基于K-S匹配与证据理论的复合故障诊断的研究

发布时间：2018-04-14 23:03

本文选题：复合故障 + K-S匹配　；参考：《太原理工大学》2017年硕士论文

【摘要】：随着现代工业系统和制造装备逐渐向着大型化、复杂化和精密化的方向发展,大型旋转机械设备在现代工业中占有举足轻重的地位,它们良好的运行状况直接关系到整个工厂安全正常的生产运作。人们迫切希望能及时了解系统的运行状态,提高系统的可靠性和有效性。目前有许多的学者致力于对旋转机械复合故障诊断进行研究,复合故障已经成为当前研究的热点。由于多重故障并发时,其表现形式是多种多样的,不同故障特征相互混杂呈现出多耦合、模糊性等特征,给故障诊断带来了极大的挑战。随着信息技术和人工智能的逐渐发展,新的技术不断地移植、应用到机械故障诊断中,丰富了故障诊断的理论与技术,推动着故障诊断向跟高层次发展。国内外相关研究工作大多集中在故障预测、故障模型设计、故障目标跟踪等方面。本文在研读大量文献的基础上,结合课题的相关研究背景,采用的是一种基于K-S和证据理论相结合的集成诊断方法,进行的工作主要如下:(1)在实际工况下运行的旋转机械,其发生的故障通常都是复合故障,现有的诊断方法对这一问题很难处理。本文通过K-S匹配计算故障的相似度,然后通过证据理论处理其冲突,结果表明,该方法能快速地判断机组上常见的轴系复合故障。(2)鉴于Kolmogorov Smilnov在双样本数据匹配具有的优点,本文用K-S对无量纲数据样本的累积分布函数曲线检验,通过线线匹配,能较好地识别出故障。(3)针对旋转机械复合故障的复杂性以及不确定性,本文充分利用证据理论处理不确定信息方面的优势,对K-S匹配后的结果进行证据理论数据融合,最后在大机组上多次实验,验证了K-S匹配与证据理论数据融合方法能快速、准确地判断大机组上的复合故障。
[Abstract]:With the development of modern industrial system and manufacturing equipment towards the direction of large scale, complexity and precision, large-scale rotating machinery and equipment play an important role in modern industry.Their good operation condition is directly related to the safe and normal production operation of the whole plant.People are eager to know the running state of the system in time and improve the reliability and effectiveness of the system.At present, many scholars devote themselves to the research of complex fault diagnosis of rotating machinery, and compound fault has become a hot research topic.When multiple faults are concurrent, their forms are various, and different fault features present multiple coupling and fuzziness, which brings a great challenge to fault diagnosis.With the gradual development of information technology and artificial intelligence, new technologies are constantly transplanted and applied to mechanical fault diagnosis, which enriches the theory and technology of fault diagnosis and promotes the development of fault diagnosis to a higher level.Most of the related researches at home and abroad focus on fault prediction, fault model design, fault target tracking and so on.On the basis of reading a large number of documents and combining the related research background of the subject, this paper adopts an integrated diagnosis method based on K-S and evidence theory. The main work of this paper is as follows: 1) rotating machinery running under actual working conditions.The fault occurring is usually a complex fault, which is difficult to deal with by the existing diagnosis methods.In this paper, the similarity of faults is calculated by K-S matching, and then the conflict is dealt with by evidence theory. The results show that this method can quickly judge the common complex fault of shafting on the unit. (2) in view of the advantages of Kolmogorov / Smilnov in double sample data matching,In this paper, we use K-S to test the cumulative distribution function curve of dimensionless data samples. By line and line matching, we can better identify the fault.This paper makes full use of the advantage of evidence theory in dealing with uncertain information, carries on the evidence theory data fusion to the K-S matching result after the result, finally many experiments on the big unit, has verified the K-S matching and the evidence theory data fusion method to be quick,Accurate judgment of complex faults on large units.
【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】：TH17

【参考文献】