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  2014 

基于PSO-ELM的建筑物爆破震动速度预测

DOI: 10.3981/j.issn.1000-7857.2014.19.001, PP. 15-20

Keywords: 爆破震动速度,极限学习机,粒子群算法

Full-Text   Cite this paper   Add to My Lib

Abstract:

针对影响爆破震动速度因素之间复杂的非线性关系,利用粒子群算法(PSO)的全局搜索最优解原理和极限学习机(ELM)处理非线性关系能力,建立了爆破震动速度预测的PSO-ELM模型。以某地区爆破震动实测数据为例,选取总药量、最大段药量、爆破点与监测点距离、建筑物所在地面震动速度和测点到地面的高度等5个因素为输入变量,以建筑物震动速度为输出变量。结果表明,PSO-ELM模型训练值与预测值,测试值与预测值的均方误差分别为0.18和2.56,平均相对误差控制在6%以内,显示出该模型具有良好的训练精度和泛化能力。对比传统ELM模型,PSO-ELM模型不但提高了精度和泛化能力,而且降低了训练样本数和隐含层节点数变化对训练结果的影响,提高了模型的拟合能力,在类似预测工程中有一定的推广价值。

References

[1]  张守中. 爆炸与冲击动力学[M]. 北京: 兵器工业出版社, 1993. Zhang Shouzhong. Explosion and shock dynamics[M]. Beijing: Ordnance Industry Publishing House, 1993.
[2]  杨佑发, 崔波. 爆破震动速度峰值的预测[J]. 振动与冲击, 2009, 28 (10): 195-197. Yang Youfa, Cui Bo. Prediction for vibration intensity due to blasting induced ground motions[J]. Journal of Vibration and Shock, 2009, 28 (10): 195-197.
[3]  张世雄, 杨明亮, 尹家国, 等. 预测爆破波振动强度的经验公式及其在 采矿中的应用[J]. 爆破, 2000, 17(3): 3-17. Zhang Shixiong, Yang Mingliang, Yin Jiaguo, et al. An empirical formula of calculating the vibrating intensity of explosive wave and its application in mining[J]. Blasting, 2000, 17(3): 13-17.
[4]  Hao H, Ma G W, Lu Y. Damage assessment of masonry infilled RC frames subjected to blasting induced ground excitations[J]. Engineering Structures, 2002, 24(6): 799-809.
[5]  龚声武, 凌同华. 爆破震速预测的模糊神经网络模型及其应用[J]. 矿业 研究与开发, 2009, 29(2): 95-97. Gong Shengwu, Ling Tonghua. Fuzzy neural network model of peak particle vibration velocity forecast for blasting and its application[J]. Mining Research and Development, 2009, 29(2): 95-97.
[6]  邵晓宁, 徐颖. 岩体爆破振速和损伤预测的支持向量机方法[J]. 采矿 与安全工程学报, 2011, 28(3): 384-390. Shao Xiaoning, Xu Ying. Prediction of vibration velocity and damnification during rock blasting based on support vector machine method[J]. Journal of Mining & Safety Engineering, 2011, 28(3): 384-390.
[7]  潘华贤, 程国建, 蔡磊. 极限学习机与支持向量机在储层渗透率预测 中的对比研究[J]. 计算机工程与科学, 2010, 32(2): 131-134. Pan Huaxian, Cheng Guojian, Cai Lei. Comparison of the extreme learning machine with the support vector machine for reservoir permeability prediction[J]. Computer Engineering & Science, 2010, 32 (2): 131-134.
[8]  Huang G B. Zhu Q Y. Siew C K. Extreme learning machine: Theory and application[J]. Neuro Computing, 2006, 70(1-3): 489-501.
[9]  刘国海, 张东娟, 梅从立. 基于IRLS-ELM生物发酵在线软测量建模 方法[J]. 东南大学学报: 自然科学版, 2011, 41(S1): 10-13. Liu Guohai, Zhang Dongjuan, Mei Congli. Soft sensor modeling based on improved regularized least-squares extreme learning machine method[J]. Journal of Southeast University: Natural Science Edition, 2011, 41(S1): 10-13.
[10]  王杰, 毕浩洋. 一种基于粒子群优化的极限学习机[J]. 郑州大学学报: 理学版, 2013, 45(1): 100-104. Wang Jie, Bi Haoyang. A new extreme learning machine optimized by PSO[J]. Journal of Zhengzhou University: Natural Science Edition, 2013, 45(1): 100-104.
[11]  Kennedy J, Eberhart R. Particle swarm optimization[C]//Proceedings of IEEE International Conference on Neural Networks. Perth, Australia: IEEE 1995: 1942-1948.
[12]  张红亮, 王水林, 吕颖慧, 等. 爆破震动效应的支持向量机分析预测[J]. 矿业研究与开发, 2007, 27(4): 57-58. Zhang Hongliang, Wang shuilin, Lü Yinghui, et al. Analysis and forecast of basting vibration effect based on support vector machine[J]. Mining Research and Development, 2007, 27(4): 57-58.
[13]  雷德明, 严新平. 多目标智能优化算法及其应用[M]. 北京: 科学出版 社, 2009. Lei Deming, Yan Xinping. Multiple objective intelligent optimization algorithms and application[M]. Beijing: Science Press, 2009.
[14]  范胜波, 王太勇, 汪文津, 等. 样本数量对切削力的神经网络预测精 度的影响[J]. 西南交通大学学报, 2005, 40(5): 637-640. Fan Shengbo, Wang Taiyong, Wang Wenjin, et al. Effect of number of training samples on ANN prediction accuracy for cutting force[J]. Journal of Southwest Jiaotong University, 2005, 40(5): 637-640.
[15]  李夕兵. 凿岩爆破工程[M]. 长沙: 中南大学出版社, 2011. Li Xibing. Drilling and blasting engineering[M]. Changsha: Central South University Press, 2011.
[16]  钮强. 岩石爆破机理[M]. 沈阳: 东北工学院出版社, 1990. Niu Qiang. Mechanism of rock blasting[M]. Shenyang: Press of Northeastern Technique Institute, 1990.

Full-Text

Contact Us

service@oalib.com

QQ:3279437679

WhatsApp +8615387084133