Data-Driven Integrated Modeling and Intelligent Control Methods of Grinding Process
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.
KeywordsGrinding Process Intelligent Control Case-based Reasoning Soft Sensor Wavelet Neural Network Shuffled Frog Leaping Algorithm PID Controller
Unable to display preview. Download preview PDF.
- 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.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.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.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.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.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.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.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.Susan, C., Ray, C.R.: Learning Aaptation Knowledge to Improve Case-base Reasoning. Artificial Intelligence 7, 1175–1192 (2006)Google Scholar