Identifying contact formations from force signals: a comparison of fuzzy and neural network classifiers

Abstract
In this paper, we present and compare two methodsof identifying single-ended contact formations fromforce sensor patterns. Instead of using geometric modelsof the workpieces, both methods use force sensorsignals only. In the first method, fuzzy logic is usedto model the patterns in the force signals. Membershipfunctions are generated automatically from trainingdata and then used by the fuzzy classifier. In thesecond method, a neural network architecture is usedto learn the mapping from ...

This publication has 5 references indexed in Scilit: