| 基于统一理论框架的故障诊断模型及学习进化方法 |
| |
| 引用本文： | 张士刚,罗旭,骆彦廷,杨拥民. 基于统一理论框架的故障诊断模型及学习进化方法[J]. 国防科技大学学报, 2020, 42(2): 142-149 |
| |
| 作者姓名： | 张士刚 罗旭 骆彦廷 杨拥民 |
| |
| 作者单位： | 国防科技大学,国防科技大学,国防科技大学,国防科技大学 |
| |
| 基金项目： | 国家自然科学基金青年基金项目（NO.61903370, NO.61503398） |
| |
| 摘 要： | 本文以概率图理论为基础，系统研究了基于这一理论框架的故障诊断模型，对模型的构建方法以及在不同场景下的模型演化方案进行了探讨，使得在统一理论框架下可实现多模式系统故障诊断、耦合故障诊断、动态故障诊断、故障预测等复杂情形的诊断。为了弥补单独利用基于模型的方法和基于数据的方法的缺陷，研究了诊断模型的学习进化策略，实现了诊断效果的改进和优化。另外，对模型后续的能力扩展和可能的研究方向进行了展望，为后续理论研究提供了参考。
|
| 关 键 词： | 贝叶斯网，概率图模型，故障诊断，机器学习，多信号模型， PHM |
| 收稿时间： | 2018-10-17 |
| 修稿时间： | 2019-11-11 |
Fault diagnosis models and evolution method based on a unified theory framework |
| |
| ZHANG Shigang,LUO Xu,LUO Yanting,YANG Yongmin. Fault diagnosis models and evolution method based on a unified theory framework[J]. Journal of National University of Defense Technology, 2020, 42(2): 142-149 |
| |
| Authors: | ZHANG Shigang LUO Xu LUO Yanting YANG Yongmin |
| |
| Affiliation: | Science and Technology on Integrated Logistics Support Laboratory, College of Intelligence Science and Technology, National University of Defense Technology, Changsha 410073, China |
| |
| Abstract: | In this paper, a unified diagnosis model based on probabilistic graphical theory is studied. The model constructing method and its variations in different scenarios are discussed. Complex problems such as fault diagnosis in multimode systems, diagnosis with coupling faults, dynamic faults and fault prognosis can be solved using the framework. In order to combine the advantages of the model-based method and the data-driven method, a model learning algorithm is proposed, by means of which the diagnostic result can be improved. At last, the possible model developing directions and research focus are discussed. |
| |
| Keywords: | Bayesian Networks probabilistic graphical model fault diagnosis machine learning multi-signal model PHM |
|
| 点击此处可从《国防科技大学学报》浏览原始摘要信息 |
|
点击此处可从《国防科技大学学报》下载免费的PDF全文 |
