Evolutionary neuro-fuzzy control

Evolutionary neuro-fuzzy control

For access to this article, please select a purchase option:

Buy chapter PDF
(plus tax if applicable)
Buy Knowledge Pack
10 chapters for £75.00
(plus taxes if applicable)

IET members benefit from discounts to all IET publications and free access to E&T Magazine. If you are an IET member, log in to your account and the discounts will automatically be applied.

Learn more about IET membership 

Recommend Title Publication to library

You must fill out fields marked with: *

Librarian details
Your details
Why are you recommending this title?
Select reason:
Flexible Robot Manipulators: Modelling, Simulation and Control — Recommend this title to your library

Thank you

Your recommendation has been sent to your librarian.

This chapter focuses on the use of genetic algorithms (GAs) in the design of FLC. An approach of adopting genetic algorithm search is adopted to determine optimal FLC scaling factors. The approach is then extended by adoption of neural network learning of the scaling factors leading to a neuro-fuzzy control method. This is further combined with genetic algorithm for optimisation of shape of activation function of the neural network. Case study experimental investigation exercises are presented demonstrating the performances of the developed paradigms in the control of a single-link flexible manipulator system.

Chapter Contents:

  • 14.1 Introduction
  • 14.2 Evolutionary fuzzy control
  • 14.2.1 PD-PI-like fuzzy control
  • 14.3 GA-fuzzy control
  • 14.3.1 Chromosome representation
  • Chromosome representation for membership functions
  • Chromosome representation of rule-base
  • Encoding scheme
  • 14.3.2 Objective function
  • 14.3.3 Evaluation
  • 14.3.4 Initialisation
  • 14.3.5 Crossover
  • 14.3.6 Mutation
  • 14.3.7 Selection
  • 14.3.8 Case study 14.1: GA-fuzzy control scheme
  • 14.4 Neuro-fuzzy control
  • 14.4.1 Parameters of PD-PI fuzzy controller
  • 14.4.2 Tuning of membership functions
  • 14.4.3 Reducing the number of scaling parameters
  • 14.4.4 Neural network tuning of the scaling factors
  • 14.4.5 Backpropagation learning of neural network
  • 14.4.6 Learning with non-linear activation function
  • 14.4.7 Case study 14.2: neuro-fuzzy control scheme
  • 14.5 GA-based neuro-fuzzy control
  • 14.5.1 Integration of fuzzy logic, neural networks and genetic algorithms
  • 14.5.2 Sigmoid function shape learning
  • 14.5.3 Neural network learning using genetic algorithms
  • 14.5.4 Case study 14.3: GA-neuro-fuzzy control scheme
  • 14.6 Summary

Inspec keywords: control system synthesis; search problems; genetic algorithms; learning systems; neurocontrollers; flexible manipulators; fuzzy control

Other keywords: evolutionary neurofuzzy control; GA; optimal scaling factors; FLC design; neural network learning; fuzzy logic controllers; single-link flexible manipulator system; shape; activation function; genetic algorithm search; optimisation

Subjects: Self-adjusting control systems; Neurocontrol; Manipulators; Fuzzy control; Optimisation techniques; Control system analysis and synthesis methods

Preview this chapter:
Zoom in

Evolutionary neuro-fuzzy control, Page 1 of 2

| /docserver/preview/fulltext/books/ce/pbce086e/PBCE086E_ch14-1.gif /docserver/preview/fulltext/books/ce/pbce086e/PBCE086E_ch14-2.gif

Related content

This is a required field
Please enter a valid email address