Soft sensing method for magnetic tube recovery ratio via fuzzy systems and neural networks

  • Authors:
  • Fenghua Wu;Tianyou Chai

  • Affiliations:
  • Key Laboratory of Process Industry Automation, Northeastern University, Shenyang 110006, China;Key Laboratory of Process Industry Automation, Northeastern University, Shenyang 110006, China

  • Venue:
  • Neurocomputing
  • Year:
  • 2010

Quantified Score

Hi-index 0.01

Visualization

Abstract

A magnetic tube recovery ratio (MTRR) is an important index in mineral processing, though it cannot be measured online. Real-time control for this product index is impossible. In this paper a new soft sensing method is proposed, which uses fuzzy system and neural network techniques. The contributions of our soft sensing method are that a fuzzy mechanism model for MTRR is used, which is obtained from data clustering. We do not update the fuzzy model, but use a neural compensator to improve the modeling accuracy, where the training algorithm for the neural network stable. This soft sensing method has been successfully applied in a metal company in China.