Fuzzy Controller Design with Fault Diagnosis System Condition On-line Monitor Using Neural Network

Conference paper
Part of the Lecture Notes in Electrical Engineering book series (LNEE, volume 107)

Abstract

This chapter presents a practical method to design and implement a fuzzy controller with system condition on-line monitor for temperatures of continuous soaking process in sugar plant. A new fuzzy control strategy is proposed to improve the control performances. The proposed strategy utilizes an innovative idea based on sectionalizing the error signal of the step response into four different functional zones. The supporting philosophy behind these four functional zones is to decompose the desired control objectives in terms of rising time, settling time and steady-state error measures maintained by an appropriate PID-type controller in each zone. Then, fuzzy membership factors are defined to configure the control signal on the basis of the fuzzy weighted PID outputs of all four zones. A method of system condition on-line monitor using neural network is presented, base on dead time, peak time, percent overshoot, steady state error, rise times, and gain of system step response. The obtained results illustrate the effectiveness of the proposed fuzzy control scheme in improving the performance and intelligent maintenance of the implemented control systems for temperatures of continuous soaking process in sugar plant.

Keywords

Fuzzy controller On-line monitor Neural network 

References

  1. 1.
    Harbeck C, Faurie R, Scheper T (2004) Application of near-infrared spectroscopy in the sugar industry for the detection of betaine. Anal Chim Acta 2:249–253Google Scholar
  2. 2.
    Hang CC, Astrom KJ, Wang QG (2002) Relay feedback auto-tuning of process controllers—A tutorial review. J Process Control 12:143–162CrossRefGoogle Scholar
  3. 3.
    Mohan BM, Sinha A (2008) Analytical structure and stability analysis of a fuzzy PID controller. Appl Soft Comput 8:749–758CrossRefGoogle Scholar
  4. 4.
    Mann GKI, Gosine RG (2005) Three-dimensional min–max-gravity based fuzzy PID inference analysis and tuning. Fuzzy Sets Syst 156:300–323CrossRefMATHMathSciNetGoogle Scholar
  5. 5.
    Woo ZW, Chung HY, Lin JJ (2000) A PID type fuzzy controller with self-tuning scaling factors. Fuzzy Sets Syst 115:321–326CrossRefMATHGoogle Scholar
  6. 6.
    Li G, Tsang KM, Ho SL (1998) Fuzzy based variable step approaching digital control for plants with time delay. ISA Trans 37:167–176CrossRefGoogle Scholar
  7. 7.
    Blanchett TP, Kember GC, Dubay R (2000) PID gain scheduling using fuzzy logic. ISA Trans 39:317–325CrossRefGoogle Scholar
  8. 8.
    Qiao WZ, Mizumoto M (1996) PID type fuzzy controller and parameters adaptive method. Fuzzy Sets Syst 78:23–35CrossRefMATHMathSciNetGoogle Scholar
  9. 9.
    Kazemian HB (2001) Comparative study of a learning fuzzy PID controller and a self-tuning controller. ISA Trans 40:245–253CrossRefGoogle Scholar

Copyright information

© Springer Science+Business Media B.V. 2012

Authors and Affiliations

  1. 1.Hangzhou Vocational and Technical CollegeHangzhouChina

Personalised recommendations