全部 标题 作者
关键词 摘要

OALib Journal期刊
ISSN: 2333-9721
费用:99美元

查看量下载量

相关文章

更多...
科技导报  2015 

超大能力超细全尾砂长距离自流输送临界流速ELM预测

DOI: 10.3981/j.issn.1000-7857.2015.15.003, PP. 27-31

Keywords: 超大能力,临界流速,极限学习机,预测精度,运算效率

Full-Text   Cite this paper   Add to My Lib

Abstract:

为准确预测司家营铁矿超大能力超细全尾砂浆体长距离管道自流输送的临界流速,对比传统的BP神经网络、支持向量机(SVM),建立了以管道直径、物料平均粒径、浆体体重和体积浓度为输入因子,临界流速为输出因子的极限学习机(ELM)预测新模型。研究结果表明,ELM模型与SVM模型的相对误差均控制在5%以内,远低于BP神经网络模型的9.56%。由于隐层节点参数均随机选取且无需调节,使得ELM算法在隐层节点数为110和200时,训练时间仅为0.02s和0.05s,远少于同节点状态SVM模型的0.04s和0.095s,且隐含节点数越多,训练时间差距越大,运算效率越高。

References

[1]  王春来, 吴爱祥, 刘晓辉, 等. 深井开采微震活动容量维Df变化特征 [J]. 北京科技大学学报, 2010, 32(11): 1379-1385. Wang Chunlai, Wu Aixiang, Liu Xiaohui, et al. Variation characteristics of capacity dimension Df with micro seismicity in deep mining[J]. Journal of University of Science and Technology, 2010, 32 (11): 1379-1385.
[2]  王新民, 古德生, 张钦礼. 深井矿山充填理论与管道输送技术[M]. 长 沙: 中南大学出版社, 2010. Wang Xinmin, Gu Desheng, Zhang Qinli. Theory of backfilling activity and pipeline transportation technology of backfill in deep mines[M]. Changsha: Central South University Press, 2010.
[3]  王洪武. 多相复合膏体充填料配比与输送参数优化[D]. 长沙: 中南大 学, 2010. Wang Hongwu. Optimum material proportion and transportation parameter of multiphase complex paste backfill[D]. Changsha: Central South University, 2010.
[4]  Trafalis T B, Oladunni O, Papavassiliou D V. Two-phase flow regime identification with a multiclassification support vector machine (SVM) model[J]. Industrial & Engineering Chemistry Research, 2005, 44(12): 4414-4426.
[5]  张钦礼, 陈秋松, 胡威, 等. 充填钻孔寿命SVM优化预测模型研究[J]. 中南大学学报: 自然科学版, 2014, 45(2): 536-541. Zhang Qinli, Chen Qiusong, Hu Wei, et al. SVM optimal prediction model of backfill drill-hole life[J]. Journal of Central South University: Science and Technology Edition, 2014, 45(2): 536-541.
[6]  王新民, 贺严, 陈秋松. 基于Fluent的分级尾砂料浆满管流输送技术 [J]. 科技导报, 2014, 32(1): 55-60. Wang Xinmin, He Yan, Chen Qiusong. Full pipeline flowing transportation technology of classified tailings based on the Fluent software[J]. Science & Technology Review, 2014, 32(1): 55-60.
[7]  吴迪, 蔡嗣经, 杨威, 等. 基于CFD的充填管道固-液两相流输送模拟 及试验[J]. 中国有色金属学报, 2012, 22(7): 2133-2139. Wu Di, Cai Sijing, Yang Wei, et al. Simulation and experiment of backfilling pipeline transportation of solid-liquid two-phase flow based on CFD[J]. Chinese Journal of Nonferrous Metals, 2012, 22(7): 2133- 2139.
[8]  Berri R N, Sahai S K, Durand J B, et al. Serum brain naturietic peptide measurements reflect fluid balance after pancreatectomy[J]. Journal of the American College of Surgeons, 2012, 214(5): 778-787.
[9]  李小冬. 核极限学习机的理论与算法及其在图像处理中的应用[D]. 杭州: 浙江大学, 2014. Li Xiaodong. Kernel ELM theory and algorithms and application in image processing[D]. Hangzhou: Zhejiang University, 2014.
[10]  Lan Y, Soh Y C, Huang G B. Ensemble of online sequential extreme learning machine[J]. Neurocomputing, 2009, 72(13): 3391-3395.
[11]  蔡磊, 程国建, 潘华贤. 极限学习机在岩性识别中的应用[J]. 计算机 工程与设计, 2010, 31(9): 2010-2012. Cai Lei, Cheng Guojian, Pan Huaxian. Lithologic identification based on ELM[J]. Computer Engineering and Design, 2010, 31(9): 2010- 2012.
[12]  Huang G B, Ding X, Zhou H. Optimization method based extreme learning machine for classification[J]. Neurocomputing, 2010, 74(1): 155-163.
[13]  尹钊, 贾尚晖. Moore-Penrose广义逆矩阵与线性方程组的解[J]. 数 学的实践与认识, 2009, 39(9): 239-244. Yin Zhao, Jia Shanghui. Solution of generalized inverse matrix and linear equations [J]. Mathematics in Practice and Theory, 2009, 39(9): 239-244.
[14]  王新民, 张德明, 张钦礼, 等. 基于FLOW-3D软件的深井膏体管道 自流输送性能[J]. 中南大学学报: 自然科学版, 2011, 42(7): 2101- 2107. Wang Xinmin, Zhang Deming, Zhang Qinli, et al. Pipeline selfflowing transportation property of paste based on FLOW-3D software in deep mine[J]. Journal of Central South University: Science and Technology Edition, 2011, 42(7): 2101-2107.
[15]  南世卿, 胡树军, 胡亚军. 石人沟铁矿充填管道布置方案优化研究 [J]. 矿业研究与开发, 2014, 34(3): 25-28. Nan Shiqing, Hu Shujun, Hu Yajun. Research on the optimization of filling pipeline layout in Shirengou iron mine[J]. Mining Research and Development, 2014, 34(3): 25-28.

Full-Text

Contact Us

service@oalib.com

QQ:3279437679

WhatsApp +8615387084133