A strip thickness prediction method of hot rolling based on D_S information reconstruction

Abstract

To improve prediction accuracy of strip thickness in hot rolling, a kind of Dempster/Shafer(D_S) information reconstitution prediction method (DSIRPM) was presented. DSIRPM basically consisted of three steps to implement the prediction of strip thickness. Firstly, ibaAnalyzer was employed to analyze the periodicity of hot rolling and find three sensitive parameters to strip thickness, which were used to undertake polynomial curve fitting prediction based on least square respectively, and preliminary prediction results were obtained. Then, D_S evidence theory was used to reconstruct the prediction results under different parameters, in which basic probability assignment (BPA) was the key and the proposed contribution rate calculated using grey relational degree was regarded as BPA, which realizes BPA selection objectively. Finally, from this distribution, future strip thickness trend was inferred. Experimental results clearly show the improved prediction accuracy and stability compared with other prediction models, such as GM(1,1) and the weighted average prediction model.

Keywords

grey relational degree / GM(1,1) model / Dempster/Shafer (D_S) method / least square method / thickness prediction

References

[1] GHEORGHIESC, CONDURACHE-BOTAS. Temperature correction for thickness measurements of hot rolled steel plates [J]. Journal of Iron and Steel Research, International, 2010, 17(12): 23-29

[2] de SOUZAE, SILVAE G, LEGEYL F L, de SOUZAE, SILVAE A. Forecasting oil price trends using wavelets and hidden Markov models [J]. Energy Economics, 2010, 32(6): 1507-1519

[3] KIMJ, LEEJ, HWANGS M. An analytical model for the prediction of strip temperatures in hot strip rolling [J]. International Journal of Heat and Mass Transfer, 2009, 52(7): 1864-1874

[4] GONGH, WUY-x, LIAOKai. Prediction model of residual stress field in aluminum alloy plate [J]. Journal of Central South University of Technology, 2011, 18(2): 285-289

[5] MOLNÁRV, FEDORKOG, STEHLÍKOVÁB, MICHALIKBP, WEISZERAM. A regression model for prediction of pipe conveyor belt contact forces on idler rolls [J]. Measurement, 2013, 46(10): 3910-3917

[6] CHENX-g, LIUS-y, ZHANGC-w, ZHUJ-long. Improved measurement accuracy in optical scatterometry using fitting error interpolation based library search [J]. Measurement, 2013, 46(8): 2638-2646

[7] PARKD, KOLIVANDM, KAHRAMANA. An approximate method to predict surface wear of hypoid gears using surface interpolation [J]. Mechanism and Machine Theory, 2014, 71: 64-78

[8] ZHANGL, GUT-q, ZHAOJ, JIS-j, SUNQ-z, HUMing. An adaptive moving total least squares method for curve fitting [J]. Measurement, 2014, 49: 107-112

[9] GUOX, ZHANGX-t, ZUOY-j, FUS-qiang. Application of precision in land updating investigation by least squares polynomial fitting algorithm [J]. Surveying and Mapping of Geology and Mineral Resources, 2013, 29(1): 14-16

[10] CHACÓNJ, IRIGARAYC, FERNANDEZT, EL HAMDOUNIR. Engineering geology maps: landslides and geographical information systems [J]. Bulletin of Engineering Geology and the Environment, 2006, 65(4): 341-411

[11] ZHANGY, ZHAOBing. Application of grey correlation analysis with support vector machine in near-infrared spectroscopy [J]. Spectroscopy and Spectral Analysis, 2013, 33(2): 363-366

[12] HUANGH-p, HUANGS-c, CHENJ-t, WANGR-chuan. Image hiding algorithm in discrete cosine transform domain based on grey prediction and grey relational analysis [J]. China Communications, 2013, 10(7): 57-70

[13] YINJ-c, WANGN-ni. Online grey prediction of ship roll motion using variable RBFN [J]. Applied Artificial Intelligence, 2013, 27(10): 941-960

[14] ZHOUY, ZHANGX-j, HANMing. The application of gray relational analysis in the classification of Karst stability [J]. Journal of Wuhan University of Technology, 2012, 34(5): 117-121

[15] DONGS-y, XIAQ-g, LINing. Research on software defect list: Prediction method based on grey relational analysis [J]. Computer Engineering and Applications, 2013, 49(2): 67-71

[16] YAOQ-f, LIC-f, MAH-l, ZHANGSenNovel network traffic forecasting algorithm based on grey model and Markov chain [J], 2007, 34(4): 396-400

[17] LIUH-b, XIANGY-m, RUANY-xing. A multivariable grey model based on background value optimization and its application to subgrade settlement prediction [J]. Applied Mechanics and Materials, 2013, 34(1): 1721-1725

[18] WANGM-h, HUNGC-pao. Novel grey model for the prediction of trend of dissolved gases in oil-filled power apparatus [J]. Electric Power Systems Research, 2003, 67(1): 53-58

[19] JIANGH, HEW-wu. Grey relational grade in local support vector regression for financial time series prediction [J]. Expert Systems with Applications, 2012, 39(3): 2256-2262

[20] JIMÉNEZT F. Estimation of parameters of the shifted Gompertz distribution using least squares, maximum likelihood and moments methods [J]. Journal of Computational and Applied Mathematics, 2014, 255: 867-877

[21] WEIG-wu. Grey relational analysis method for 2-tuple linguistic multiple attribute group decision making with incomplete weight information [J]. Expert Systems with Applications, 2011, 38(5): 4824-4828

[22] CHENL-w, WANGW-h, ZHANGW-jun. Risk evaluation of regional collapses geological hazard based on D-S evidence theory [J]. Energy Procedia, 2012, 16: 371-376

[23] LID C, CHANGC J, CHENW C, CHENC C. An extended grey forecasting model for omnidirectional forecasting considering data gap difference [J]. Applied Mathematical Modelling, 2011, 35(10): 5051-5058

[24] ZHAOZ, WANGJ-z, ZHAOJ, SUZ-yue. Using a grey model optimized by differential evolution algorithm to forecast the per capita annual net income of rural households in China [J]. Omega, 2012, 40(5): 525-532

[25] MAW-m, ZhuX-x, WANGM-miao. Forecasting iron ore import and consumption of China using grey model optimized by particle swarm optimization algorithm [J]. Resources Policy, 2013, 38(4): 613-620