Prediction of Surface Roughness in Cylindrical Traverse Grinding Based on ALS Algorithm

Jia-Zhong Wang, Longshan Wang, Guofa Li, Gui-Hong Zhou

2005 · 10 citations · 6 references

Concepts

Abstract

A framework for modeling traverse surface roughness using fuzzy basis function neural networks (FBFN) is presented with adaptive least-squares (ALS) training algorithm. The ALS algorithm, based on the least-squares method and genetic algorithm (GA), is proposed for autonomous learning and construction of FBFN without any human intervention. Simulation and experiment studies are performed to demonstrate advantages of the proposed modeling framework with the training algorithm in modeling grinding processes. Simulation studies indicated that the new algorithms generate superior results over conventional algorithms such as backpropagation algorithms and conventional GA-based algorithm. The study on traverse grinding process using a small amount of experimental data demonstrated the potential of the ALS algorithm. The accuracy of developed models is validated through independent sets of grinding experiments.

References

6