Advertisement

Fault Tolerant Control of Nonlinear Processes with Adaptive Diagonal Recurrent Neural Network Model

  • Ding-Li Yu
  • Thoonkhin Chang
  • Jin Wang
Conference paper
Part of the Lecture Notes in Computer Science book series (LNCS, volume 3498)

Abstract

Fault tolerant control (FTC) using an adaptive recurrent neural network model is developed in this paper. The model adaptation is achieved with the extended Kalman filter (EKF). A novel recursive algorithm is proposed to calculate the Jacobian matrix in the model adaptation so that the algorithm is simple and converges fast. A model inversion control with the developed adaptive model is applied to nonlinear processes and fault tolerant control is achieved. The developed control scheme is evaluated by a simulated continuous stirred tank reactor (CSTR) and effectiveness is demonstrated.

Keywords

Hide Layer Extended Kalman Filter Model Predictive Control Recurrent Neural Network Nonlinear Process 
These keywords were added by machine and not by the authors. This process is experimental and the keywords may be updated as the learning algorithm improves.

Preview

Unable to display preview. Download preview PDF.

Unable to display preview. Download preview PDF.

References

  1. 1.
    Almeida, L.B.: Backpropagation in Non-Feedforward Networks in Neural Computing Architectures, pp. 75–91. MIT Press, Cambridge (1989)Google Scholar
  2. 2.
    Ku, C.C., Lee, K.Y.: Diagonal Recurrent Neural Networks for Dynamic System Control. IEEE Trans. on Neural Networks 6, 144–156 (1995)CrossRefGoogle Scholar
  3. 3.
    Chang, T.K.: Fault Tolerant Control for Nonlinear Processes Using Adaptive Neural Networks. PhD Thesis, Scholl of Engineering, Liverpool John Moores University, U.K. (2002)Google Scholar

Copyright information

© Springer-Verlag Berlin Heidelberg 2005

Authors and Affiliations

  • Ding-Li Yu
    • 1
  • Thoonkhin Chang
    • 1
  • Jin Wang
    • 1
  1. 1.Control Systems Research Group, School of EngineeringLiverpool John Moores UniversityLiverpoolUK

Personalised recommendations