基于FOA-GRNN模型的转炉炼钢终点预报
|
摘要
目前广泛采用的RBF神经网络具有训练时间长与训练困难等缺陷.本研究结合实际生产数据,建立了FOA-GRNN神经网络预报模型,并对转炉终点温度与碳质量分数进行预报.结果表明:与RBF神经网络相比,FOA-GRNN神经网络可以有效提高命中率并满足实际生产要求.当碳质量分数绝对误差小于±0. 03%时,FOA-GRNN神经网络预报命中率可由91%提高至94%;当温度绝对误差小于±15℃时,预报命中率可由89%提高至97%.同时,FOA-GRNN神经网络训练时间在RBF神经网络基础上分别降低了42. 22%与37. 08%,预报结果与实测值的均方差也有一定的降低,故可为现场生产提供重要的参考.
The widely used RBF neural network nowadays has shortcomings of long training time and difficult training.Based on the production data,a FOA-GRNN model was established to predict the end-point temperature and carbon content in the present paper.The results showed that the hit rates of the FOA-GRNN model can meet requirement of the production and are higher than that of RBF model.When the absolute error of predicted carbon content is within ± 0.03%,the accuracy of the model increases from 91% to 94%.When the absolute error of predicted temperature is within ± 15℃,accuracy of the model increases from 89% to 97%.Meanwhile,the training time decreases 42.22% and 37.08% and the mean square errors also decrease.So that it can provide an important reference for practical applications.
The widely used RBF neural network nowadays has shortcomings of long training time and difficult training.Based on the production data,a FOA-GRNN model was established to predict the end-point temperature and carbon content in the present paper.The results showed that the hit rates of the FOA-GRNN model can meet requirement of the production and are higher than that of RBF model.When the absolute error of predicted carbon content is within ± 0.03%,the accuracy of the model increases from 91% to 94%.When the absolute error of predicted temperature is within ± 15℃,accuracy of the model increases from 89% to 97%.Meanwhile,the training time decreases 42.22% and 37.08% and the mean square errors also decrease.So that it can provide an important reference for practical applications.
引文
[1] Wang Z,Chang Ju Q P,et al. Prediction model of endpoint manganese content for BOF steelmaking process[J]. ISIJ International,2012,52(9):1585-1590.
[2]汪宙.转炉冶炼中高碳钢过程及终点控制研究[D].北京:北京科技大学,2016.(Wang Zhou. Study on the control of steelmaking process and blowing end-point for medium-high carbon steel melting by converter[D]. Beijing:University of Science and Technology Beijing,2016.)
[3]谢书明,孙凯,陈昌.基于RBF神经网络的转炉炼钢终点预报[J].沈阳工业大学学报,2006,28(4):405-408.(Xie Shuming, Sun Kai, Chen Chang. BOF endpoint prediction based on RBF neural network[J]. Journal of Shenyang University of Technology, 2006, 28(4):405-408.)
[4]姚俊峰,江金宏,梅炽,等.小波神经网络在炼铜转炉炉渣重量和成分预报中的应用[J].有色金属,2001,53(2):42-44.(Yao Junfeng,Jiang Jinhong,Mei Chi,et al. Application of wavelet neural network in forecasting slag weight and components of copper-smelting converter[J]. Nonferrous Metals,2001,53(2):42-44.)
[5]刘俊,杨荃,何安瑞,等.贝叶斯框架下的LS-SVM在热连轧机轧制力预报中的应用[J].钢铁研究学报,2011,23(6):5-8.(Liu Jun,Yang Quan,He Anrui,et al. Application of LSSVM with the bayesian evidence framework to prediction of rolling load of hot strip rolling mill[J]. Journal of Iron and Steel Research,2011,23(6):5-8.)
[6]李长荣,赵浩文,谢祥,等.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,2011,46(4):23-25.(Li Changrong,Zhao Haowen,Xie Xiang,et al. Prediction of end-point phosphorus content for BOF based on LM BP neural network[J]. Iron and Steel,2011,46(4):23-25.)
[7]谢书明,陈昌,丁惜瀛.基于BP神经网络的转炉炼钢终点预报[J].沈阳工业大学学报,2007,29(6):707-710.(Xie Shuming, Chen Chang, Ding Xiying. Endpoint prediction of basic-oxygen furnace based on BP neural network[J]. Journal of Shenyang University of Technology,2007,29(6):707-710.)
[8]任彦军,王家伟,张晓兵,等.基于LM算法BP神经网络的高炉-转炉界面铁水温度预报模型[J].钢铁,2012,47(9):40-42.(Ren Yanjun, Wang Jiawei, Zhang Xiaobing, et al.Prediction model of hot metal temperature for BF-BOF interface based on LM BP neural network[J]. Iron and Steel,2012,47(9):40-42.)
[9]柴天佑,谢书明,杜斌,等.基于RBF神经网络的转炉炼钢终点预报[J].中国有色金属学报,1999,9(4):868-872.(Chai Tianyou,Xie Shuming,Du Bin, et al. Endpoint prediction of basic oxygen furnace steelmaking based on RBF neural network[J]. The Chinese Journal of Nonferrous Metals,1999,9(4):868-872.)
[10]张军红,沈峰满,谢安国. G-BP算法在烧结矿FeO指标预测中的应用[J].东北大学学报(自然科学版),2002,23(11):1073-1075.(Zhang Junhong, Shen Fengman, Xie Anguo. The application of G-BP in FeO content prediction during sintering[J]. Journal of Northeastern University(Natural Science),2002,23(11):1073-1075.)
[11]高彩云,崔希民,高宁,等. GRNN神经网络在矿区地表变形预测中的应用[J].金属矿山,2014,43(3):97-100.(Gao Caiyun,Cui Ximin,Gao Ning,et al. Application of GRNN in the prediction of surface deformation in mining areas[J]. Metal Mine,2014,43(3):97-100.)
[12]钱光兴,崔东文. RBF与GRNN神经网络模型在城市需水预测中的应用[J].水资源与水工程学报,2012,23(5):148-152.(Qian Guangxing,Cui Dongwen. Application of RBF and GRNN neural network model in the urban water forecast[J].Journal of Water Resources&Water Engineering,2012,23(5):148-152.)
[13]王小龙,全强明,熊立新.基于改进粒子群-GRNN模型的地铁隧道沉降预测[J].世界科技研究与发展,2016(6):1142-1146.(Wang Xiaolong,Quan Qiangming,Xiong Lixin. Prediction on metro tunnel settlement based on modified PSO-GRNN model[J]. World SCI-TECH R&D,2016(6):1142-1146.)
[14]葛柳飞,李克清,戴欢.基于自适应GRNN的无线室内定位算法[J].计算机工程,2016,42(6):81-85.(Ge Liufei,Li Keqing,Dai Huan. Wireless indoor location algorithm based on adaptive GRNN[J]. Computer Engineering,2016,42(6):81-85.)
[15]郭斌,孟令启,杜勇,等.基于GRNN神经网络的中厚板轧机厚度预测[J].中南大学学报(自然科学版),2011,42(4):960-965.(Guo Bin, Meng Lingqi, Du Yong, et al. Thickness prediction of medium plate mill based on GRNN neural network[J]. Journal of Central South University(Science and Technology),2011,42(4):960-965.)
[16] Dong L,Li X. Comprehensive models for evaluating rockmass stability based on statistical comparisons of multiple classifiers[J]. Mathematical Problems in Engineering,2013.
[17] Chausa P,Tormos J M. Data mining applied to the cognitive rehabilitation of patients with acquired brain injury[J]. Expert Systems with Applications an International Journal,2013,40(4):1054-1060.
[18] Pan Wen-Tsao. A new fruit fly optimization algorithm:taking the financial distress model as an example[J]. KnowledgeBased Systems,2012,26(2):69-74.
[19]李蓬勃,闫晓冉,徐东瑞. BP神经网络和多元线性回归在粮食产量空间分布预测中的比较[J].干旱区资源与环境,2014,28(9):74-79.(Li Pengbo,Yan Xiaoran,Xu Dongrui. Comparison of grain yield spatial distribution forecast between the models of BP neural network and multiple linear regression[J]. Journal of Arid Land Resources and Environment,2014,28(9):74-79.)
[2]汪宙.转炉冶炼中高碳钢过程及终点控制研究[D].北京:北京科技大学,2016.(Wang Zhou. Study on the control of steelmaking process and blowing end-point for medium-high carbon steel melting by converter[D]. Beijing:University of Science and Technology Beijing,2016.)
[3]谢书明,孙凯,陈昌.基于RBF神经网络的转炉炼钢终点预报[J].沈阳工业大学学报,2006,28(4):405-408.(Xie Shuming, Sun Kai, Chen Chang. BOF endpoint prediction based on RBF neural network[J]. Journal of Shenyang University of Technology, 2006, 28(4):405-408.)
[4]姚俊峰,江金宏,梅炽,等.小波神经网络在炼铜转炉炉渣重量和成分预报中的应用[J].有色金属,2001,53(2):42-44.(Yao Junfeng,Jiang Jinhong,Mei Chi,et al. Application of wavelet neural network in forecasting slag weight and components of copper-smelting converter[J]. Nonferrous Metals,2001,53(2):42-44.)
[5]刘俊,杨荃,何安瑞,等.贝叶斯框架下的LS-SVM在热连轧机轧制力预报中的应用[J].钢铁研究学报,2011,23(6):5-8.(Liu Jun,Yang Quan,He Anrui,et al. Application of LSSVM with the bayesian evidence framework to prediction of rolling load of hot strip rolling mill[J]. Journal of Iron and Steel Research,2011,23(6):5-8.)
[6]李长荣,赵浩文,谢祥,等.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,2011,46(4):23-25.(Li Changrong,Zhao Haowen,Xie Xiang,et al. Prediction of end-point phosphorus content for BOF based on LM BP neural network[J]. Iron and Steel,2011,46(4):23-25.)
[7]谢书明,陈昌,丁惜瀛.基于BP神经网络的转炉炼钢终点预报[J].沈阳工业大学学报,2007,29(6):707-710.(Xie Shuming, Chen Chang, Ding Xiying. Endpoint prediction of basic-oxygen furnace based on BP neural network[J]. Journal of Shenyang University of Technology,2007,29(6):707-710.)
[8]任彦军,王家伟,张晓兵,等.基于LM算法BP神经网络的高炉-转炉界面铁水温度预报模型[J].钢铁,2012,47(9):40-42.(Ren Yanjun, Wang Jiawei, Zhang Xiaobing, et al.Prediction model of hot metal temperature for BF-BOF interface based on LM BP neural network[J]. Iron and Steel,2012,47(9):40-42.)
[9]柴天佑,谢书明,杜斌,等.基于RBF神经网络的转炉炼钢终点预报[J].中国有色金属学报,1999,9(4):868-872.(Chai Tianyou,Xie Shuming,Du Bin, et al. Endpoint prediction of basic oxygen furnace steelmaking based on RBF neural network[J]. The Chinese Journal of Nonferrous Metals,1999,9(4):868-872.)
[10]张军红,沈峰满,谢安国. G-BP算法在烧结矿FeO指标预测中的应用[J].东北大学学报(自然科学版),2002,23(11):1073-1075.(Zhang Junhong, Shen Fengman, Xie Anguo. The application of G-BP in FeO content prediction during sintering[J]. Journal of Northeastern University(Natural Science),2002,23(11):1073-1075.)
[11]高彩云,崔希民,高宁,等. GRNN神经网络在矿区地表变形预测中的应用[J].金属矿山,2014,43(3):97-100.(Gao Caiyun,Cui Ximin,Gao Ning,et al. Application of GRNN in the prediction of surface deformation in mining areas[J]. Metal Mine,2014,43(3):97-100.)
[12]钱光兴,崔东文. RBF与GRNN神经网络模型在城市需水预测中的应用[J].水资源与水工程学报,2012,23(5):148-152.(Qian Guangxing,Cui Dongwen. Application of RBF and GRNN neural network model in the urban water forecast[J].Journal of Water Resources&Water Engineering,2012,23(5):148-152.)
[13]王小龙,全强明,熊立新.基于改进粒子群-GRNN模型的地铁隧道沉降预测[J].世界科技研究与发展,2016(6):1142-1146.(Wang Xiaolong,Quan Qiangming,Xiong Lixin. Prediction on metro tunnel settlement based on modified PSO-GRNN model[J]. World SCI-TECH R&D,2016(6):1142-1146.)
[14]葛柳飞,李克清,戴欢.基于自适应GRNN的无线室内定位算法[J].计算机工程,2016,42(6):81-85.(Ge Liufei,Li Keqing,Dai Huan. Wireless indoor location algorithm based on adaptive GRNN[J]. Computer Engineering,2016,42(6):81-85.)
[15]郭斌,孟令启,杜勇,等.基于GRNN神经网络的中厚板轧机厚度预测[J].中南大学学报(自然科学版),2011,42(4):960-965.(Guo Bin, Meng Lingqi, Du Yong, et al. Thickness prediction of medium plate mill based on GRNN neural network[J]. Journal of Central South University(Science and Technology),2011,42(4):960-965.)
[16] Dong L,Li X. Comprehensive models for evaluating rockmass stability based on statistical comparisons of multiple classifiers[J]. Mathematical Problems in Engineering,2013.
[17] Chausa P,Tormos J M. Data mining applied to the cognitive rehabilitation of patients with acquired brain injury[J]. Expert Systems with Applications an International Journal,2013,40(4):1054-1060.
[18] Pan Wen-Tsao. A new fruit fly optimization algorithm:taking the financial distress model as an example[J]. KnowledgeBased Systems,2012,26(2):69-74.
[19]李蓬勃,闫晓冉,徐东瑞. BP神经网络和多元线性回归在粮食产量空间分布预测中的比较[J].干旱区资源与环境,2014,28(9):74-79.(Li Pengbo,Yan Xiaoran,Xu Dongrui. Comparison of grain yield spatial distribution forecast between the models of BP neural network and multiple linear regression[J]. Journal of Arid Land Resources and Environment,2014,28(9):74-79.)