Bone Scaffold Forming Filament Width Prediction of LDM Based on the Improved BP Neural Network

Abstract:

LDM process is used for preparing three-dimensional scaffolds for tissue engineering rapid prototyping technologies. Because of its forming process is complex, which influenced by a variety of factors, so the processing environment is not stable, the forming of scaffold pore size can not be guaranteed, therefore the forming precision is poor. However, the scaffold pore size accuracy is mainly decided by the wire filament width. Neural network theory and development provides a powerful tool for the study of nonlinear systems. This article analyzed the influence factors for forming bone scaffold filament width of LDM process, based on improved BP neural network, using MATLAB software programming, then predicted the filament width. The results show that model prediction error was less than 8%, it has high forecasting precision, and it can be used to guide the LDM process parameter selection and forming precision of prediction.

• Periodical: Key Engineering Materials (Volume 568)
• Pages: 187-192
• DOI: https://doi.org/10.4028/www.scientific.net/KEM.568.187
• Online since: July 2013
• Authors: Yuan Yuan Liu, Zhen Zhong Han, Shu Hui Fang, Da Li Liu, Ying Liu, Qing Xi Hu
• Keywords: Filament Width, Improved BP Neural Network, Low-Temperature Deposition Manufacturing (LDM), Precision Predict

References

[1] T. Wohlers, The rapid prototyping manufacturing industry [J]. Advanced Materials & Processes, 161 (2003)35 -37.

[2] L. Jin, Z. Xiong, L. Liu, et al. Low temperature deposition process based on piston-extrusion for fabricating t issue engineering scaffold. J Tsinghua Univ(Sci&Tech). 49 (2009)34-38.

[3] S.R. Yin, G.J. Chen, Y.L. Xie. Wavelet neural network based fault diagnosis in nonlinear analog circuits [J]. Journal of Systems Engineering and Electronics, 17, (2006)60-66.

[4] Y.K. Zhang Y.L. Li. The inversion of bird's material parameters using improved BP neural network [J]. Machinery Design & Manufactur, 2 (2010)51-53.

[5] R.Y. He: Research of the Control System and Technology of the Fused Deposition Modeling MS., Huazhong University of Science &Technology, China, (2005).

[6] H. Zhao , B.L. Feng, X.H. Dong and Z.H. Wu. Optimization Choice of Cutting Parameter Based on Improved BP Neural Network . MACH I NE TOOL & HYDRAULICS, 36, (2008)213-226.

[7] H.X. Fu, H. Zhao. MATLAB neural network application design, Mechanic industry Press, China (2010).

[8] D. Sarkav, Methods to Speed up Error BP Learning Algorithm. ACM Computing Survey, 27(1995)519-592.

[9] Q.L. Ren. Test optimization design and analysis, Higher Education Press, China (2003).