A Regression Neural Model for In-Process Surface Roughness Monitoring in End Milling Operations

Abstract:

The key element of the in-process surface roughness monitoring system is the decision-making model, which is utilized to analyze the input factors and then to generate a proper output. The success of the in-process monitoring system depends on the accuracy of the decision-making model. To increase the accuracy and reliability of model, it is important to reduce the variation of the inputs. To achieve this objective, an integration of regression and neural network was developed as a decision-making model in this research. In this integrated model, the regression model was applied as a filter to sort the input variables into groups. Furthermore, the grouped data was implemented to train and to generate different neural networks models to reduce the affection of input variation and increase the accuracy of the monitoring system. The input variables was first filtered by the threshold of regression model, and then analyzed by different neural networks model based on the filtered result. Finally, to evaluate the performance of the integrated model, the regression neural network and traditional neural networks were both developed for surface roughness monitoring system in an end milling operation to compare the accuracy of systems.

• Periodical: Key Engineering Materials (Volumes 419-420)
• Pages: 369-372
• DOI: https://doi.org/10.4028/www.scientific.net/KEM.419-420.369
• Online since: October 2009
• Authors: Po Tsang B. Huang, James C. Chen, Yuan Tsan Jou
• Keywords: End Milling, In-Process Surface Roughness Monitoring, Neural Network (NN), Regression Neural Model

References

[1] J. C. Chen & M. S. Lou: Fuzzy-nets based approach to using an accelerometer for an in-process surface roughness prediction system in milling operations. Int. Journal of Computer Integrated Manufacturing, Vol. 13 (2000), pp.358-368.

DOI: 10.1080/095119200407714

[2] Y. C. Shin, S. J. Oh, & S. A. Coker: Surface roughness measurement by ultrasonic sensing for in-process monitoring, Journal of Engineering for Industry, Vol. 117 (1995), pp.439-449.

DOI: 10.1115/1.2804352

[3] B. Ozcelik & M. Bayramoglu: The statistical modeling of surface roughness in high-speed flat end milling. Int. Journal of Mach. Tools and Manufact., Vol. 46 (2006), pp.1395-1402.

DOI: 10.1016/j.ijmachtools.2005.10.005

[4] M. A. Elbestawi, F. Ismail & K. M. Yuen: Surface topography characterization in finish milling, Int. Journal of Mach. Tools Manufact. Vol. 34 (1994), pp.245-255.

DOI: 10.1016/0890-6955(94)90104-x

[5] B. Huang, & J. C. Chen. An in-process neural network-based surface roughness prediction (INN-SRP) system using a dynamometer in end milling operations. Int. Journal of Adv. Manufact. Tech., Vol. 21 (2003), pp.339-347.

DOI: 10.1007/s001700300039

[6] B. P. Huang, J. C. Chen &Y. Li: Artificial-Neural-Networks Based Surface Roughness Pokayoke System for End-Milling Operations. Journal of Neuro., Vol. 71 (2008), pp.544-549.

DOI: 10.1016/j.neucom.2007.07.029