2.793

                    2018影響因子

                    (CJCR)

                    • 中文核心
                    • EI
                    • 中國科技核心
                    • Scopus
                    • CSCD
                    • 英國科學文摘

                    留言板

                    尊敬的讀者、作者、審稿人, 關于本刊的投稿、審稿、編輯和出版的任何問題, 您可以本頁添加留言。我們將盡快給您答復。謝謝您的支持!

                    姓名
                    郵箱
                    手機號碼
                    標題
                    留言內容
                    驗證碼

                    基于多模態特征子集選擇性集成建模的磨機負荷參數預測方法

                    劉卓 湯健 柴天佑 余文

                    劉卓, 湯健, 柴天佑, 余文. 基于多模態特征子集選擇性集成建模的磨機負荷參數預測方法. 自動化學報, 2020, 46(x): 1?12 doi: 10.16383/j.aas.c190735
                    引用本文: 劉卓, 湯健, 柴天佑, 余文. 基于多模態特征子集選擇性集成建模的磨機負荷參數預測方法. 自動化學報, 2020, 46(x): 1?12 doi: 10.16383/j.aas.c190735
                    LIU Zhuo, TANG Jian, CHAI Tian-Yo, YU Wen. Selective ensemble modeling approach for mill load parameter forecasting based on multi-modal feature sub-sets. Acta Automatica Sinica, 2020, 46(x): 1?12 doi: 10.16383/j.aas.c190735
                    Citation: LIU Zhuo, TANG Jian, CHAI Tian-Yo, YU Wen. Selective ensemble modeling approach for mill load parameter forecasting based on multi-modal feature sub-sets. Acta Automatica Sinica, 2020, 46(x): 1?12 doi: 10.16383/j.aas.c190735

                    基于多模態特征子集選擇性集成建模的磨機負荷參數預測方法

                    doi: 10.16383/j.aas.c190735
                    基金項目: 國家自然科學基金(61703089, 61803191, 61673097), 中央高?;究蒲袠I務費專項資金項目(N17080400), 礦冶過程自動控制技術國家重點實驗室, 礦冶過程自動控制技術北京市重點實驗室(BGRIMM-KZSKL-2018-06)
                    詳細信息
                      作者簡介:

                      劉卓:博士, 東北大學流程工業綜合自動化國家重點實驗室講師. 主要研究方向為復雜工業過程建模. E-mail: liuzhuo@ise.neu.edu.cn

                      湯?。罕本┕I大學教授. 主要研究方向為小樣本數據建模、城市固廢自動化處理等. 本文通訊作者. E-mail: freeflytang@bjut.edu.cn

                      柴天佑:中國工程院院士, 東北大學教授. IEEE Fellow, IFAC Fellow, 歐亞科學院院士. 主要研究方向為自適應控制, 智能解耦控制, 流程工業綜合自動化理論、方法與技術. E-mail: ychai@mail.neu.edu.cn

                      余文:墨西哥國立理工大學高級研究中心自動化部教授. 主要研究方向為復雜工業過程建模與控制, 機器學習. E-mail: yuw@ctrl.cinvestav.mx

                      通訊作者:

                      湯健, freeflytang@bjut.edu.cn

                    Selective Ensemble Modeling Approach for Mill Load Parameter Forecasting Based on Multi-modal Feature Sub-sets

                    Funds: Supported by National Natural Science Foundation of P. R. China (61703089, 61803191, 61673097), the Fundamental Research Funds for the Central Universities (N17080400), National & Beijing Key Laboratory of Process Automation in Mining & Metallurgy(BGRIMM-KZSKL-2018-06)
                    • 摘要: 如何融合球磨機系統研磨過程所產生的多模態機械信號構建磨機負荷參數預測(MLPF)模型是當前研究的熱點問題. 針對上述問題, 本文提出一種基于多模態特征子集選擇性集成(SEN)建模的MLPF方法. 首先, 對多模態機械信號進行時頻域變換得到高維頻譜數據; 接著, 采用相關系數法和互信息法對多模態頻譜進行線性和非線性特征子集的自適應選擇; 最后, 采用優化和加權算法對上述特征子集的候選子模型進行自適應地選擇與合并, 得到基于SEN機制的MLPF模型. 采用磨礦過程實驗球磨機的機械信號仿真驗證了所提方法的有效性.
                    • 圖  1  磨機系統不同位置機械信號的產生機理示意圖

                      Fig.  1  Generation mechanism of mechanical signals in different position of mill system

                      圖  2  建模策略

                      Fig.  2  The proposed modeling strategy

                      圖  3  實驗球磨機傳感器布置示意圖

                      Fig.  3  Layout of sensors for experimental ball mill

                      圖  4(a)  模態Ch1的頻譜變量與MBVR間的相關系數和互信息值

                      Fig.  4(a)  Correlation coefficient and mutual information value between spectrum variable of mode ch1 and MBVR

                      圖  4(b)  模態Ch6的頻譜變量與MBVR間的相關系數和互信息值

                      Fig.  4(b)  Correlation coefficient and mutual information value between spectrum variable of mode ch6 and MBVR

                      圖  4(c)  模態Ch8的頻譜變量與MBVR間的相關系數和互信息值

                      Fig.  4(c)  Correlation coefficient and mutual information value between spectrum variable of mode ch8 and MBVR

                      表  1  面向PD的不同模態頻譜特征的特征選擇系數統計表

                      Table  1  Coefficients Statistical table of different modal spectrum feature for PD

                      類別Ch1Ch2Ch3Ch4Ch5Ch6Ch7Ch8
                      線性特征選擇系數Min0.090500.0078680.36780.0050180.00019940.0095960.0020750.8741
                      線性特征選擇系數Max1.28971.73511.19131.39045.28831.26492.05641.0571
                      非線性特征選擇系數Min0.66440.56590.88130.84030.57180.70390.48600.9228
                      非線性特征選擇系數Max1.07151.08851.16801.13041.35561.13521.6231.0599
                      下載: 導出CSV

                      表  2  候選子模型編碼

                      Table  2  Coding of candidate sub-models

                      序號子模型特點子模型名稱子模型編碼多模態通道編號
                      1lin_linCorr-PLS1-81-Ch1, 2-Ch2, 3-Ch3, 4-Ch4, 5-Ch5, 6-Ch6, 7-Ch7, 8-Ch8
                      2nonlin_linMi-PLS9-169-Ch1, 10-Ch2, 11-Ch3, 12-Ch4, 13-Ch5, 14-Ch6, 15-Ch7, 16-Ch8
                      3lin_nonlinCorr-RWNN17-2417-Ch1, 18-Ch2, 19-Ch3, 20-Ch4, 21-Ch5, 22-Ch6, 23-Ch7, 24-Ch8
                      4nonlin_nonlinMi-RWNN25-3225-Ch1, 26-Ch2, 27-Ch3, 28-Ch4, 29-Ch5, 30-Ch6, 31-Ch7, 32-Ch8
                      下載: 導出CSV

                      表  3  不同特征選擇系數時所構建的SEN模型的預測誤差和所選擇的子模型編號

                      Table  3  Prediction error of SEN model with different feature selection coefficients and selected sub-model number

                      序號MBVRPDCVR
                      測試誤差集成子模型編號測試誤差集成子模型編號測試誤差集成子模型編號
                      10.05330{ 21 23 27 31 17 32 19 24 30}0.01579{26 18 30}0.01083{14 19 26 18 30 22}
                      20.06204{14 31 32 24 27 30}0.01805{25 10 31 32 14 19 24 18 30}0.009697{27 26 22 30}
                      30.04515{9 17 26 14 30 27 22 32 19 24}0.01855{24 14 18 30 26}0.01146{27 14 19 26 31 18 30 22}
                      40.04717{23 17 27 19 32 24 30}0.01582{14 24 26 27 32 30}0.009544{19 30 22}
                      50.05231{27 17 30 23 19 32 24}0.01843{24 14 25 22 18 19 30}0.01093{20 14 31 27 32 19 26 22 30}
                      60.04433{31 22 30 32 19 24}0.01452{22 14 24 32 26 19 30}0.009930{23 25 20 18 32 27 26 19 30 22}
                      70.05697{31 32 24}0.01627{26 22 18 24 32 19 30}0.009870{6 20 28 19 32 18 26 27 22 30}
                      80.04459{27 26 23 22 31 25 30 17 32 24}0.01687{27 18 32 19 30}0.009280{28 18 26 27 19 22 30}
                      90.04969{26 32 27 30 25 19 24}0.01718{2 18 27 6 26 32 25 30}0.009650{18 32 26 25 27 19 30 22}
                      100.04624{22 17 26 27 30 25 32 19 31 24}0.01748{25 26 22 32 27 6 18 19 30}0.01212{22 30}
                      110.04404{25 17 18 27 22 19 30 24}0.01769{17 23 22 26 27 6 30 19 18}??
                      下載: 導出CSV

                      表  4  磨機負荷參數各通道與多模態特征子集選擇性集成模型的測試誤差比較

                      Table  4  Comparison of test errors between various channels of mill load parameters and multi-modal feature subset SEN model

                      RMSREs備注
                      MBVRPDCVR
                      Corr-PLSMi-PLSCorr-RWNNMi-RWNNCorr-PLSMi-PLSCorr-RWNNMi-RWNNCorr-PLSMi-PLSCorr-RWNNMi-RWNN
                      Ch10.19240.34260.13140.15030.067100.054110.069100.051610.059110.066220.070300.04930筒體振動
                      Ch20.32130.72070.31030.14010.042210.044300.033210.037510.056500.047110.037110.02620筒體振動
                      Ch30.44010.44310.091120.090200.120120.076110.031110.052100.11320.078310.029220.03810筒體振聲
                      Ch40.51250.42250.28220.20010.11420.086200.064600.11840.074420.069100.041100.04772筒體振聲
                      Ch50.46110.34090.19110.22210.10870.081220.11610.098100.097110.096100.044400.09911軸承振動
                      Ch60.31050.21410.14310.13410.044100.037200.035200.024310.035200.036410.016300.01720軸承振動
                      Ch70.38020.25020.13210.11010.10830.062410.061210.056110.094510.048110.049100.04141軸承振動
                      Ch80.59340.60310.080900.36310.09710.079100.033100.032200.14210.089300.068400.03730研磨振聲
                      本文方法0.044040.014520.00928
                      下載: 導出CSV

                      表  5  磨機負荷參數各通道與多模態特征子集選擇性集成模型的平均測試誤差比較

                      Table  5  Average test errors comparison of the various channels of mill load parameters and multi-modal feature subset SEN model

                      通道MBVRPDCVR平均預測誤差備注
                      Ch10.13140.051610.049300.07740筒體振動
                      Ch20.14010.033210.026200.06650筒體振動
                      Ch30.090200.031110.029220.05020筒體振聲
                      Ch40.20010.064600.041100.1019筒體振聲
                      Ch50.19110.081220.044400.1056軸承振動
                      Ch60.13410.024310.016300.05820軸承振動
                      Ch70.11010.056110.041410.06920軸承振動
                      Ch80.080900.032200.037300.05010研磨振聲
                      本文方法0.044040.014520.009280.02260
                      下載: 導出CSV
                      360彩票
                    • [1] 1 Zhou Ping, Chai Tian-You, Wang Hong. Intelligent optimal-setting control for grinding circuits of mineral processing. IEEE Transactions on Automation Science and Engineering, 2009, 6(4): 730?743 doi: 10.1109/TASE.2008.2011562
                      [2] 柴天佑. 復雜工業過程運行優化與反饋控制. 自動化學報, 2013, 39(11): 1744?1757 doi: 10.3724/SP.J.1004.2013.01744

                      2 Chai Tian-You. Operational optimization and feedback control for complex industrial processes. Acta Automatica Sinica, 2013, 39(11): 1744?1757 doi: 10.3724/SP.J.1004.2013.01744
                      [3] 3 Kano M, Fujiwara K. Virtual sensing technology in process industries: trends & challenges revealed by recent industrial applications. Journal of Chemical Engineering of Japan, 2013, 46(1): 1?17
                      [4] 湯健, 趙立杰, 岳恒, 柴天佑. 磨機負荷檢測方法研究綜述. 控制工程, 2010, 17(5): 565?570 doi: 10.3969/j.issn.1671-7848.2010.05.001

                      4 Tang Jian, Zhao Li-Jie, Yue Heng, Chai Tian-You. Present status and future developments of detection method for mill load. Control Engineering of China, 2010, 17(5): 565?570 doi: 10.3969/j.issn.1671-7848.2010.05.001
                      [5] 湯健, 喬俊飛, 劉卓, 周曉杰, 余剛, 趙建軍. 磨礦過程球磨機研磨機理數值仿真及磨機負荷參數軟測量綜述. 北京工業大學學報, 2018, 44(11): 1459?14

                      5 Tang Jian, Qiao Jun- Fei, Liu Zhuo, Zhou Xiao-Jie Yu Gang, Zhao Jian-Jun. Review of Ball Mill Grinding Mechanism Numerical Simulation and Mill Load Parameters Soft Measurement for Mineral Grinding Process. Journal of Beijing University of Technology, 2018, 44(11): 1459?14
                      [6] 6 Baltrusaitis T, Ahuja C, Morency L P. Multimodal Machine Learning: A Survey and Taxonomy. IEEE Transactions on Pattern Analysis and Machine Intelligence, 2019, 41(2): 423?443 doi: 10.1109/TPAMI.2018.2798607
                      [7] 7 Huang Peng, Jia Min-Ping, Zhong Bing-Lin. Investigation on measuring the fill level of an industrial ball mill based on the vibration characteristics of the mill shell. Minerals Engineering, 2009, 14: 1200?1208
                      [8] 8 Das, Sarada Prasad, Das, Debi Prasad, Behera, Santosh Kumar, Mishra, Barada Kanta. Interpretation of mill vibration signal via wireless sensing. Minerals Engineering, 2011, 24: 245?251 doi: 10.1016/j.mineng.2010.08.014
                      [9] 馮天晶, 王煥鋼, 徐文立, 徐寧. 基于筒壁振動信號的磨機工況監測系統. 礦冶, 2010, 19(2): 66?69 doi: 10.3969/j.issn.1005-7854.2010.02.018

                      9 Feng Tian-Jing, Wang Huan-Gang, Xu Wen Li, Xu Ning. An on-line mill load monitoring system based on shell vibration signals. Mining & Metallurgy, 2010, 19(2): 66?69 doi: 10.3969/j.issn.1005-7854.2010.02.018
                      [10] 湯健, 喬俊飛, 柴天佑, 劉卓, 吳志偉. 基于虛擬樣本生成技術的多組分機械信號建模. 自動化學報, 2018, 44(9): 1569?1589

                      10 Tang Jian, Qiao Jun-Fei, Chai Tian-You, Liu Zhuo, Wu Zhi-Wei. Modeling Multiple Components Mechanical Signals by Means of Virtual Sample Generation Technique. Acta Automatica Sinica, 2018, 44(9): 1569?1589
                      [11] 湯健, 田福慶, 賈美英, 李東. 基于頻譜數據驅動的旋轉機械設備負荷軟測量[M], 國防工業出版社, 2015年6月, 北京

                      Tang Jian, Tian Fu-Qing, Jia Mei-Ying. Soft Measurement of Rotating Machinery Equipment Load Based on Spectrum Data Drive. Beijing: National Defense Industry Press, 2015.
                      [12] Hasnat A, Molla A U. Feature selection in cancer microarray data using multi-objective genetic algorithm combined with correlation coefficient[C]//Emerging Technological Trends (ICETT), International Conference on. IEEE, 2016: 1−6.
                      [13] Coelho F, Braga A P, Verleysen M. Multi-Objective Semi-Supervised Feature Selection and Model Selection Based on Pearson’s Correlation Coefficient[C]// Iberoamerican Congress Conference on Progress in Pattern Recognition. Springer-Verlag, 2010.
                      [14] Malji P, Sakhare S. Significance of entropy correlation coefficient over symmetric uncertainty on FAST clustering feature selection algorithm[C]//Intelligent Systems and Control (ISCO), 201711th International Conference on. IEEE, 2017: 457−463.
                      [15] 15 Vergara J R, Estévez P A. A review of feature selection methods based on mutual information. Neural computing and applications, 2014, 24(1): 175?186 doi: 10.1007/s00521-013-1368-0
                      [16] 16 Battiti R. Using mutual information for selecting features in supervised neural net learning. Neural Networks IEEE Transactions on, 1994, 5(4): 537?550 doi: 10.1109/72.298224
                      [17] 17 Jain A K, Duin R P W, Mao J. Statistical pattern recognition: A review. IEEE Transactions on pattern analysis and machine intelligence, 2000, 22(1): 4?37 doi: 10.1109/34.824819
                      [18] 18 Fleuret F. Fast binary feature selection with conditional mutual information. Journal of Machine Learning Research, 2004, 5(Nov): 1531?1555
                      [19] Gavin Brown, Jeremy Wyatt, Rachel Harris, Xin Yao. Diversity creation methods: a survey and categorisation[J]. Information Fusion 6(2005) 5-20
                      [20] 20 Tang Jing, Chai Tian-You, Yu Wen, Liu Zhuo, Zhou Xiao-Jie. A Comparative study that measures ball mill load parameters through different single-scale and multi-scale frequency spectra-based approaches. IEEE Transactions on Industrial Informatics, 2016, 12(6): 2008?2019 doi: 10.1109/TII.2016.2586419
                      [21] 湯健, 柴天佑, 叢秋梅, 劉卓, 余文. 選擇性融合多尺度筒體振動頻譜的磨機負荷參數建模. 控制理論與應用, 2015, 32(12) doi: 10.7641/CTA.2015.14049

                      21 Tang Jian, Chai Tian-You, Cong qiu-mei, Liu Zhuo, Yu wen. Modeling mill load parameters based on selective fusion of multi-scale shell vibration frequency spectra. Control theory & Applications, 2015, 32(12 doi: 10.7641/CTA.2015.14049
                      [22] 22 Tang Jian, Qiao Jun-fei, Wu Zhi-Wei, Chai Tian-You, Zhang Jian, Yu Wen. Vibration and acoustic frequency spectra for industrial process modeling using selective fusion multi-condition samples and multi-source features. Mechanical Systems & Signal Processing, 2018, 99: 142?168
                      [23] 23 Pao, Y. H., & Takefuji, Y. Functional-link net computing: theory, system architecture, and functionalities. Computer, 1992, 25(5): 76?79 doi: 10.1109/2.144401
                      [24] 24 Pao, Y. H., Park, G. H., & Sobajic, D. J. Learning and generalization characteristics of the random vector functional-link net. Neurocomputing, 1994, 6(2): 163?180 doi: 10.1016/0925-2312(94)90053-1
                      [25] 湯健, 趙立杰, 柴天佑, 岳恒. 基于振動頻譜的磨機負荷在線軟測量建模. 信息與控制, 2012, 41(1): 123?128

                      25 Tang Jian, Zhao Li-Jie, Chai Tian-You, Yue Heng. On-line Soft-sensing Modelling of Mill Load Based on Vibration Spectrum. Information and Control, 2012, 41(1): 123?128
                      [26] 賀敏, 湯健, 郭旭琦, 閻高偉. 基于流形正則化域適應隨機權神經網絡的濕式球磨機負荷參數軟測量. 自動化學報, 2019, 45(2): 398?406

                      26 He Min, Tang Jing, Guo Xu-Qi, Yan Gao-Wei. Soft sensor for ball mill load based on DAMRRWNN model. Acta Automatica Sinica, 2019, 45(2): 398?406
                      [27] 閻高偉, 賀敏, 湯健, 韓東升. 基于最大均值差異多源域遷移學習的濕式球磨機負荷參數軟測量. 控制與決策, 2018, 33(10): 1795?1800

                      27 Yan Gao-Wei, He Min, Tang Jian, Han Dong-Sheng. Soft sensor of wet ball mill load based on maximum mean discrepancy multi-source domain transfer learning. Control and Decision, 2018, 33(10): 1795?1800
                      [28] 湯健, 喬俊飛, 劉卓, 周曉杰, 余剛, 趙建軍. 面向磨機負荷參數預測的多通道機械信號分析評估與優化組合. 北京工業大學學報, 2019,

                      28 Tang Jian, Qiao Jun-Fei, Liu Zhuo, Zhou Xiao-Jie, Yu Gang, Zhao Jian-Jun. Multi-channel Mechanical Signal Analytical Estimation and Optimal Combination Method for Mill Load Parameter Forecasting. Journal of Beijing University of Technology, 2019,
                      [29] 趙軒, 郭蔚, 劉京. RGB-D圖像中的分步超像素聚合和多模態融合目標檢測. 中國圖象圖形學報, 2018, 23(08): 1231?1241

                      29 Zhao Xuan, Guo Wei, Liu Jing. Object detection adopting sub-step merging of super-pixel and multi-modal fusion in RGB-D. Journal of Image and Graphics, 2018, 23(08): 1231?1241
                      [30] 馬江河, 孫穎, 張雪英. 融合語音信號和腦電信號的多模態情感識別. 西安電子科技大學學報, 2019, 46(01): 143?150

                      30 Ma Jiang-He, Sun Ying, Zhang Xue-Ying. Multimodal emotion recognition for the fusion of speech and EEG signals. Journal of Xidian University, 2019, 46(01): 143?150
                      [31] 31 Dahne S, Biebmann F, Samek W, et al. Multivariate Machine Learning Methods for Fusing Multimodal Functional Neuroimaging Data. Proceedings of the IEEE, 2015, 103(9): 1?24 doi: 10.1109/JPROC.2015.2466311
                      [32] 32 Ramachandram D, Taylor G W. Deep Multimodal Learning: A Survey on Recent Advances and Trends. IEEE Signal Processing Magazine, 2017, 34(6): 96?108 doi: 10.1109/MSP.2017.2738401
                      [33] 33 Wu D, Pigou L, Kindermans P J, et al. Deep Dynamic Neural Networks for Multimodal Gesture Segmentation and Recognition. IEEE Transactions on Pattern Analysis and Machine I Pattern Analysis and Machine Intelligence, 2016, 38(8): 1583?1597 doi: 10.1109/TPAMI.2016.2537340
                    • 加載中
                    計量
                    • 文章訪問數:  2223
                    • HTML全文瀏覽量:  1375
                    • 被引次數: 0
                    出版歷程
                    • 收稿日期:  2019-10-23
                    • 錄用日期:  2020-02-07

                    目錄

                      /

                      返回文章
                      返回