Proceedings of the Korea Society for Simulation Conference (한국시뮬레이션학회:학술대회논문집)

The Korea Society for Simulation (한국시뮬레이션학회)
권호 표지

A METHOD OF DEVELOPING SOFT SENSOR MODEL USING FUZZY NEURAL NETWORK

  • Chang, Yuqing (Dept. of Information Science and Engineering P.O.Box 131, Northeastern University) ;
  • Wang, Fuli (Dept. of Information Science and Engineering P.O.Box 131, Northeastern University) ;
  • Lin, Tian (Dept. of Information Science and Engineering P.O.Box 131, Northeastern University)
  • Published : 2001.10.01
Download PDF
⟨ Previous Next ⟩

Abstract

Soft sensor is an effective method to deal with the estimation of variables, which are difficult to measure because of the reasons of economy or technology. Fuzzy logic system can be used to develop the soft sensor model by infinite rules, but the fuzzy dividing of variable sets is a key problem to achieve an accurate fuzzy logic model, In this paper, we proposed a new method to develop soft sensor model based on fuzzy neural network. First, using a novel method to divide the variable fuzzy sets by the process input and output data. Second, developing the fuzzy logic model based on that fuzzy set dividing. After that, expressing the fuzzy system with a fuzzy neural network and getting the initial soft sensor model based FNN. Last, adjusting the relative parameters of soft sensor model by the BP learning method. The effectiveness of the method proposed and the preferable generalization ability of soft sensor model built are demonstrated by the simulation.

Keywords