Parameter Identification of Surface Roughness in Ultra-Precision Turning Processing Based on GA-RBF Neural Network

Jie Lai Chen

doi:10.4028/www.scientific.net/AMR.940.267

Paper Titles

Analysis of Axial Holding Capability about the Lengthened Shrink-Fit Holder and Cutting Tool System
p.249

Fire Rescue Robot Design Based on Solidworks
p.254

Cleaning Machine Design of Building Glass Curtain Wall
p.258

Analysis of a Micro-Displacement Amplification Mechanism Based on Piezoelectric Stack
p.262

Parameter Identification of Surface Roughness in Ultra-Precision Turning Processing Based on GA-RBF Neural Network
p.267

The Simulation and Improvement of the Heating Furnace Lifting Framework Based on ANSYS
p.271

Research on the Punching Method of Multi-Position Progressive Die with the Feature Unit as the Step
p.275

Fault Diagnosis for the Electric Starting System of Self-Propelled Artillery Based on Information Fusion Technology
p.280

Test Study on Slipping Performance of the Flexible Nodes of the Precast Concrete Exterior Wall Cladding Panel
p.284

HomeAdvanced Materials ResearchAdvanced Materials Research Vol. 940Parameter Identification of Surface Roughness in...

Parameter Identification of Surface Roughness in Ultra-Precision Turning Processing Based on GA-RBF Neural Network

Abstract:

The modeling of surface roughness is the key factor to improve the quality of products and raise the efficiency of process equipment in ultra-precision turning process. In order to analyze the influence of each cutting parameters on surface roughness, the prediction model of surface roughness was constructed, and parameter identification of the prediction model was required. To meet the requirement, the curve fitting tool of MATLAB toolbox and radial basis function neural network optimized by genetic algorithm were respectively used as a case study to validate the feasibility and reliability of the method proposed in this paper. The parameter identification results were given, and the comparison of the parameter identification results shows that the parameter identification based on radial basis function neural network optimized by genetic algorithm has higher prediction accuracy than curve fitting tool of MATLAB toolbox.

You might also be interested in these eBooks

Machinery, Materials Science and Engineering Applications 2014

View Preview

Info:

Periodical:

Advanced Materials Research (Volume 940)

Pages:

267-270

DOI:

https://doi.org/10.4028/www.scientific.net/AMR.940.267

Citation:

Cite this paper

Online since:

June 2014

Authors:

Jie Lai Chen

Keywords:

Genetic Algorithm (GA), Radial Basis Function Neural Network, Surface Roughness (SR)

Export:

RIS, BibTeX

Price:

Permissions CCC:

Request Permissions

Permissions PLS:

Request Permissions

Сopyright:

Citation:

References

[1] L. Lennart. Convergence analysis of parametric identification methods. IEEE transactions on automatic control, 1978, AC-23: 770-783.

DOI: 10.1109/tac.1978.1101840

Google Scholar

[2] L. Monostori. A step towards Intelligent Manufacturing: Modeling and Monitoring of Manufacturing Process through Artificial Neural Networks. Annals of CIRP, 1993, 42: 485-488.

DOI: 10.1016/s0007-8506(07)62491-3

Google Scholar

[3] M.H. Wang, Z.S. Liu. Predictive Modeling of Surface Roughness Optimization in Ultra-precision Turning Based on Genetic Algorithm. Aviation Precision Manufacturing Technolog y, 2005, 41(3): 1-8.

DOI: 10.3901/jme.2005.11.158

Google Scholar

[4] H.X. Wang, D. Li, S. Dong. The Establishment of a Surface Roughness Model for Ultraprecision Turning . High Technology Letters, 2000, 10(3): 77-82.

Google Scholar

[5] L.Q. Han. Artificial neural networks tutorial. Beijing: Beijing University of Posts and Telecornmunications Press, (2006).

Google Scholar