A multiple-RBF neural network model to set rolling force Based on wavelet analysis

被引：0

作者：

Chen Z.-M. ^{[1
]}

Luo F. ^{[1
]}

Cao J.-Z. ^{[2
]}

机构：

[1] School of Automation Science and Engineering, South China University of Technology, Guangzhou 510640, Guangdong

[2] Department of Electronic Science, Huizhou University, Huizhou 516007, Guangdong

来源：

Huanan Ligong Daxue Xuebao/Journal of South China University of Technology (Natural Science) | 2010年 / 38卷 / 02期

关键词：

Continuous hot rolling; Multi-RBF neural network; Rolling force; Wavelet analysis;

D O I：

10.3969/j.issn.1000-565X.2010.02.027

中图分类号：

学科分类号：

摘要：

During the setting of rolling force in continuous hot strip rolling, force signals are influenced by various factors with complicated correlation. It is, therefore, difficult to establish an accurate model to describe the rolling mechanism. In order to solve this problem, a multi-RBF neural network model is proposed. In this new model, the multi-resolution wavelet analysis method is employed to separate the rolling force signal into several sub-signals corresponding to different factors, and several RBF neural networks are established, each for a certain sub-signal. All the outputs of the sub-networks are integrated into a rolling force signal, and both the input and the output of each network relate to the affecting factors of the corresponding sub-signal. Thus, the sub-networks can well reflect the variation mechanism of the rolling force. Simulated results show that the proposed model decreases the number of system dimensions, improves the learning ability of the network, and reduces the error rate of rolling force setting from the original 10% in BP neural network model to 5%.

引用

页码：142 / 148

页数：6

共 13 条

[1] Son J.S., Lee D.M., Kim I.S., Et al., A study on on-line learning neural network for rolling force in hot-rolling mill, Journal of Materials Processing Technology, 164-165, pp. 1612-1617, (2005)
[2] Son J.S., Lee D.M., Kim I.S., A study on genetic algorithm to select architecture of an optimal neural network in the hot rolling process, Journal of Materials Processing Technology, 153-154, pp. 643-648, (2004)
[3] Jia C.Y., Shan X.Y., Niu Z.P., High precision prediction of rolling force based on fuzzy and nerve method for cold tandem mill, Journal of Iron and Steel Research: International, 15, 2, pp. 23-27, (2008)
[4] Hu X.-L., Wang Z.-D., Gan J.-M., Et al., Prediction of rolling load by BP neural networks integrating with self-adaption of traditional model, Journal of Northeastern University: Natural Science, 25, 11, pp. 1089-1092, (2002)
[5] Zhang J.-M., Liu J., Yu X.-F., Et al., Application of combination of RBF neural network to prediction of rolling force, Journal of Iron and Steel Research, 20, 2, pp. 33-36, (2008)
[6] Cho S.Z., Cho Y.J., Yoon S.C., Reliable roll force prediction in cold mill using multiple neural networks, IEEE Transactions on Neural Networks, 8, 4, pp. 874-882, (1997)
[7] Liu D.-D., Wang Y., Guo Q.-L., Prediction of rolling force based on multi-neural network, Journal of University of Jinan: Science and Technology, 21, 3, pp. 234-237, (2002)
[8] pp. 48-50, (2007)
[9] Mallat S.G., A theory for multi-resolution signal decomposition: The wavelet representation, IEEE Transactions on Pattern Analysis and Machine Intelligence, 11, 7, pp. 674-693, (1989)
[10] Fan S.-S., Wang Y.-N., Fouling soft-sensing in condenser based on feature selection and multiple RBF neural network, Chinese Journal of Scientific Instrument, 29, 4, pp. 723-728, (2008)

← 1 2 →