混凝土泵车移动互联应用和关键数据算法

详细信息    查看全文 | 推荐本文 |

英文篇名：Mobile internet application and key data algorithm research of truck-mounted concrete pump 作者：张剑敏 ; 赵鑫 ; 付新宇 ; 万梁 英文作者：ZHANG Jianmin;ZHAO Xin;FU Xinyu;WAN Liang;R&D Center,Zomlion Heavy Industry Science and Technology Co.,Ltd.;R&D Center,Chinese National Engineering Research Center of Concrete Machinery; 关键词：工程机械 ; 混凝土泵车(TMCP) ; 神经网络PID算法 ; 移动互联 ; 手机应用 英文关键词：construction machinery;;truck-mounted concrete pump(TMCP);;neural network PID algorithm;;mobile internet;;mobile phone application 中文刊名：GCHE 英文刊名：Chinese Journal of Construction Machinery 机构：中联重科股份有限公司研发中心;国家混凝土机械工程技术研究中心研发中心; 出版日期：2019-06-15 出版单位：中国工程机械学报 年：2019 期：v.17 基金：国家重点研发计划资助项目(2018YFC0705800) 语种：中文; 页：GCHE201903004 页数：5 CN：03 ISSN：31-1926/TH 分类号：17-21

摘要

随着工程机械移动互联应用的逐步发展,手机APP以其方便携带和使用,正在成为工程机械客户管理车辆的有效手段.泵送方量是客户泵车施工过程中最为关注的数据,本文通过采用神经网络PID算法来控制泵送行程,并根据算法得出准确的泵送方量.将泵车施工关键数据通过GPS传输到数据平台,再推送给开发的手机APP,使客户通过移动互联设备实时了解施工工况.测试结果表明:运用基于神经网络PID控制算法,泵送全工况行程精度达96%以上,验证了神经网络PID算法的准确性;方量统计计算准确率>95%,移动APP提升了客户对于车辆管理的效率,提高了泵车的移动互联应用水平.
        The development of construction machinery's mobile internet makes the mobile phone application more useful,which increasingly becomes the most efficient way to manage the machine for the clients.The pumping cube is the most concern data during the work process,this paper introduces a neural network PID algorithm to control the pumping displacement.The key data of truck-mounted concrete pump(TMCP) work transmitted to the data center,and after data treatment,the APP which have developed can receive the work data easily,which make our customer real-time know the machines' work conditions.The experimental results demonstrate that the accuracy of control displacement is over 96%,the neural network PID algorithm is right.The pumping cube's accuracy is over 95%.The mobile application(APP) can promote the management efficiency of TMCP,also increase the level of mobile application.

引文

[1] 孟小峰,慈祥.大数据管理:概念、技术与挑战[J].计算机研究与发展,2013,50(1):146-169.MENG X F,CI X.Big data management:concepts,techniques and challenges[J].Journal of Computer Research and Development,2013,50(1):146-169.
    [2] 黄毅,吴斌兴,王佳茜.混凝土泵车臂架振动响应的主动控制实验研究[J].振动与冲击,2012,31(2):91-94.HUANG Y,WU B X,WANG J Q.Experimental research on active control of boom vibration of concrete pump truck[J].Journal of Vibration and Shock,2012,31(2):91-94.
    [3] 丛爽.典型人工神经网络的结构、功能及其在智能系统中的应用[J].信息与控制,2001,30(2):97-103.CONG S.A survey of structures,functions of artificial neural networks and their applications in intelligent systems[J].Information and Control,2001,30(2):97-103.
    [4] SONG Q,XIAO J Z,CHAI S.Robust back propagation training algorithm form ultilayered neural tracking controller[J].IEEE Transactions on Neural Networks,1999,10(5):1133-1141,1112.
    [5] ZHENG Y.Trajectory data mining:an overview[J].ACM Transactions on Intelligent Systems and Technology,2015,6(3):29.
    [6] 孙吉书,窦远明,周戬,等.应变速率对混凝土抗压特性影响的试验研究[J].混凝土与水泥制品,2011,5(5):1-3.SUN J S,DOU Y M,ZHOU J,et al.The experimental study of compressive property of concrete from strain rate[J].China Concrete and Cement Products,2011,5(5):1-3.
    [7] 张泽旭.神经网络控制与Matlab仿真[M].哈尔滨:哈尔滨工业大学出版社,2011:47.ZHANG Z X.Neural network control and Matlab simulation[M].Harbin:Harbin Institute of Technology Press,2011:47.