The Studies of Grinding Granularity Prediction Model Based on RBF Neural Network


According to the characters of the grinding process, such as many interference factors, big the inertia, long delay, large amount of calculation and nonlinear time-varying, complicated working mechanism and so on, we proposes a RBF neural network of grinding process control model, including the network structure and learning algorithm of selecting network, adopting nearest neighbor clustering algorithm. This model is firstly data preparation of milling process, including the experimental parameter selection, data selection and normalized processing. Secondly we establish the RBF neural network model, including conforming the network structure and selecting learning algorithm. Then we perform simulation experiments on Matlab, compare the simulation results with experimental results, analyze the results and propose the improvement ideas. Finally, we improve the training algorithm, and compare the simulation results of the changed network with the original. Simulation results show that the improved network prediction is better than the original network.

  • Abstract
  • Keywords
  • Introduction
  • Griding Procees
  • Grinding Granularity Prediction Model and Simulation
  • The Algorithm Improvement and Simulation Results
  • Conclusion
  • Acknowledgments
  • Reference

Related Content

Customize your page view by dragging and repositioning the boxes below.

Related Journal Articles
Related eBook Content
Topic Collections

Sorry! You do not have access to this content. For assistance or to subscribe, please contact us:

  • TELEPHONE: 1-800-843-2763 (Toll-free in the USA)
  • EMAIL: asmedigitalcollection@asme.org
Sign In