中的应用[J]. 过程工程学报, 2017, 17(3): 440-446.

Minjie ZHAO Jianjun FANG Lin ZHANG Zong DAI Zhangwei YAO. Applying-based artificial neural networks of flotation processes -A review[J]. Chin. J. Process Eng., 2017, 17(3): 440-446.

参考文献

[1]JIAO L C, YANG S Y, LIU F, et al. Seventy Years beyond Neural Networks: Retrospect and Prospect. Chinese Journal of Computers, 2016,39:1-22. (in chinese) [2]CHEN S P, QIAN S. History, Current Development and Trend of ANN. //Conference on Industrial Instrumentation and Automation. Shanghai, China, 2004: 63-66. (in chinese) [3]Delavar H M, Karamzadeh A, Pahlavanneshan S. Shining Light on the Sprout of Life: Optogenetics Applications in Stem Cell Research and Therapy. Journal of Membrane Biology, 2016:1-6. [4]ZHANG H J, MU Z C, LIU K. Ear Recognition Method Based on Independent Component Analysis. Pattern Recognition and Artificial Intelligence, 2006, 19(5):685-688. (in chinese) [5]DU H F, LI J C, GONG M G, et al. An Immune Clonal Seleetion Network and Its Learning Algorithm. Pattern Recognition and Artificial Intelligence, 2005, 18(2):198-204. (in chinese) [6]ZHANG L, HUANG S G, SHI Z X, et al. CAPTCHA Recognition Method Based on RNN of LSTM. Pattern Recognition and Artificial Intelligence, 2011, 24(1):40-47. (in chinese) [7]JIANG H L, SUN Y M. Study of Fault-Tolerance Estimation and Calculation Method for Feed Forward Neural Networks. Pattern Recognition and Artificial Intelligence, 2004, 17(2):201-206. (in chinese) [8]ZHANG L, CHENG J S. Loose Brain- A Mathematical Model of Swarm Intelligence. Pattern Recognition and Artificial Intelligence, 2003, 16(1):1-5. (in chinese) [9]Debnath A, Deb K, Chattopadhyay K K, et al. Methyl orange adsorption onto simple chemical route synthesized crystalline α-Fe2O3 nanoparticles: kinetic, equilibrium isotherm, and neural network modeling. Desalination & Water Treatment, 2015, 55(2):1-12. [10]Gastegger M, Kauffmann C, Behler J, et al. Comparing the accuracy of high-dimensional neural network potentials and the systematic molecular 18.fragmentation method: A benchmark study for all-trans alkanes. Journal of Chemical Physics, 2016, 144(19): 194110. [11]Baldi P, Bauer K, Eng C, et al. Jet Substructure Classification in High-Energy Physics with Deep Neural Networks. Physical Review D, 2016, 93(9):1-8. [12]Betti V, Aglioti S M. Dynamic construction of the neural networks underpinning empathy for pain. Neuroscience & Biobehavioral Reviews, 2016, 63:191-206. [13]Roth H, Lu L, Liu J, et al. Improving Computer-aided Detection using Convolutional Neural Networks and Random View Aggregation. IEEE Transactions on Medical Imaging, 2015, 28(9):1170-1181. [14]Dou Q, Chen H, L. Y U, et al. Automatic Detection of Cerebral Microbleeds from MR Images via 3D Convolutional Neural Networks. IEEE Transactions on Medical Imaging, 2016, 35(5):1182-1195. [15]MEI J T, HE R A, YANG W. Development and Application of KS-ⅡNew High Efficiency Flotation Reagents to Iron Ores // National Metal Mines Difficult Dressing and Low Grade Ore Beneficiation Technology Academic Exchange with Technology and Equipment Exhibition. Shenzhen, China, 2008: 208-210. (in chinese) [16]XU J B, XU Q G, ZHOU C G, et al. Development of Recurrent Neural Network. Control and Instruments in Chemical Industry, 2003, 30(1): 6-10.(in chinese) [17]Jovanovi? I, Miljanovi? I, Jovanovi? T. Soft computing-based modeling of flotation processes – A review. Minerals Engineering, 2015, 84:34-63. [18]FENG H Z. Control System Simulation. Beijing: Posts and Telecom Press, 2009. (in chinese) [19]Baliyan A, Gaurav K, Mishra S K. A Review of Short Term Load Forecasting using Artificial Neural Network Models. Procedia Computer Science, 2015, 48:121-125. [20]WANG X Q. Dielectric Loss Value Prediction Method Based on BP Neural Network. Electronic World, 2014(4):258-259. (in chinese) [21]CAO X F, YE Z, WAN J, et al. The Expermi entofFunction Smi ulation Based on Backpropagation Neuron Network. Research and Exploration in Laboratory, 2008, 27(5):34-38. (in chinese) [22]ZHANG X L. The advancement of vista of a neural network adaptive control. Industrial Instrumentation & Automation, 2002(1):10-14. (in chinese) [23]Kayhan G, Ozdemir A E, ?lyas Eminoglu. Reviewing and designing pre-processing units for RBF networks: initial structure identification and coarse-tuning of free parameters. Neural Computing & Applications, 2012, 22(7-8):1655-1666. [24]LI S J, LIU Y X, SONG S C, et al. Identification procedure of vibrating load parameters of hydraulic generator with RBF neural network. Journal of Dalian University of Technology, 2007, 47(1):6-10. (in chinese) [25]XIE G Y. Mineral Processing Technology. Xuzhou: China Mining University Press, 2001. (in chinese) [26]ZHAO H W, XIE Y F, JIANG C H, et al. An Intelligent Optimal Setting Approach Based on Froth Features for Level of Flotation Cells. Acta Automatica Sinica, 2014(6):1086-1097. (in chinese) [27]WANG X L, HUANG L, YANG P, et al. Dynamic RBF neural networks for model mismatch problem and its application in flotation process. CIESC Journal, 2016, 67(3):897-902. (in chinese) [28]TANG C H, LIU J P, CHEN Q, et al. pH control in flotation process based on prediction model. Control Theory & Applications, 2013, 30(7):885-890. (in chinese) [29]LIU Q, WANG B, YUAN W, et al. Prediction model of floatation recovery ratio for a gold mine. Journal of University of Science and Technology Beijing, 2014(11):1456-1461. (in chinese) [30]LI H B, ZHENG X P, CHAI T Y. Hybrid Intelligent Optimal Control in Flotation Processes. Journal of Northeastern University(Natural Science), 2012, 33(1):1-5. (in chinese) [31]SONG L Y, CHENG Y, LI Z F. Research of Dosing Control System Based on BP Neural Network. Computer Measurement & Control, 2012, 20(2):389-391. (in chinese) [32]Kalegowda Y, Harmer S L. Classification of time-of-flight secondary ion mass spectrometry spectra from complex Cu–Fe sulphides by principal component analysis and artificial neural networks. Analytica Chimica Acta, 2013, 759(1):21-27. [33]Wang A, Yan X, Wang L, et al. Effect of cone angles on single-phase flow of a laboratory cyclonic-static micro-bubble flotation column: PIV measurement and CFD simulations. Separation & Purification Technology, 2015, 149:308-314. [34]LIAO Y F, LIU J T, WANG Y T, et al. Prediction of gas holdup in cyclonic-static micro-bubble flotation column based on BP neural networks. Journal of China University of Mining & Technology, 2011, 40(3):443-447. (in chinese) [35]Li X B, Zhu W, Liu J T, et al. Gas holdup in cyclone-static micro-bubble flotation column. Environmental Technology, 2015, 37(7):1-32. [36]Mohanty S. Artificial neural network based system identification and model predictive control of a flotation column. Journal of Process Control, 2009, 19(6):991-999. [37]Nakhaei F, Mosavi M R, Sam A, et al. Recovery and grade accurate prediction of pilot plant flotation column concentrate: Neural network and statistical techniques. International Journal of Mineral Processing, 2012, s 110–111(8):140-154. [38]Chelgani S C, Shahbazi B, Rezai B. Estimation of froth flotation recovery and collision probability based on operational parameters using an artificial neural network. International Journal of Minerals, Metallurgy and Materials, 2010, 17(5):526-534. [39]Nakhaeie F, Sam A, Mosavi M R. Concentrate Grade Prediction in an Industrial Flotation Column Using Artificial Neural Network. Arabian Journal Forence & Engineering, 2012, 38(5):1011-1023. [40]Fardis N, Mehdi I. Application and comparison of RNN, RBFNN and MNLR approaches on prediction of flotation column performance. International Journal of Mining Science & Technology, 2015, 246(6):983-990. [41]Huang Y, Takaoka M, Takeda N. Chlorobenzenes removal from municipal solid waste incineration fly ash by surfactant-assisted column flotation. Chemosphere, 2003, 52(4):735-43. [42]Suarez S, Lema J M, Omil F. Pre-treatment of hospital wastewater by coagulation–flocculation and flotation. Bioresource Technology, 2009, 100(7): 2138-2146. [43]Sena R F D, Claudino A, Moretti K, et al. Biofuel application of biomass obtained from a meat industry wastewater plant through the flotation process—A case study. Resources Conservation & Recycling, 2008, 52(3):557-569. [44]M?kinen J, Bachér J, Kaartinen T, et al. The effect of flotation and parameters for bioleaching of printed circuit boards. Minerals Engineering, 2015, 75: 26-31. [45]Gallegos-Acevedo P M, Espinoza-Cuadra J, Olivera-Ponce J M. Conventional flotation techniques to separate metallic and nonmetallic fractions from waste printed circuit boards with particles nonconventional size. Journal of Mining Science, 2015, 50(5):974-981. [46]Vasseghian Y, Heidari N, Ahmadi M, et al. Simultaneous ash and sulfur removal from bitumen: Experiments and neural network modeling. Fuel Processing Technology, 2014, 125(125):79-85. [47]Sulbaran B. Deinking by flotation under neutral condition using fatty alcohol ethoxylates. Nordic Pulp & Paper Research Journal, 2016, 31(1):170-174. [48]Gao Y, Yuan X, Gao L, et al. Study on neutral chemical deinking of laser printed papers. TAPPI JOURNAL, 2016, 15(1): 49-57. [49]Ravi K, Schrinner T, Grossmann H, et al. Improving Adsorption Deinking by Identifying the Optimum Balance between Polymer Beads and Deinking Chemistry. BioResources, 2016, 11(1): 1664-1671. [50]Fernandez E O, Hodgson K T. Deinking flexographically printed papers: The effect of deinking chemicals on water clarification with cupric chloride. Appita Journal, 2014, 67(2):117-121. [51]Zeltner M, Toedtli L M, Hild N, et al. Ferromagnetic inks facilitate large scale paper recycling and reduce bleach chemical consumption.. Langmuir the Acs Journal of Surfaces & Colloids, 2013, 29(16):5093-5098. [52]Behin J. Deinking in bubble column and airlift reactors: Influence of wastewater of Merox unit as pulping liquor. Chemical Engineering Research & Design, 2012, 90(8):1045-1051. [53]Fricker A, Manning A, Thompson R. Deinking of indigo prints using high-intensity ultrasound. Surface Coatings International Part B Coatings Transactions, 2006, 89(2):145-155. [54]Pauck W J, Venditti R A, Pocock J, et al. Neural network modelling and prediction of the flotation deinking behaviour of recycled paper mixes. Nordic Pulp & Paper Research Journal, 2014, 29(29):521-532. [55]Wang J S, Han S. Feed-Forward Neural Network Soft-Sensor Modeling of Flotation Process Based on Particle Swarm Optimization and Gravitational Search Algorithm. Computational Intelligence & Neuroscience, 2015, 2015(6):1-10. [56]Esmaeili A. Comparison study of biosorption and coagulation/air flotation methods for chromium removal from wastewater: experiments and neural network modeling. Rsc Advances, 2015, 5(111):91776-91784. [57]Bhunia K. Prediction of Gas Holdup in Flotation Column by Artificial Neural Network. International Journal of Coal Preparation & Utilization, 2015, 35(4):165-175. [58]Hosseini M R, Shirazi H H A, Mehrshad M M N. Modeling the Relationship Between Froth Bubble Size and Flotation Performance Using Image Analysis and Neural Networks. Chemical Engineering Communications, 2015, 202(7):911-919. [59]Jahedsaravani A, Marhaban M H, Massinaei M. Prediction of the metallurgical performances of a batch flotation system by image analysis and neural networks. Minerals Engineering, 2014, 69(8):137-145. [60]T. Gouri Charan, V. K. Kalyani, K. K. Sharma, et al. Use of an Artificial Neural Network to Evaluate the Oleo-Flotation Process to Treat Coal Fines. International Journal of Coal Preparation & Utilization, 2014, 34(5):435-52. [61]Mashevskiy G N, Romanenko S A. Copper-pyrite ores flotation cleaning cycle mathematical model. 2014,4:27-33. [62]Nakhaei F, Irannajad M. Comparison Between Neural Networks and Multiple Regression Methods in Metallurgical Performance Modeling of Flotation Column . Fizykochemiczne Problemy Mineralurgii - Physicochemical Problems of Mineral Processing, 2013, 49(1):255-266. [63]Romanenko S A. Effectiveness of multisensor ionometry systems and neural network modeling methods application in flotation processes laboratory studies. Analytica Chimica Acta, 1979, 108(01):315-323. [64]Mashevsky G N, Petrov A V, Romanenko S A, et al. Development of ore types processing classification principles on the basis of flotation process parameters control and neural network modeling. International Scholarly Research Notices, 2015, 2015(5):1-11. [65]Wang R. Neural Network and Support Vector Machines in Slime Flotation Soft Sensor Modeling Simulation Research. Communications in Computer & Information Science, 2011, 237:506-513. [66]Nakhaei F, Sam A, Mosavi M R, et al. Prediction of copper grade at flotation column concentrate using Artificial Neural Network// IEEE, International Conference on Signal Processing. IEEE, 2010:1421-1424. [67]Estrada-Ruiz R H, Peérez-Garibay R. Neural networks to estimate bubble diameter and bubble size distribution of Dotation froth surfaces. Journal of the Southern African Institute of Mining & Metallurgy, 2009, 109(7):441-446. [68]V. K. Kalyani, Pallavika, Sanjay Chaudhuri, et al. Study of a laboratory-scale froth flotation process using artificial neural networks. Mineral Processing & Extractive Metallurgy Review An International Journal, 2007, 29(2):130-142. [69]ZHAO H W, XIE Y F, CAO B F, et al. The Extraction and Application of Froth Texture Feature based On Gabor Wavelets and LPP in Flotation Process. Journal of Shanghai Jiao Tong University, 2014, 48(7):942-947. (in chinese) [70]Jorjani E, Poorali H A, Sam A, et al. Prediction of coal response to froth flotation based on coal analysis using regression and artificial neural network. Minerals Engineering, 2009, 22(11):970-976. [71]Massinaei M, Doostmohammadi R.Modeling of bubble surface area flux in an industrial rougher column using artificial neural network and statistical techniques. Minerals Engineering, 2010, 23(2):83-90. [72]Al-Thyabat S. Investigating the effect of some operating parameters on phosphate flotation kinetics by neural network. Advanced Powder Technology, 2009, 20(4):355-360. [73]ZHANG C, WANG X, WANG K, et al.Optimization of Weld Strength for Laser Transmission Welding of Thermoplastic -based on the Response Surface Methodology and Based Algorithm and Artificial Neural Network. Chinese Journal of Lasers, 2011(11):110-116. (in chinese) [74]ZHOU M. Principle and Application of Genetic Algorithm. Beijing: National Defence Industry Press, 1999. (in chinese) [75]HEI G. Neural Network Design. Beijing: China Machine Press, 2002. (in chinese) [76]Motamedi M, Bathaie S Z, Hemmateenejad B, et al. Optimisation of metallurgical performance of industrial flotation column using neural network and gravitational search algorithm. Canadian Metallurgical Quarterly, 2013, 52(2):115-122. [77]Wang J S, Han S, Shen N N, et al. Features extraction of flotation froth images and BP neural network soft-sensor model of concentrate grade optimized by shuffled cuckoo searching algorithm.. Thescientificworldjournal, 2014, (2014):1-17. [78]WU M X, ZHANG X L, WEN S H, et al. Summarization of BP Neural Network's Improvement. Journal of Taiyuan University of Science and Technology,2005, 26(2):120-125. (in chinese)