Predicting Range of Chip Breaking of 3D Complex Groove Turning Inserts with Neural Networks

Xin Min Feng; Guang Yu Tan

doi:10.4028/www.scientific.net/MSF.723.148

Paper Titles

Research on the Method of Error Prediction in Milling Thin-Walled Impeller Blade
p.124

Rapid Toolpath Correction for Five-Axis High Efficiency Machining Based on Image Analysis
p.130

Determination of Constitutive Equation Parameters for Face Milling 3-D Simulation via Pressure Bar and Orthogonal Cutting Tests
p.136

Turbine Blade Distortion Analysis during Spiral NC Milling Based on FEM
p.143

Predicting Range of Chip Breaking of 3D Complex Groove Turning Inserts with Neural Networks
p.148

Tool Path Planning of 5-Axis Finishing Milling Machining for Closed Blisk
p.153

The Experimental Modal Analysis of High Speed Machining Tool System Based on Integral Polynomial Recognition Method
p.159

Drilling Simulation of High Manganese Steel Processing Based on the J-C Constitutive Relation
p.164

Using the Flat-End Mill in the Strip Width Machining
p.170

HomeMaterials Science ForumMaterials Science Forum Vol. 723Predicting Range of Chip Breaking of 3D Complex...

Predicting Range of Chip Breaking of 3D Complex Groove Turning Inserts with Neural Networks

Abstract:

BP neural networks model which was used to predict the rang of breaking chip of 3D complex groove turning inserts was established, then training and testing of the network was realized with MATLAB, finally ,range of breaking chip of the insert which was designed by the author was predicted. Percentage of accuracy of predicting results reached 91.67% comparing with the chip breaking experiment. This indicates that neural networks can be used to predict rang of breaking chip of turning inserts, so, saving the inserts which is used for cutting experiments and work of experiments, reducing the periodic time of inserts designing and development, increasing the competitive strength of inserts.

You might also be interested in these eBooks

View Preview

Info:

Periodical:

Materials Science Forum (Volume 723)

Pages:

148-152

DOI:

https://doi.org/10.4028/www.scientific.net/MSF.723.148

Citation:

Cite this paper

Online since:

June 2012

Authors:

Xin Min Feng, Guang Yu Tan

Keywords:

3D Complex Groove, BP Neural Network (BPNN), Chip Breaking

Export:

RIS, BibTeX

Price:

Permissions CCC:

Request Permissions

Permissions PLS:

Request Permissions

Сopyright:

Citation:

References

[1] X.M. Feng, G.Y. Tan and G.J. Liu: Mach. Des. Res. Vol.25 (2009), No. 5, pp.68-70

Google Scholar

[2] Q. Liu, G.Y. Tan, Y.J. Sun: Mach. Des. Vol. 23 (2006), No. 2, pp.33-35 (In Chinese).

Google Scholar

[3] X.M. Feng, G.Y. Tan: Key Eng. Mater. Vol. 458 (2011), pp.23-28

Google Scholar

[4] X.M. Feng, G.Y. Tan, G.H. Li and Y.H. Zhang: Vol. 69-70 (2009), pp.636-640

Google Scholar

[5] L.Q. Han: Theory, Design and Application of Artificial Neural Networks (Chemical Industry Press, China 2004), pp.51-57 Fig. 3 Construction of BP net for pre-estimated chip breaking range of inserts

Google Scholar