提升设备远程监测与故障诊断试验系统开发

发布时间：2018-02-27 22:09

本文关键词： 提升机远程监测故障诊断组态王支持向量机试验系统　出处：《太原理工大学》2017年硕士论文　论文类型：学位论文

【摘要】：提升设备是能源开采业中重要的机械设备,作为井上与井下的连接枢纽,其安全稳定运行的重要性不言而喻,所以对于研究保证提升设备的安全稳定工作具有重要的意义。本文将矿井提升机作为提升设备研究的工程背景,重点探讨了提升机远程监测与故障诊断的研究方向,并结合目前有关提升机试验系统研究情况,提出了提升机远程监测与故障诊断“现场试验子系统+互联网试验子系统”的试验系统搭建模式。本文针对现场试验子系统,提出了基于组态王的现场监测与诊断模式,包括监测内容设计,硬件的选型设计,硬件的连接设计,采集方案的设计,通讯方式设计以及现场监测系统方案设计,同时还有现场数据库的建立。针对以往提升机的监测系统模拟量采集匮乏导致其他应用研究缺乏数据,同时用户维护开发难度大,提出了系统模块化设计并且将更多的模拟量纳入采集范围。本文针对互联网试验子系统,提出了基于互联网的远程监测与诊断模式,包括Web服务器以及本地服务器的硬件选型设计,远程数据传输方式设计以及远程数据库的建立,基于ASP.NET的互联网监测系统设计。针对以往数据不能实时显示在网页监测与诊断页面上,提出了同步数据库系统设计,并将数据实时传输到互联网监测界面上进行显示。本文针对以往提升机远程监测与诊断系统中故障诊断不足,且故障样本数据少的情况,提出了支持向量机的故障诊断方法,为了解决支持向量机参数选择困难和其对于故障诊断的影响,提出利用粒子群优化算法(PSO),遗传算法(GA)对支持向量机的参数进行优化,提高提升机故障诊断分类的准确率。试验证明:“现场试验子系统+互联网试验子系统”这种提升设备远程监测与故障诊断试验系统模式不仅能够在多层次上对提升设备进行监测,诊断以及维护,能够实现现场数据库与远程数据库数据同步,并且故障诊断用户图形界面简洁,操作简单。参数优化后的支持向量机故障诊断方法具有快速,高诊断率,所需样本少的优点,使得该远程监测与诊断系统故障分类更高,实现动态诊断,并且可以进行运动学,结构静力学,电控系统,加载系统等其它科学应用研究试验。
[Abstract]:Lifting equipment is an important equipment of energy exploitation, as well as the connection hub, it is self-evident importance of the safe and stable operation, so the research has important significance to enhance the security and stability of equipment. This paper will study the engineering background as lifting equipment of mine hoist, discusses the research direction of hoist remote monitoring and fault diagnosis, combined with the current research situation about hoist test system, put forward the test system of the elevator remote monitoring and fault diagnosis "field test subsystem + Internet test system" construction mode. According to the field test subsystem, proposed on-site monitoring and diagnosis model based on Kingview, including monitoring content design, selection of hardware design, hardware connection design, collection design, communication design and field monitoring system The system design, as well as the scene database. In the past, enhance the monitoring system of analog acquisition led to the lack of other applications of lack of data, and user maintenance is difficult to develop and put forward the modular design of the system and the analog more into the collection range. According to the Internet test subsystem, the remote monitoring and the diagnosis model based on Internet, including Web servers and hardware selection and design of the local server, the design of remote data transmission and the establishment of the remote database, the design of network monitoring system based on ASP.NET. According to the data of the past can not be displayed in real-time monitoring and diagnosis of web page, put forward the design of synchronous database system, and real-time data transmission to the Internet monitoring interface for display. In this paper the elevator remote monitoring and diagnosis system fault The diagnosis is insufficient, and the failure of few sample data, the paper puts forward a fault diagnosis method of support vector machine, support vector machine in order to solve the difficulty in parameter selection and its effect on the fault diagnosis, proposed using particle swarm optimization algorithm (PSO), genetic algorithm (GA) to optimize the parameters of SVM, improve the accuracy of hoist fault diagnosis classification. Experimental results show that: "field test subsystem + Internet test system" the mode of remote monitoring and fault diagnosis of equipment test system can not only at multiple levels of lifting equipment for monitoring, diagnosis and maintenance, to achieve on-site and remote databases and data synchronization, fault diagnosis of graphical user the interface is simple and easy to operate. The optimized parameters of support vector machine fault diagnosis method is rapid, high diagnostic rate, and required fewer samples, so that the remote monitoring The test and diagnosis system has higher fault classification and dynamic diagnosis, and can carry out other scientific application research experiments such as kinematics, structural statics, electronic control system, loading system and so on.

【学位授予单位】：太原理工大学
【学位级别】：硕士
【学位授予年份】：2017
【分类号】：TP274;TD534

【参考文献】