Please wait a minute...
 首页  期刊介绍 期刊订阅 联系我们 横山亮次奖 百年刊庆
 
最新录用  |  预出版  |  当期目录  |  过刊浏览  |  阅读排行  |  下载排行  |  引用排行  |  横山亮次奖  |  百年刊庆
清华大学学报(自然科学版)  2019, Vol. 59 Issue (8): 628-634    DOI: 10.16511/j.cnki.qhdxxb.2019.26.008
  水利水电工程 本期目录 | 过刊浏览 | 高级检索 |
基于CNN模型的施工现场典型安全隐患数据学习
林鹏1, 魏鹏程1, 樊启祥2, 陈闻起3
1. 清华大学 水利水电工程系, 北京 100084;
2. 中国华能集团有限公司, 北京 100031;
3. 清华大学 计算机科学与技术系, 北京 100084
CNN model for mining safety hazard data from a construction site
LIN Peng1, WEI Pengcheng1, FAN Qixiang2, CHEN Wenqi3
1. Department of Hydraulic Engineering, Tsinghua University, Beijing 100084, China;
2. China Huaneng Group Co., Ltd., Beijing 100031, China;
3. Department of Computer Science and Technology, Tsinghua University, Beijing 100084, China
全文: PDF(1080 KB)  
输出: BibTeX | EndNote (RIS)      
摘要 该文旨在通过卷积神经网络(convolutional neural networks,CNN)模型对基础设施建设期典型安全隐患进行数据学习与挖掘,为现场智能安全管控提供方法和依据。依托于Wesafety平台实时统计出的某大型水电站现场安全隐患数据,分析了现场典型安全隐患特征,提出了基于CNN的安全隐患学习与挖掘模型,并定义了模型结构的卷积层、池化层、全连接层以及训练和测试流程,开发了相应的程序。结果表明:该方法提高了基础设施建设现场扁平-闭环安全管理的效率,为智能安全管理提供了崭新的思路,达到了机器自动识别典型隐患的目的,研究结果对建设工程安全隐患自动分类分析具有参考意义。
服务
把本文推荐给朋友
加入引用管理器
E-mail Alert
RSS
作者相关文章
林鹏
魏鹏程
樊启祥
陈闻起
关键词 智能安全管理安全隐患数据学习与挖掘卷积神经网络    
Abstract:A convolutional neural network model was used to mine typical safety hazard data from an infrastructure construction site for site intelligent safety control. Safety hazard data from a hydropower station during construction was analyzed to show the typical safety hazard data characteristics. The learning and mining used a convolution neural network (CNN) with the convolution layer, pooling layer, fully connected layer and training and testing processes defined here. The data mining and learning improves the safety flat-closed loop management safety for the construction site for intelligent safety management. The method then automatically identifies typical safety hazards for construction sites. The results provide guidance for automatic classification and analysis of safety hazards for a construction project.
Key wordsintelligent safety management    safety hazards    data learning and mining    convolutional neural networks
收稿日期: 2018-10-07      出版日期: 2019-08-05
引用本文:   
林鹏, 魏鹏程, 樊启祥, 陈闻起. 基于CNN模型的施工现场典型安全隐患数据学习[J]. 清华大学学报(自然科学版), 2019, 59(8): 628-634.
LIN Peng, WEI Pengcheng, FAN Qixiang, CHEN Wenqi. CNN model for mining safety hazard data from a construction site. Journal of Tsinghua University(Science and Technology), 2019, 59(8): 628-634.
链接本文:  
http://jst.tsinghuajournals.com/CN/10.16511/j.cnki.qhdxxb.2019.26.008  或          http://jst.tsinghuajournals.com/CN/Y2019/V59/I8/628
  图1 “有价值”信息预处理生成矩阵流程
  图2 CNN 分析典型隐患流程
  图3 反向传播示例
  图4 训练流程图
  图5 训练主要结果
[1] 刘大有, 陈慧灵, 齐红, 等. 时空数据挖掘研究进展[J]. 计算机研究与发展, 2013, 50(2):225-239. LIU D Y, CHEN H L, QI H, et al. Advances in spatiotemporal data mining[J]. Journal of Computer Research and Development, 2013, 50(2):225-239. (in Chinese)
[2] 冯勤. 基于回归数据挖掘预测系统的分析与研究[D]. 天津:天津大学, 2005. FENG Q. The analysis and research of regress-based prediction system on data mining[D]. Tianjin:Tianjin University, 2005. (in Chinese)
[3] ZHOU G Q, WANG L B, WANG D, et al. Integration of GIS and data mining technology to enhance the pavement management decision making[J]. Journal of Transportation Engineering, 2010, 136(4):332-341.
[4] 杨铁建. 基于支持向量机的数据挖掘技术研究[D]. 西安:西安电子科技大学, 2005. YANG T J. Research of data mining techniques based on support vector machines[D]. Xi'an:Xi'an University, 2005. (in Chinese)
[5] 黄静华. 支持向量机算法研究及在气象数据挖掘中的应用[D]. 北京:中国矿业大学(北京), 2011. HUANG J H. The research of support vector machine algorithm and the application in meteorological data mining[D]. Beijing:China University of Mining and Technology (Beijing), 2011. (in Chinese)
[6] 蒋旻. 基于空间数据库的数据挖掘技术[J]. 武汉科技大学学报(自然科学版), 2002, 25(2):183-186. JIANG M. Spatial data mining based on spatial databases[J]. Journal of Wuhan University of Science and Technology (Natural Science Edition), 2002, 25(2):183-186. (in Chinese)
[7] 郭翠翠. 基于神经网络的数据挖掘方法研究[D]. 武汉:武汉理工大学, 2007. GUO C C. Research on data mining technique using artificial neural networks[D]. Wuhan:Wuhan University of Technology, 2007. (in Chinese)
[8] TAVANA M, ABTAHI A R, DI CAPRIO D, et al. An artificial neural network and Bayesian network model for liquidity risk assessment in banking[J]. Neurocomputing, 2018, 275:2525-2554.
[9] 张长鲁. 基于数据挖掘的煤矿安全可视化管理研究[D]. 北京:中国矿业大学(北京), 2015. ZHANG C L. Visual management of safety in coal mines based on data mining[D]. Beijing:China University of Mining and Technology (Beijing), 2015. (in Chinese)
[10] 柴文光, 周宁. 网络信息安全防范与Web数据挖掘技术的整合研究[J]. 情报理论与实践, 2009, 32(3):97-101. CHAI W G, ZHOU N. Self-adaptive personalized web page recommendation based on semantics[J]. Information Studies:Theory & Application, 2009, 32(3):97-101. (in Chinese)
[11] 刘清毅. 计算机网络安全病毒防御中的数据挖掘技术应用[J]. 微型电脑应用, 2018, 34(4):73-75. LIU Q Y. Application of data mining technology in virus defense and computer network security[J]. Microcomputer Applications, 2018, 34(4):73-75. (in Chinese)
[12] 林国顺, 陈燕, 贾智辉, 等. 基于数据挖掘的道路运行安全因素关联分析[J]. 大连海事大学学报, 2011, 37(3):62-65. LIN G S, CHEN Y, JIA Z H, et al. Association analysis of the road running safety factors based on data mining technology[J]. Journal of Dalian Maritime University, 2011, 37(3):62-65. (in Chinese)
[13] 张晓辉. 云理论和数据挖掘在水上安全分析中的应用[D]. 大连:大连海事大学, 2011. ZHANG X H. Applications of cloud theory and data mining in marine safety analysis[D]. Dalian:Dalian Maritime University, 2011. (in Chinese)
[14] GUO J X, DING H. Application of data mining on water supply management[C]//Proceedings of International Joint Conference on Artificial Intelligence. Hainan Island, China:IEEE, 2009:606-608.
[15] 傅韬, 史赟. 数据挖掘技术在水利信息化中的应用[J]. 江西水利科技, 2009, 35(1):74-75. FU T, SHI Y. Application of the data mining technology in informationizing water conservancy[J]. Jiangxi Hydraulic Science & Technology, 2009, 35(1):74-75. (in Chinese)
[16] 陈谦亮, 王义民. 基于数据挖掘的水库智能决策支持系统研究[J]. 水资源与水工程学报, 2009, 20(3):75-78, 82. CHEN Q L, WANG Y M. Intelligent decision-making supporting system of reservoir based on data mining techniques[J]. Journal of Water Resources and Water Engineering, 2009, 20(3):75-78, 82. (in Chinese)
[17] 李智录, 李波. 基于PLSR的静态灰色模型在大坝安全监控中的应用[J]. 大坝与安全, 2006(6):48-51. LI Z L, LI B. Application of static gray model based on PLSR into dam safety monitoring[J]. Dam & Safety, 2006(6):48-51.
[18] LI X C, ZHONG D H, REN B Y, et al. Prediction of curtain grouting efficiency based on ANFIS[J]. Bulletin of Engineering Geology and the Environment, 2019, 78(1):281-309.
[19] ZHONG D H, DU R X, CUI B, et al. Real-time spreading thickness monitoring of high-core rockfill dam based on K-nearest neighbor algorithm[J]. Transactions of Tianjin University, 2018, 24(3):282-289.
[20] 常成. 基于PDMiner大数据挖掘平台的电力系统安全评估及故障诊断系统[J]. 电力与能源, 2016, 37(1):7-11. CHANG C. Power system security assessment and fault diagnosis system based on PDMiner large data mining platform[J]. Power & Energy, 2016, 37(1):7-11. (in Chinese)
[21] SZEGEDY C, LIU W, JIA Y Q, et al. Going deeper with convolutions[C]//Proceedings of the IEEE Conference on computer Vision and Pattern Recognition. Boston, USA:IEEE, 2015:1-9.
[22] SUN Y, WANG X G, TANG X O. Deeply learned face representations are sparse, selective, and robust[C]//Proceedings of IEEE Conference on Computer Vision and Pattern Recognition. Boston, USA:IEEE, 2015:2892-2900.
[23] 张晴晴, 刘勇, 潘接林, 等. 基于卷积神经网络的连续语音识别[J]. 工程科学学报, 2015, 37(9):1212-1217. ZHANG Q Q, LIU Y, PAN J L, et al. Continuous speech recognition by convolutional neural networks[J]. Chinese Journal of Engineering, 2015, 37(9):1212-1217. (in Chinese)
[24] 林鹏, 王英龙, 汪志林, 等. 基于微信的大型水电工程安全隐患排查治理系统研发与应用[J]. 中国安全生产科学技术, 2017, 13(7):137-143. LIN P, WANG Y L, WANG Z L, et al. Development and application of potential safety hazard investigation and control system for large hydropower engineering based on WeChat[J]. Journal of Safety Science and Technology, 2017, 13(7):137-143. (in Chinese)
[1] 梁杰, 陈嘉豪, 张雪芹, 周悦, 林家骏. 基于独热编码和卷积神经网络的异常检测[J]. 清华大学学报(自然科学版), 2019, 59(7): 523-529.
[2] 张思聪, 谢晓尧, 徐洋. 基于dCNN的入侵检测方法[J]. 清华大学学报(自然科学版), 2019, 59(1): 44-52.
[3] 刘琼, 李宗贤, 孙富春, 田永鸿, 曾炜. 基于深度信念卷积神经网络的图像识别与分类[J]. 清华大学学报(自然科学版), 2018, 58(9): 781-787.
[4] 芦效峰, 张胜飞, 伊胜伟. 基于CNN和RNN的自由文本击键模式持续身份认证[J]. 清华大学学报(自然科学版), 2018, 58(12): 1072-1078.
[5] 李晓飞, 许庆, 熊辉, 王建强, 李克强. 基于候选区域选择及深度网络模型的骑车人识别[J]. 清华大学学报(自然科学版), 2017, 57(5): 491-496.
Viewed
Full text


Abstract

Cited

  Shared   
  Discussed   
版权所有 © 《清华大学学报(自然科学版)》编辑部
本系统由北京玛格泰克科技发展有限公司设计开发 技术支持:support@magtech.com.cn