Soft sensor of wet ball mill load based on maximum mean discrepancy multi-source domain transfer learning

被引：0
|
作者：
Yan G.-W. [1 ]
He M. [1 ]
Tang J. [2 ]
Han D.-S. [1 ]
机构：
[1] College of Information Engineering, Taiyuan University of Technology, Taiyuan
[2] Information Department, Beijing University of Technology, Beijing
来源：
Kongzhi yu Juece/Control and Decision | 2018年 / 33卷 / 10期
关键词：
Joint distribution adaptation; Maximum mean discrepancy; Multi source domain; sensor; Soft; Transfer learning; Wet ball mill load;
D O I：
10.13195/j.kzyjc.2017.0636
中图分类号：
学科分类号：
摘要：
When the working condition of a wet ball mill is changed, the distribution of real-time data and modeling data is inconsistent. It is difficult to accurately measure the load parameters by using the traditional soft sensor algorithm based on historical data. Therefore, a transfer learning strategy is introduced, and the robustness of the model is improved by the multi domain mechanism. The process is to preprocess and extract the characteristics of multi working conditions data, and the distribution of the edge and the conditional distribution is obtained by joint distribution fitting. Then the maximum mean discrepancy is used to measure the distribution of adaptive data, and the calculated results are applied to the regression weighted. Finally, the target domain data is used for load forecasting. The practicability and effectiveness of the model are illustrated by comparing experiments and cross experiments. © 2018, Editorial Office of Control and Decision. All right reserved.
引用
收藏
页码：1795 / 1800
页数：5
相关论文
共 15 条
  • [1] Wang H., Jia M.P., Chen Z.L., Soft measurement based on mechanism model and LS-SVM for fill level of ball mill, Electric Power Automation Equipment, 30, 7, pp. 92-95, (2010)
  • [2] Zhou P., Chai T.Y., Wang H., Intelligent optimal-setting control for grinding circuits of mineral processing process, IEEE Trans on Automation Science & Engineering, 6, 4, pp. 730-743, (2009)
  • [3] Tian H., Mao Z., Wang S., Et al., Application of genetic algorithm combined with BP neural network in soft sensor of molten steel temperature, The 6th World Congress on Intelligent Control and Automation, pp. 7742-7745, (2006)
  • [4] Tang J., Zhao L., Yu W., Et al., Soft sensor modeling of ball mill load via principal component analysis and support vector machines, Lecture Notes in Electrical Engineering, 67, 67, pp. 803-810, (2010)
  • [5] Tang J., Zheng X.P., Zhao L.J., Et al., Soft sensing of mill load based on frequency domain feature extraction and information fusion, Chinese J of Scientific Instrument, 31, 10, pp. 2161-2167, (2010)
  • [6] Tang J., Chai T.Y., Cong Q.M., Et al., Soft sensor approach for modeling mill load parameters based on EMD and selective ensemble learning algorithm, Acta Automatica Sinica, 40, 9, pp. 1853-1866, (2014)
  • [7] Tang J., Yuw, Chai T., Et al., On-line principal component analysis with application to process modeling, Neurocomputing, 82, 1, pp. 167-178, (2012)
  • [8] Tang J., Chai T.Y., Liu Z., Et al., Adaptive ensemble modelling approach based on updating sample intelligent identification, Acta Automatica Sinica, 42, 7, pp. 1040-1052, (2016)
  • [9] Jin H., Chen X., Yang J., Et al., Multi-model adaptive soft sensor modeling method using local learning and online support vector regression for nonlinear time-variant batch processes, Chemical Engineering Science, 131, pp. 282-303, (2015)
  • [10] Gretton A., Borgwardt K.M., Rasch M., Et al., A kernel method for the two-sample-problem, Conf on Advances in Neural Information Processing Systems, pp. 513-520, (2007)
12