基于炉口辐射和改进神经网络的转炉终点预测模型

温宏愿; 赵琦; 陈延如; 周木春; 张猛; 许凌飞

光学学报, 2008, 28 (11): 2131, 网络出版: 2008-11-17

基于炉口辐射和改进神经网络的转炉终点预测模型

Basic-Oxygen-Furnace Endpoint Forecasting Model Based on Radiation and Modified Neural Network

论文大纲

温宏愿 ^*赵琦陈延如周木春张猛许凌飞

作者单位

南京理工大学电子工程与光电技术学院, 江苏南京 210094

信号处理预测神经网络辐射信息转炉终点 signal processing forecasting neural networks radiation information basic oxygen furnace endpoint

摘要

针对国内外转炉炼钢终点控制的现状, 建立了一种用于终点预测的神经网络模型。以炉口辐射信息获取系统为实验平台, 运用光纤谱分复用和颜色空间模型转换技术, 分析发现了光谱与图像信息特征量在吹炼过程中呈现出中前期类似、末期相反的规律。从得到的特征规律曲线中选用一些关键特征量, 在改进的修正系数算法基础上, 进行了模型的训练和预测分析。实验结果表明：响应时间在2 s以内, 满足快速判定的时间要求; 改进算法的模型预测精度高于常规算法, 该系统可以正常工作在转炉炼钢的恶劣环境下, 达到了预期效果。

Abstract

Considering the present situation of the basic oxygen furnace (BOF) steelmaking endpoint control, a neural network model was established to judge the steelmaking endpoint. Based on the furnace mouth radiation information acquisition platform, the spectrum and image characteristics were analyzed using the fiber spectrum division multiplexing technology and the color space conversion method. The results indicate that they are similar at early-middle stage but inverse at the steelmaking late stage. Some appropriate variables were selected from the law curve as the neural network model parameters and the model was trained and forecasted on the basis of an improved back propagation (BP) neural network correction coefficient algorithm. The experimental results show the response time is less than 2 s which meets the requirements of online endpoint judgment, and the prediction accuracy of the proposed algorithm is better than that of the conventional algorithm. The system works stably and the anticipated effect is achieved.

参考文献

[1] 冯捷,张红文. 转炉炼钢生产[M]. 北京：冶金工业出版社, 2006. 332～338

Feng Jie, Zhang Hongwen. BOF Steelmaking[M]. Beijing: Metallurgical Industry Press, 2006. 332～338

[2] . Mass spectrometry for oxygen steel-making control[J]. Steel Times, 1997, 225(11): 439-440.

[3] Sharan A. Light sensors for BOF carbon control in low carbon heats[C]. Steelmaking Conference Proceedings, 1998, 81: 337～345

[4] . 我国转炉炼钢的现状和发展[J]. 特殊钢, 2005, 26(4): 1-5.

. Present situation and development of converter steelmaking in China[J]. Special Steel, 2005, 26(4): 1-5.

[5] . An outlier identification and judgment method for an improved neural-network BOF forecasting model[J]. Steel Research International, 2008, 79(5): 323-331.

[6] . 基于神经网络的转炉炼钢终点控制[J]. 控制理论与应用, 2003, 20(6): 903-907.

. BOF steelmaking endpoint control based on network[J]. Control Theory and Applications, 2003, 20(6): 903-907.

[7] Cemalettin K, Harnun T, Recep A et al.. Bofy-fuzzy logic control for the basic oxygen furnace (BOF)[J]. Robotics and Autonomous System, 2004, 49(3～4): 193～205

[8] . Color gamut transform pairs[J]. Computer Graphics, 1978, 12(3): 12-19.

[9] Chen Chulung, Wu Weijun. Color pattern recognition with the multi-channel non-zero-order joint transform correlator based on the HSV color space[J]. Opt. Commun., 2005, 244(1～6): 51～59

[10] 赵建华,方俊,疏学明. 基于神经网络的火灾烟雾识别方法[J]. 光学学报, 2003, 23(9): 1086～1089

Zhao Jianhua, Fang Jun, Shu Xueming. An idetification method of fire smoke based on neural network[J]. Acta Optica Sinica, 2003, 23(9): 1086～1089

[11] 唐燕, 陈文静. 应用神经网络的复杂物体三维测量[J]. 光学学报, 2007, 27(8): 1435～1439

Tang Yan, Chen Wenjing. Neural network applied to three-dimensional measurement of complex objects[J]. Acta Optica Sinica, 2007, 27(8): 1435～1439

[12] 杜西亮, 戴景民. 基于神经网络的分振幅光偏振仪的数据处理[J]. 中国激光, 2007, 34(1): 89～93

Du Xiliang, Dai Jingmin. Data processing method for the division-of-amplitude photopolarimeter based on an artificial neural network[J]. Chin. J. Lasers, 2007, 34(1): 89～93

[13] 齐锋, 刘文清, 周斌等. 利用人工神经网络方法提高差分光学吸收光谱系统测量精度研究[J]. 光学学报, 2002, 22(11): 1345～1349

Qi Feng, Liu Wenqing, Zhou Bin et al.. Improving DOAS system measurement precision with artificial neutral network method[J]. Acta Optica Sinica, 2002, 22(11): 1345～1349

[14] 陈开周. 最优化计算方法[M]. 西安：西北电讯工程学院出版社, 1985. 83～87

Chen Kaizhou. Optimized Arithmetic[M]. Xi′an: Northwest Institute of Telecommunication Engineering Press, 1985. 83～87

[15] . Neural networks with a continuous squashing function in the output are universal approximators[J]. Neural Networks, 2000, 13(6): 561-563.

温宏愿, 赵琦, 陈延如, 周木春, 张猛, 许凌飞. 基于炉口辐射和改进神经网络的转炉终点预测模型[J]. 光学学报, 2008, 28(11): 2131. Wen Hongyuan, Zhao Qi, Chen Yanru, Zhou Muchun, Zhang Meng, Xu Lingfei. Basic-Oxygen-Furnace Endpoint Forecasting Model Based on Radiation and Modified Neural Network[J]. Acta Optica Sinica, 2008, 28(11): 2131.

基于炉口辐射和改进神经网络的转炉终点预测模型

关于本站 Cookie 的使用提示

全站搜索

基于炉口辐射和改进神经网络的转炉终点预测模型

相关论文

相关资讯

关于本站 Cookie 的使用提示

全站搜索