Design and Application of an Adaptive Fuzzy Control Strategy to Zeroing Neural Network for Solving Time-Variant QP Problem | IEEE Journals & Magazine | IEEE Xplore

Design and Application of an Adaptive Fuzzy Control Strategy to Zeroing Neural Network for Solving Time-Variant QP Problem


Abstract:

Zeroing neural network (ZNN), as an important class of recurrent neural network, has wide applications in various computation and optimization fields. In this article, ba...Show More

Abstract:

Zeroing neural network (ZNN), as an important class of recurrent neural network, has wide applications in various computation and optimization fields. In this article, based on the traditional-type zeroing neural network (TT-ZNN) model, an adaptive fuzzy-type zeroing neural network (AFT-ZNN) model is proposed to settle time-variant quadratic programming problem via integrating an adaptive fuzzy control strategy. The most prominent feature of the AFT-ZNN model is to use an adaptive fuzzy control value to adaptively adjust its convergence rate according to the value of the computational error. Four different activation functions are injected to analyze the convergence rate of the AFT-ZNN model. In addition, different membership functions and different ranges of the fuzzy control value are discussed to study the character of the AFT-ZNN model. Theoretical analysis and numerical comparison results further show that the AFT-ZNN model has better performance than the TT-ZNN model.
Published in: IEEE Transactions on Fuzzy Systems ( Volume: 29, Issue: 6, June 2021)
Page(s): 1544 - 1555
Date of Publication: 16 March 2020

ISSN Information:

Funding Agency:


References

References is not available for this document.