arXivDaily arXiv每日学术速递 周一至周五更新
arXiv 1302.6846cs.AI
收藏

基于层次模型诊断的概率方法

A Probabilistic Approach to Hierarchical Model-based Diagnosis

Stanford University(斯坦福大学);Rockwell International Science Center(罗克韦尔国际科学中心)

Sampath Srinivas

摘要:

基于模型的诊断从系统的功能示意图向后推理,以在观察到异常行为的情况下隔离故障。我们开发了一个完全概率的方法,基于模型的诊断,并将其扩展到支持层次模型。我们的计划将功能原理图转换为贝叶斯网络和诊断推理发生在贝叶斯网络。一个贝叶斯网络诊断推理算法的修改,利用层次结构,以提供计算增益。

英文摘要:

Model-based diagnosis reasons backwards from a functional schematic of a system to isolate faults given observations of anomalous behavior. We develop a fully probabilistic approach to model based diagnosis and extend it to support hierarchical models. Our scheme translates the functional schematic into a Bayesian network and diagnostic inference takes place in the Bayesian network. A Bayesian network diagnostic inference algorithm is modified to take advantage of the hierarchy to give computational gains.

机构、总结、中文摘要均由AI分析而来,可能存在错误,请以论文正文为准。

↑