Soft measurement for a ball mill load parameters based on integration of semi-supervised multi-source domain adaptation

被引：0
|
作者：
Li S. [1 ,2 ]
Yan G. [1 ,2 ]
Yan F. [1 ]
Cheng L. [1 ]
Du Y. [1 ]
机构：
[1] College of Electrical and Power Engineering, Taiyuan University of Technology, Taiyuan
[2] Shanxi Institute of Technology, Yangquan
来源：
Zhendong yu Chongji/Journal of Vibration and Shock | 2019年 / 38卷 / 19期
关键词：
Ball mill load parameter; Multi-source domain; Semi-supervised domain adaptation; Transfer learning;
D O I：
10.13465/j.cnki.jvs.2019.19.031
中图分类号：
学科分类号：
摘要：
Aiming at the model mismatch problem caused by distribution difference between historical data and data to be measured after changes of a ball mill's working conditions and the problem of less samples of working conditions to be measured, a soft measurement method for ball mill load parameters based on semi-supervised domain adaptation was studied here. Considering effects of output label on the characteristic transform matrix, firstly constraint conditions were integrated to search the characteristic transform matrix, and historical data and data to be measured were projected into the common subspace. Then, a regression model was established according to the projected historical data and less labeled data to be measured to obtain load parameters of unlabeled data to be measured. Considering different working conditions' historical data having information complementation feature, a soft measurement model based on integration of semi-supervised multi-source domain adaptation was built to further improve the correctness of soft measurement model. The measured data of multi-working condition tests of ball mills in laboratory showed that the proposed method can effectively improve the prediction accuracy of ball mill load parameters. © 2019, Editorial Office of Journal of Vibration and Shock. All right reserved.
引用
收藏
页码：202 / 207
页数：5
相关论文
共 17 条
  • [1] Liu Q., Qin S., Perspectives on big data modeling of process industries, Acta Automatica Sinica, 42, 2, pp. 161-171, (2016)
  • [2] Tang J., Zheng X., Zhao L., Et al., Soft sensing of mill load based on frequency domain feature extraction and information fusion, Chinese Journal of Scientific Instrument, 31, 10, pp. 2161-2167, (2010)
  • [3] Das S.P., Das D.P., Behera S.K., Et al., Interpretation of mill vibration signal via wireless sensing, Minerals Engineering, 24, 3-4, pp. 245-251, (2011)
  • [4] Liu Z., Chai T., Tang J., Multi-scale shell vibration frequency spectrum analysis and modeling approach of ball mill, Journal of Northeastern University(Natural Science), 36, 3, pp. 305-308, (2015)
  • [5] Su Z.G., Wang P.H., Song Z.L., Kernel based nonlinear fuzzy regression model, Engineering Applications of Artificial Intelligence, 26, 2, pp. 724-738, (2013)
  • [6] Tang J., Wang D.H., Chai T.Y., Predicting mill load using partial least squares and extreme learning machines, Soft Computing, 16, 9, pp. 1585-1594, (2012)
  • [7] Ma H.H., Hu Y., Shi H.B., A novel local neighborhood standardization strategy and its application in fault detection of multimode processes, Chemometrics and Intelligent Laboratory Systems, 118, pp. 287-300, (2012)
  • [8] Rato T.J., Reis M.S., Markovian and non-Markovian sensitivity enhancing transformations for process monitoring, Chemical Engineering Science, 163, pp. 223-233, (2017)
  • [9] Ma Y.X., Shi H.B., Ma H.H., Et al., Dynamic process monitoring using adaptive local outlier factor, Chemometrics and Intelligent Laboratory Systems, 127, pp. 89-101, (2013)
  • [10] Jaffel I., Taouali O., Harkat M.F., Et al., Moving window KPCA with reduced complexity for nonlinear dynamic process monitoring, ISA Transactions, 64, pp. 184-192, (2016)
12