A Transductive Neuro-Fuzzy Force Control: An Ethernet-Based Application to a Drilling Process

Authors:
Agustin Gajate;Rodolfo Haber;Pastora Vega
Affiliations:
Instituto de Automatica Industrial, Spanish Council for Scientific Research, Arganda del Rey, Spain 28500;Instituto de Automatica Industrial, Spanish Council for Scientific Research, Arganda del Rey, Spain 28500;Departamento de Informatica y Automatica, Universidad de Salamanca, Salamanca, Spain 37008
Venue:
ICONIP '09 Proceedings of the 16th International Conference on Neural Information Processing: Part II
Year:
2009

Citing 7
Cited 0

Using local models to control movement

Advances in neural information processing systems 2
Locally Weighted Learning for Control

Artificial Intelligence Review - Special issue on lazy learning
HyFIS: adaptive neuro-fuzzy inference systems and their application to nonlinear dynamical systems

Neural Networks
Incorporating Fuzzy Membership Functions into the Perceptron Algorithm

IEEE Transactions on Pattern Analysis and Machine Intelligence
NFI: a neuro-fuzzy inference method for transductive reasoning

IEEE Transactions on Fuzzy Systems
Neuro-fuzzy rule generation: survey in soft computing framework

IEEE Transactions on Neural Networks
An approximate internal model-based neural control for unknown nonlinear discrete processes

IEEE Transactions on Neural Networks

Quantified Score

Hi-index	0.00

Visualization

Abstract

This paper presents the application of a neural fuzzy inference method to the field of control systems using the internal model control paradigm (IMC). Through a transductive reasoning system, a neuro-fuzzy inference system enables local models to be created for each input/output set in the system at issue. These local models are created for modeling the direct and inverse dynamics of the process. The models are then applied according to IMC paradigm. In order to demonstrate the benefits of this technique for control systems, it is applied for networked cutting force control in a high-performance drilling process. A comparative study between a well-established neuro-fuzzy technique and the suggested method is performed.