【作者】 张树；

【导师】 刘丽冰；

【作者基本信息】 河北工业大学 ， 精密仪器及机械， 2007， 硕士

【摘要】 随着现代工业生产自动化、连续化水平的不断提高,加工中心的占有率也在增大,在生产中已经占有重要地位。加工中心在许多企业中被用于重要的加工环节,如果出现故障后不能及时正确地进行故障诊断和维修,则会带来较大的经济损失。随着粗集理论近年来在智能信息处理研究领域获得了迅速发展,它基于现实的大数据集,从中推理、发现知识和分类系统的某些特点,对于研究不精确知识的表达、学习、归纳方面有其独特之处。本文研究了基于数据挖掘的加工中心故障诊断方法,跟以往的故障诊断方法不同,研究的方向并不是基于机械振动分析,而是采用了粗集理论结合神经网络的方法。论文研究了粗集对故障数据进行约简的可行性,并应用自组织映射神经网络的聚类功能,来实现连续属性值离散化的方法;通过对诊断信息的分析,采取常规约简方法,该方法实现了样本条件属性的约简,可消除样本数据中的冗余信息。采用MATLAB神经网络工具箱建立了加工中心故障类型的智能混合诊断系统;研究了智能混合故障诊断系统,并进行了功能模块设计,各功能模块分别为:数据采集模块,数据预处理模块,数据约简模块,神经网络模块,故障诊断模块。在此基础上构建了一个基于粗集-神经网络的智能混合故障诊断系统。更多还原

【Abstract】 With the development of automation and the high demand of reliableness, Machining Center has got important status and predomination in manufacturing. Machining Center has grown as key and deciding factor in many plants. Without timely fault diagnosis and service, serious economic loss can be caused. Rough Sets theory has made fast progress in recent years, it has outstanding ability in research of expressing, learning , concluding non-precise knowledge. It is based on practical large data sets, and deduces, find the knowledge and key of the classification systems.So this paper studies a method of Machining Center fault diagnosis based on Rough Sets theory, which is one of the latest tools in Data Mining area. Not like the usual methods that based on mechanical vibrancy, this method combines the Rough Sets theory with the Artificial Neural Network.The practicality of using rough set to reduce the date was discussed, in this paper, and the interval-valued continuous attribute discretization by applying self-organizing map neural network clustering was proposed, too. This article proposes a normal concision’s method, which reduces the example’s condition attribute and eliminates the redundant information of the date. What’s more, it provides the methods used to diagnosis Machining Center’s faults based on the intelligence hybrid system by adopting the MATLAB neural network workbox. At last, the functional modules which make up into intelligence hybrid system for fault diagnosis was introduced, including: data acquisition module, date preprocessor module, date reduction module, neural network module and fault diagnosis module. Herein, intelligence hybrid system based on rough sets and neural network for fault diagnosis is established in this paper.更多还原