A dynamic size-based time series feature and application in identification of zinc flotation working conditions

Abstract

Conventional feature description methods have large errors in froth features due to the fact that the image during the zinc flotation process of froth flotation is dynamic, and the existing image features rarely have time series information. Based on the conventional froth size distribution characteristics, this paper proposes a size trend core feature (STCF) considering the froth size distribution, i.e., a feature centered on the time series of the froth size distribution. The core features of the trend are extracted, the inter-frame change factor and the inter-frame stability factor are given and two calculation methods of the feature factors are proposed. Meanwhile, the STCF feature algorithm was established based on the core features by adding the inter-frame change factor and the inter-frame stability factor. Finally, a flotation condition recognition model based on BP neural network was established. The experiments show that the recognition model has achieved excellent results, proving that the method proposed effectively overcomes the limitation of the lack of dynamic information in the existing traditional size distribution features and the introduction of the two factors can improve the classification accuracy to varying degrees.

Keywords

froth flotation process / froth size distribution / working condition identification

References

[1] AldrichC, MaraisC, SheanB J, CilliersJ J. Online monitoring and control of froth flotation systems with machine vision: A review [J]. International Journal of Mineral Processing, 2010, 96(1–4): 1-13

[2] ZhangJ, TangZ, AiM, GuiW. Nonlinear modeling of the relationship between reagent dosage and flotation froth surface image by Hammerstein-Wiener model [J]. Minerals Engineering, 2018, 120: 19-28

[3] ZhangW, NessetJ E, FinchJ A. A novel approach to prevent bubble coalescence during measurement of bubble size in flotation [J]. Journal of Central South University, 2014, 21(1): 338-343

[4] LiuJ, GuiW, TangZ, YangC, ZhuJ, LiJ. Recognition of the operational statuses of reagent addition using dynamic bubble size distribution in copper flotation process [J]. Minerals Engineering, 2013, 45: 128-141

[5] WANG J, ZHANG J, TIAN J, ZHANG D, LIU X. The method for froth floatation condition recognition based on adaptive feature weighted [C]// Pattern Recognition & Computer Vision. 2018. DOI: https://doi.org/10.1080/18756891.2013.809938.

[6] LiuJ, GuiW, TangZ, HuH, ZhuJ. Machine vision based production condition classification and recognition for mineral flotation process monitoring [J]. International Journal of Computational Intelligence Systems, 2013, 6(5): 969-986

[7] FuY, AldrichC. Froth image analysis by use of transfer learning and convolutional neural networks [J]. Minerals Engineering, 2018, 115: 68-78

[8] KaartinenJ, HatonenJ, HyotyniemiH, MiettunenJ. Machine-vision-based control of zinc flotation—A case study [J]. Control Engineering Practice, 2006, 14(12): 1455-1466

[9] WanX, ChenX, GuiW, YueW, XieY. A novel shapelet transformation method for classification of multivariate time series with dynamic discriminative subsequence and application in anode current signals [J]. Journal of Central South University, 2020, 27(1): 114-131

[10] O’ConnorC T, RandallE W, GoodallC M. Measurement of the effects of physical and chemical variables on bubble size [J]. International Journal of Mineral Processing, 1990, 28(12): 139-149

[11] LiJ, YangC, ZhuH. Improved image enhancement method for flotation froth image based on parameter extraction [J]. Journal of Central South University of Technology, 2013, 20(6): 1602-1609

[12] FuY, AldrichC. Flotation froth image analysis by use of a dynamic feature extraction algorithm [C]// Proceedings of the 17th IFAC Symposium on Control, Optimization and Automation in Mining, Mineral and Metal Processing (MMM 2016). Vienna, Austria, 2016, 49(20): 84-89

[13] ZhaoG, PietikainenM. Dynamic texture recognition using local binary patterns with an application to facial expressions [J]. IEEE Transactions on Pattern Analysis and Machine Intelligence, 2007, 29: 915-928

[14] ZhangH, TangZ, XieY, GaoX, GuiW. A similarity-based burst bubble recognition using weighted normalized cross correlation and chamfer distance [J]. IEEE Transactions on Industrial Informatics, 2019, 16(6): 4077-4089

[15] YANG C, XU C, GUI W, DU J. Nonparametric density estimation of bubble size distribution for monitoring mineral flotation process [C]// IEEE Conference on Decision & Control. IEEE, 2009. DOI: https://doi.org/10.1109/CDC.2009.5399975.

[16] ZhouK J, YangC H, GuiW H, XuC H. Clustering-driven watershed adaptive segmentation of bubble image [J]. Journal of Central South University of Technology, 2010, 17(5): 1049-1057

[17] JianqiL, ChunhuaY, BinfangC, LiJ, YangC, CaoB, ZhuQ, LiuJ. Improved watershed segmentation method for flotation froth image based on parameter measurement [J]. Chinese Journal of Scientific Instrument, 2013, 34(6): 1233-1240

[18] ZhangH, TangZ, XieY, GaoX, ChenQ. A watershed segmentation algorithm based on an optimal marker for bubble size measurement [J]. Measurement, 2019, 138: 182-193

[19] RiquelmeA, DesbiensA, VillarR D, et al.. Predictive control of the bubble size distribution in a two-phase pilot flotation column [J]. Minerals Engineering, 2016, 89: 71-76

[20] FALOUTSOS C. Fast time sequence indexing for arbitrary Lp norms [C]// Proc International Conference on VLDB. Cairo, Egypt. 2000: 385–394.

[21] KeoghE, ChakrabartiK, PazzaniM, MehrotraS. Dimensionality reduction for fast similarity search in large time series databases [J]. Knowledge and Information Systems, 2002, 3(3): 263-286

[22] KohonenT. An introduction to neural computing [J]. Neural Networks, 1988, 1(1): 3-16

[23] ZHAO G, HUANG H, LU X. Discriminating earthquakes and explosion events by seismic signals basing on BP-Adaboost classifier [C]// 2016 2nd IEEE International Conference on Computer and Communications (ICCC). IEEE, 2016. DOI: https://doi.org/10.1109/CompComm.2016.7925045.

[24] ZhangJ, TangZ, XieY, AiM, GuiW. Convolutional memory network-based flotation performance monitoring [J]. Minerals Engineering, 2020, 151106332

[25] WangZ. LS-SVM Recognition of fruit using in harvesting robot based on RIO-HOG feature [J]. Applied Mathematics & Information Sciences, 2017, 11(2): 489-495