文档介绍：重庆大学硕士学位论文摘要
摘要
随着机械设备的自动化、智能化、大型化、集成化、复杂化程度不断提高。
在设备运行状态检测的基础上展开设备故障诊断就显得尤为必要,利用诊断结论
采取相应的对策,可以提高设备运行的可靠性,保证设备的完好性。针对以信息
处理技术为手段的现代设备诊断技术,对多故障同时发生和各种故障之间可能存
在的相互联系及影响难以分析的不足,本文对贝叶斯网络在机械故障诊断中的应
用进行了研究。
贝叶斯网络是目前不确定性知识表达和推理领域最有效的理论模型之一,适
用于不确定性和概率推理的知识表达和推理。它是一种基于网络结构的有向图解
描述,能进行双向并行推理,并能综合先验信息和样本信息,使得推理结果更为
准确可信。因此,贝叶斯网络在故障诊断领域中的应用具有重要意义。
本文以旋转机械常见振动故障为对象,首先对旋转机械常见振动故障特征进
行了论述。然后阐述了贝叶斯网络基本理论,对贝叶斯网络基于联合树的精确推
理方法进行了论述,探讨了贝叶斯网络的学习算法。在之前理论研究的基础上,
针对机械故障特有的表现形式建立了基于贝叶斯网络的机械故障诊断模型。该模
型是一个两层结构的贝叶斯网络模型,该模型具有以下特点:
(1)贝叶斯网络模型能够自然的融入机械故障诊断中的不确定性知识,对各
种因素不确定度的结合有着见识的概率论基础,使诊断结论更加全面和准确;
(2)图形化的知识表达方式更加清晰,具有良好的可解性;
(3)推理机制与知识表达完全分开,知识库更便于扩充和完善;
(4)可以进行多种形式的诊断推理,能有效的进行复合故障诊断;
(5)可以提供量化的故障诊断结论,给出诊断建议;
利用该模型本文采用 Decision Systems Laboratory, University of Pittsburgh 所开发
的贝叶斯网络推理平台 GeNIe 对一些设备的实测数据进行了故障诊断分析,验证
了该模型的有效性。最后对推理诊断系统做出了总体设计。
关键词:贝叶斯网络,故障诊断,概率推理,不确定性推理
I
重庆大学硕士学位论文 Abstract
ABSTRACT
With the improvement of mechanical on automatic, intelligence, large scale,
integration plication, it is the very turn to start out diagnose of mechanical
failure, which is based on the check-up of function condition of machine. To carry out
some relative of function as well as we can ensure the reliability of modern machine
diagnose by means of information process, the bination of many failures
that happen at the same time, as well as the ings of unanalysable, the author
will focus more on the work.
The work is one of the most efficient theoretically model on
uncertain things expression and inference field. If can be used to the expression as well
as inference of uncertainty and probability. As a exist-way diagram description based
construction, it can start two-way inference as well as synthesize pre-tested and
sample information. The result seems conceivable of we follow that. Since that,
work has a deep impact on mechanical failure field.
With the target of mon vibration failure in rotary machine, the author
gives a depiction of some