Data-Driven Integrated Modeling and Intelligent Control Methods of Grinding Process

  • Jiesheng Wang
  • Xianwen Gao
  • Shifeng Sun
Part of the Lecture Notes in Computer Science book series (LNCS, volume 7368)


The grinding process is a typical complex nonlinear multivariable process with strongly coupling and large time delays. Based on the data-driven modeling theory, the integrated modeling and intelligent control method of grinding process is carried out in the paper, which includes the soft-sensor model of the key technology indicators (grinding granularity and mill discharge rate) based on wavelet neural network optimized by the improved shuffled frog leaping algorithm (ISFLA), the optimized set-point model utilizing case-based reasoning and the self-tuning PID decoupling controller. Simulation results and industrial application experiments clearly show the feasibility and effectiveness of control methods and satisfy the real-time control requirements of the grinding process.


Grinding Process Intelligent Control Case-based Reasoning Soft Sensor Wavelet Neural Network Shuffled Frog Leaping Algorithm PID Controller 


Unable to display preview. Download preview PDF.

Unable to display preview. Download preview PDF.


  1. 1.
    Wu, X.G., Yuan, M.Z., Yu, H.B.: Product Flow Rate Control in Ball Mill Grinding Process Using Fuzzy Logic Controller. In: 8th IEEE International Conference on Machine Learning and Cybernetics, pp. 761–764. IEEE Press, New York (2009)Google Scholar
  2. 2.
    Yu, J.Q., Xi, A.M., Fu, J.H.: The Application of Fuzzy Adaptive Learning Control (FALCON) in Milling-classification Operation System. Journal of Xi’an University of Architecture & Technology 2, 175–178 (2000) (in Chinese)Google Scholar
  3. 3.
    Zhou, P., Yue, H., Zheng, X.P.: Multivariable Fuzzy Supervisory Control for Mineral Grinding Process. Control and Decision 6, 685–688 (2008) (in Chinese)Google Scholar
  4. 4.
    Tie, M., Yue, H., Chai, T.Y.: Hybrid Intelligent Modeling and Simulation for Ore Grinding and Classification Process. Journal of Northeastern University (Natural Science) 5, 609–612 (2007) (in Chinese)Google Scholar
  5. 5.
    Zhang, X.D., Wang, W., Wang, X.G.: Beneficiation Process of Neural Networks Granularity of Soft Measurement Method. Control Theory and Application 1, 85–88 (2002) (in Chinese)Google Scholar
  6. 6.
    Ding, J.L., Yue, H., Qi, Y.T.: NN Soft-sensor for Particle Size of Grinding Circuit Based GA. Chinese Journal of Scientific Instrument 9, 981–984 (2006) (in Chinese)Google Scholar
  7. 7.
    He, G.C., Mao, Y.P., Ni, W.: Grinding size soft sensor model based on neural network. Metal Mines 2, 47–49 (2005) (in Chinese)Google Scholar
  8. 8.
    Zhou, P., Yue, H., Zhao, D.Y.: Soft-sensor Approach with Case-based Reasoning and Its Application in Grinding Process. Control and Decision 6, 646–650 (2006) (in Chinese)Google Scholar
  9. 9.
    Susan, C., Ray, C.R.: Learning Aaptation Knowledge to Improve Case-base Reasoning. Artificial Intelligence 7, 1175–1192 (2006)Google Scholar

Copyright information

© Springer-Verlag Berlin Heidelberg 2012

Authors and Affiliations

  • Jiesheng Wang
    • 1
    • 2
  • Xianwen Gao
    • 1
  • Shifeng Sun
    • 2
  1. 1.College of Information Science and EngineeringNortheastern UniversityShenyangChina
  2. 2.School of Electronic and Information EngineeringLiaoning University of Science and TechnologyAnshanChina

Personalised recommendations