Prediction of Endpoint Phosphorus Content of Molten Steel in BOF Using Weighted K-Means and GMDH Neural Network

钢铁研究学报(英文版), 2012, 19(1): 11-16.

Prediction of Endpoint Phosphorus Content of Molten Steel in BOF Using Weighted K-Means and GMDH Neural Network

^1, , ^2, , ^3, , ^4,

1.School of Computer and Communication Engineering, University of Science and Technology Beijing, Beijing 100083, China Key Laboratory of Advanced Control of Iron and Steel Process of Ministry of Education, Beijing 100083, China

2.School of Metallurgical and Ecological Engineering, University of Science and Technology Beijing, Beijing 100083, China

3.School of Metallurgical and Ecological Engineering, University of Science and Technology Beijing, Beijing 100083, China

4.School of Metallurgical and Ecological Engineering, University of Science and Technology Beijing, Beijing 100083, China

基金项目: Item Sponsored by National Key Technology Research and Development in 11th Five Years Plan of China(2006BAE03A07) Fundamental Research Funds for Central University of China(FRF-AS-09-006B)

关键词： BP神经网络 , K-means , GMDH , 磷含量 , 预测 , 转炉 , 钢水 , 加权

Prediction of Endpoint Phosphorus Content of Molten Steel in BOF Using Weighted K-Means and GMDH Neural Network

Keywords： basic oxygen furnace , endpoint phosphorus content , K-means , neural network , GMDH ,

The hybrid method composed of clustering and predicting stages is proposed to predict the endpoint phos- phorus content of molten steel in BOF （Basic Oxygen Furnace）. At the clustering stage, the weighted K-means is performed to generate some clusters with homogeneous data. The weights of factors influencing the target are calcu- lated using EWM （Entropy Weight Method）. At the predicting stage, one GMDH （Group Method of Data Handling） polynomial neural network is built for each cluster. And the predictive results from all the GMDH polynomial neural networks are integrated into a whole to be the result for the hybrid method. The hybrid method, GMDH polnomial neural network and BP neural network are employed for a comparison. The results show that the proposed hybrid method is effective in predicting the endpoint phosphorus content of molten steel in BOF. Furthermore, the hybrid method outperforms BP neural network and GMDH polynomial neural network.

参考文献

[1]	Narra R;Malaya R K;Shyamal K P .Feed Forward Neural Network for Prediction of End Blow Oxygen in LD Converter Steel Making[J].Materials Research,2010,13(01):-15.
[2]	A.M. Frattini Fileti;T.A. Pacianotto;A. Pitasse Cunha .Neural modeling helps the BOS process to achieve aimed end-point conditions in liquid steel[J].Engineering Applications of Artificial Intelligence: The International Journal of Intelligent Real-Time Automation,2006(1):9-17.
[3]	Anupam Das .Process control strategies for a steel making furnace using ANN with bayesian regularization and ANFIS[J].Expert Systems with Application,2010(2):1075-1085.
[4]	李长荣,赵浩文,谢祥,尹青.基于L-M算法BP神经网络的转炉炼钢终点磷含量预报[J].钢铁,2011(04):23-25,30.
[5]	杨立红,刘浏,何平.基于自适应模糊神经网络系统的转炉终点磷的预报控制模型[J].钢铁研究学报,2002(04):47-51.
[6]	刘剑,袁守谦,李建国.用基于统计模式识别的优化BP网络预报转炉的终点磷含量[J].钢铁研究学报,2005(03):65-67,78.
[7]	谢书明,陶钧,柴天佑.转炉炼钢终点磷的智能预报[J].控制理论与应用,2003(04):555-559.
[8]	HSIEH Nan chen .Hybrid Mining Approach in the Design of Credit Scoring Models[J].Expert Systems with Applications,2005,28(04):655.
[9]	Vida Varahrami .Recognition of Good Prediction of Gold Price Between MLFF and GMDH Neural Network[J].Journal of Economics and International Finance,2011,3(04):204.
[10]	Gopalakrishnan M;Sridhar V;Krishnamurthy H .Some Applications of Clustering in the Design of Neural Networks[J].Pattern Recognition Letters,1995,16(01):59.
[11]	Balakin K V;Korshun V A;Mikhalev II et al.Ranking Im portance of Input Parameters of Neural Networks[J].Expert Systems With Applications,1998,15(03):405.
[12]	KIM Yong seog;STREET WN .An Intelligent System for Customer Targeting:A Data Mining Approach[J].Decision Support Systems,2004,37(02):215.
[13]	P. V. (Sundar) Balakrishnan;Martha C. Cooper;Varghese S. Jacob;Phillip A. Lewis .Comparative performance of the FSCL neural net and K-means algorithm for market segmentation[J].European Journal of Operational Research,1996(2):346-357.
[14]	Kuo R J;Ho L M;Hu C M .Integration of Self Organizing Feature Map and K-means Algorithm for Market Segmentation[J].Computers and Operations Research,2002,29(11):1475.
[15]	Yi Qingming.Blind source separation by weighted K-means clustering[J].系统工程与电子技术(英文版),2008(05):882-887.
[16]	Salih G;Kemal P;Sebnem Y .Efficient Sleep Stage Recogni tion System Based on EEG Signal Using K-Means Clustering Based Feature Weighting[J].Expert Systems With Applications,2010,37(12):7922.
[17]	Chan EY;Ching WK;Ng MK;Huang JZ .An optimization algorithm for clustering using weighted dissimilarity measures[J].Pattern Recognition: The Journal of the Pattern Recognition Society,2004(5):943-952.
[18]	Chieh-Yuan Tsai;Chuang-Cheng Chiu .Developing a feature weight self-adjustment mechanism for a K-means clustering algorithm[J].Computational statistics & data analysis,2008(10):4658-4672.
[19]	ZOU Zhi-hong,YUN Yi,SUN Jing-nan.Entropy method for determination of weight of evaluating indicators in fuzzy synthetic evaluation for water quality assessment[J].环境科学学报(英文版),2006(05):1020-1023.
[20]	Evaluation of Black-Start Schemes Employing Entropy Weight-Based Decision-Making Theory[J].Journal of energy engineering,2010(2):42-49.

上一张下一张

计量

下载量()
访问量()

作者相关

在本站搜索
在百度学术搜索
在万方数据库搜索
在CNKI搜索

文章评分

您的评分：
1

0%
2

0%
3

0%
4

0%
5

0%

材料期刊网

Prediction of Endpoint Phosphorus Content of Molten Steel in BOF Using Weighted K-Means and GMDH Neural Network

Prediction of Endpoint Phosphorus Content of Molten Steel in BOF Using Weighted K-Means and GMDH Neural Network

参考文献