An Improved General Regression Neural Network for Prediction Based on Small Samples Data

Abstract:

This paper proposed an improved General Regression Neural Network (GRNN) for prediction based on small samples data by adding the procedure of filtrating the input variables, since the training of original GRNN relies too heavily on data samples and is lack of the relevant process to deal with the errors, while the measurement error and sample error from a plenty of input and output variables in small samples data cannot be easily recognized, but could obviously influence the effect of the training. All the input variables were divided into critical factors and non-critical factors by the impact degree of every input variable, in accordance with the result of the partial correlation analysis on the experimental data. The critical factors were considered as the input of the GRNN model while the non-critical factors were removed to eliminate the error. To verify the performance of the proposed approach, a test on the case of residual stress prediction based on fourteen groups of experimental data was taken as an example application. The improved method could not only avoid the limit to the orthogonality and the quantity of the experiments in traditional method of residual stress prediction, but also get prediction results with smaller error, compared with the original GRNN method. The results have shown that the improved GRNN outperformed the original algorithm with average 4.1% lower prediction error in 92% of the tested cases. And in the rest 8% of tested cases, the prediction error of the improved GRNN was only 0.24% higher than the original one’s.

• Periodical: Applied Mechanics and Materials (Volume 743)
• Pages: 646-651
• DOI: https://doi.org/10.4028/www.scientific.net/AMM.743.646
• Online since: March 2015
• Authors: Pan Zou, Bei Zhi Li*, Steven Y. Liang
• Keywords: General Regression Neural Network (GRNN), Improved Algorithm, Partial Coefficient Analysis, Residual Stress Prediction, Small Samples Data

References

[1] M.H. El-Axir. A method of modeling residual stress distribution in turning for different materials [J]. International Journal of Machine Tools and Manufacture, 2002, 429.

DOI: 10.1016/s0890-6955(02)00031-7

[2] G.F. Batalha, S. Delijaicov, J.B. Aguiar, E.C. Bordinassi, M. Stipkovic Filho. Residual stresses modelling in hard turning and its correlation with the cutting forces[J]. Journal of Achievements in Materials and Manufacturing Engineering, 2007, 241.

[3] Litao Wang, Yinglin Ke, Zhigang Huang, Jie Sun. Residual Stress Analysis Caused by NC Machining for Aviation Aluminum-alloy[J]. Chinese Journal of Mechanical Engineering, 2004, 04: 123-126.

DOI: 10.3901/jme.2004.04.123

[4] Longquan Xue, Guoning Xu, Rongchang Liu, Xiaogang Jia. Residual Stress Prediction of the Crankshaft Based on Neural Network [J]. Practical Technical Research, 2007, 05: 686-689.

[5] Yaqin Zhao. Predicting Model for Residual Stress in Brazed Stainless Steel Plate-fin Structure Based on Neural Network[J]. Welding Technology, 2009, 11: 14-16+1.

[6] Yong Yu, Li Huang. The Prediction for Welding Residual Stress of Bucket Based on BP Neural Network[J]. Machine Design and Manufacturing Engineering, 2013, 05: 79-82.

[7] Specht D F. A general regression neural network. [J]. IEEE transactions on neural networks / a publication of the IEEE Neural Networks Council, 1991, 26.

DOI: 10.1109/72.97934

[8] Tom M. Mitchell. Machine Learning(pp.49-55). The McGraw-Hill Companies, Inc.

[9] Jinhuang Yu, Weiquan Yang. Multivariate Statistical Analysis and Application(pp.14-18). Guangzhou：Zhongshan University Press, (2005).