文档介绍：基于数据驱动的工业过程故障监测
摘要
现代工业生产过程中,及时有效地检测、诊断和修复过程故障是提供性能
优良、品质一致产品的先决条件,这也是进行工业过程监控的目的和动机。多
变量统计过程监控技术历经三十多年的发展,已经取得了一系列令人瞩目的成
果,并在现代过程工业中得到了广泛的应用。但是大部分研究基本上是在过程
检测数据服从多元正态分布和独立同分布的两个假设下进行的。然而,在实际
工业过程中,过程信息非常复杂,服从何种分布很难确定。本文的研究正是着
眼于克服这两大假设条件,通过独立成分分析的方法(ICA)使过程监测技术能
更好地适用于实际工业生产过程。
为此,本文采用独立元分析方法作为研究的主要数学工具。独立元分析的
基本原理是通过分析多维观测数据间的高阶统计相关性,找出相互独立的隐含
信息成分,完成分量间高阶冗余的去除及独立源信号的提取。它具有比主元分
析更好的刻画过程运行特征的性能。本文的主要内容如下:
,并指出了流程工业基于子空间特征
信息提取进行过程监控的优越性。此外,还简要地描述了主元分析方法和独立
元分析方法及它们在过程监控中的应用。
,根据过程信息能够用若干“尽可能
独立”的过程特征信号进行描述的原理,提出了一种基于独立元分析的过程监
控方法。并对它的计算原理进行了陈述。
matlab 中对 ICA 过程监测方法进行了仿真,证明了它在过程监测中的
作用。
最后,对以后多元过程监测技术的研究方向进行了一些有益的展望。
关键词: 过程监测,主元分析,独立元分析,TE 过程
- I -
哈尔滨理工大学学士学位论文
Fault Detection in Industrial Process
Based on Data Driven
Abstract
In modern industrial process, detecting, diagnosing and restoring fault timely and
efficiently is the precondition of providing produce with good performance and
consistent quality, which is also the motivation and object of process monitoring.
Multivariate statistic process control (MSPC) has developed more than thirty years.
Lots of research result have been acquired and applied in this field widely. However,
conventional MSPC is based on the assumption that the separated latent variables
must be subjected to normal probability distribution (or independent and identical
distribution),which sometimes can not be satisfied .The main of this dissertation is to
e these two assumption, and to improve the monitoring performance of
process and enlarge the range of the application by ponent analysis
(ICA).
So, ICA is the primary mathematical tool used in this dissertation. Its principle is
to find mutual independent ponents, to remove the higher-order
redundancy ponents and to extract the independent original signals by
analyzing the higher-order statistical relationship among multidimensional
observations. So ICA is more effective than PCA (ponent Analy