制造物联网生产过程工序流波动分析方法研究  

A Research of Fluctuation Analysis Method on Process Flow of Production Process Based on Internet of Manufacturing Things

作　　者：黄田安 程良伦[1] 黄思猛 Huang Tian-an;Cheng Liang-lun;Huang Si-meng(School of Computers,Guangdong University of Technology,Guangzhou 510006,China)

机构地区：[1]广东工业大学计算机学院,广东广州510006

出　　处：《广东工业大学学报》2019年第1期57-62,共6页Journal of Guangdong University of Technology

基　　金：国家自然科学基金青年科学基金资助项目(61502110);粤港共性技术招标资助项目(2013B010134011);广东省科技计划项目(2016B090918045;2017B090901019)

摘　　要：制造物联网通过部署大规模传感器节点获取工业生产过程实时状态数据流,利用复杂事件处理方法对生产过程监测产生的大规模数据流进行实时智能分析处理非常有必要,而其中工序流稳定性判断是生产部门关心的重要问题.然而,制造物联网传感器数据流大量存在的固有误差,给工序流稳定性判断带来较大困难.针对该问题,本文定义了概率事件模型并采用一种基于带缓冲的不确定性有穷自动机(NFA with run buffer, r NFA)的概率事件检测方法,提出结合游程检验和灰色系统模型以及bootstrap经验预测的方法对工序流的稳定性做出定量校验.实验结果表明,所提出的方法能够有效检测概率工序流中的生产全局状态,从而在不确定工序流找出较稳定而均衡的工序,给生产线提供改进方向.Internet of Manufacturing Things obtains real-time state data streams through the deployment of massive sensor nodes in industrial processes.Using the complex event processing method to analyse and process the large-scale and real-time data streams generated in the monitoring of production process monitoring is necessary,and to judge the stability of the process flow is one of the important problems concerned with production department.However,the raw data from the physical world has high level of uncertainty because of the inherent inaccuracy of sensor readings,bringing greater difficulties to judge the stability of the process flow.The probability of the event model is defined and the probability event detection method used based on finite automata with buffer uncertainty(NFA with run buffer,rNFA),and a method combined with the runs test and the grey system model and the bootstrap experience prediction is put forward to make quantitative checking of the stability of the process flow.Experimental results show that the proposed method can effectively detect probability event flow state of the global production.

关 键 词：工序流 复杂事件检测 游程检验 灰色系统模型 bootstrap预测 

分 类 号：TP301.1[自动化与计算机技术—计算机系统结构]