Neural Network with High-Dimension Multi-Input Layers Based on Production Control and its Application

Abstract:

A new neural network with High-Dimension-Input Multi-Input layers based on production control is proposed; its construction figure and algorithm are given as well in this paper. Because the new neural network can be seen as the result of moving some input dot of BP neural network to its hide layers, it is of few weigh value. In addition as the position of input dots in new neural network may be chosen according to production flow, as long as the chose is suitable, it can obtain a better effect than BP neural network. This paper uses the new neural network to the modeling of hot steel rolling production quality and compares the result with that of BP neural network. The fact shows that as number of weight values is decreased, the new neural network is of fast leaning rate and simultaneously can get a better result than BP neural network.

• Periodical: Advanced Materials Research (Volumes 383-390)
• Pages: 4461-4466
• DOI: https://doi.org/10.4028/www.scientific.net/AMR.383-390.4461
• Online since: November 2011
• Authors: Jin Ling Li
• Keywords: Hot Steel Rolling Production, Multi-Input Layers, Neural Network with Hight-Dimension-Input, Production Control

References

[1] Zengqi Sun, Theory and Technology Intelligent Control, Beijing, Tsinghua University, (1997).

[2] Robb J. Muirnead, Aspects of multivariate statistical theory, , John Wiley and sons, Inc. (1982).

[3] Yongji Wang, and Jian Tu, Neural Network Control, Beijing, Mechanical Industry Press, (1998).

[4] Robert M. et al. Gaussion, Networks for Direct Adaptive Control, IEEE. Trans. on Neural Networks, 1992, 3(6): p.837–863.

[5] Jinsheng Xing and Bai-wu Wan, Two Phase Mixed Algorithm and its Application to Modeling in Hot Rolling Data, Xian, Journal of Xian Jiaotong University, 2000, 34(12): p.105–107.

[6] WH Inmon, JA Zachman, and JG Geiger, Data Warehouse, McGraw-Hill, Inc. New York, NY, USA, (1997).

[7] J.Y. Jung, Y.T. Im . Fuzzy algorithm for calculating roll speed variation based on roll separating force in hot rolling. International Journal of Mechanical Sciences, 2000, 42(3): 65-70.

DOI: 10.1016/s0020-7403(98)00122-2

[8] Huanqin li , A quality modeln for large-scale hot steel rolling production based on Wavelet Neural Network[j] . China Journal of system engineering 2009. 20(5).