BAYESIAN METHODS FOR CONTROL LOOP MONITORING AND DIAGNOSIS
BAYESIAN METHODS FOR CONTROL LOOP MONITORING AND DIAGNOSIS
复制标题
DOI：
10.3182/20070606-3-mx-2915.00004
复制
发表时间：
2008-10
期刊：
影响因子：
--
通讯作者：
Biao Huang
中科院分区：
文献类型：
--
作者：
Biao Huang
摘要控制性能监测算法有很多种。还有许多算法可用于过程监控。然而，有几种方法可用于综合各种监测技术，形成一个诊断系统，最佳决策。本文研究建立和论证了一种新的控制回路监控概率诊断框架。新的框架具有许多所需的属性，包括，例如，概率诊断程序，在合成不同的监测技术，在存在缺失的数据或缺失的变量，易于扩展或收缩的诊断系统，能力，将先验过程知识的鲁棒性的灵活性，和决策能力。作为所提出的框架的骨干，新兴的贝叶斯方法进行了介绍，并被证明是适当的工具。几个代表性的控制回路诊断问题的贝叶斯框架下制定和他们的解决方案，通过例子来证明。总结了贝叶斯方法在工业应用中的经验和挑战，并讨论了未来的研究方向。
Abstract There exist many algorithms for control performance monitoring. There are also many algorithms available for process monitoring. There are, however, few methods available for synthesis of various monitoring technologies to form a diagnosing system for optimal decision making. This paper is concerned with establishing and demonstrating a novel probabilistic diagnostic framework for control loop monitoring. The new framework possesses a number of desired properties including, for example, probabilistic diagnosing procedure, flexibility in synthesizing different monitoring technologies, robustness in the presence of missing data or missing variables, ease of expansion or shrinking of the diagnosing system, ability to incorporate a priori process knowledge, and capability for decision making. As the backbone of the proposed framework, the emerging Bayesian methods are introduced and shown to be the appropriate tools. Several representative control loop diagnostic problems are formulated under the Bayesian framework and their solutions are demonstrated through examples. The experiences and challenges learned from industrial applications of Bayesian methods are summarized and some of future research directions are discussed.