引用本文: | 陈彧赟,侯博文,何章鸣,等.数据驱动的复杂系统非预期故障诊断通用过程模型.[J].国防科技大学学报,2017,39(6):126-133.[点击复制] |
CHEN Yuyun,HOU Bowen,HE Zhangming,et al.General process model for unanticipated fault diagnosis of complex system based on data driven[J].Journal of National University of Defense Technology,2017,39(6):126-133[点击复制] |
|
|
|
本文已被:浏览 7985次 下载 7022次 |
数据驱动的复杂系统非预期故障诊断通用过程模型 |
陈彧赟1, 侯博文1, 何章鸣1,2, 王炯琦1,2 |
(1. 国防科技大学 文理学院, 湖南 长沙 410073;2. 北京控制工程研究所, 北京 100080)
|
摘要: |
提高对复杂系统非预期故障诊断能力是故障诊断领域的难点。结合非预期故障诊断内涵及基本原理,构建了一种用于复杂系统非预期故障诊断的通用过程模型。该模型采用四层递进结构,包括四个主要模型,即预期(已知)故障检测模型、预期(已知)故障识别模型、非预期(未知)故障检测模型和非预期(未知)故障识别模型。分析了各模型所包含的关键问题及其相应的实现算法,包括检测统计量的构建及评估、故障特征方向提取、故障识别器设计及故障贡献率计算。该通用过程模型规范了复杂系统非预期故障的诊断流程,明确了数据驱动的实现原理。以卫星姿态控制系统为例,验证了非预期故障诊断通用过程模型的有效性。 |
关键词: 非预期故障诊断 通用过程模型 数据驱动 检测统计量 偏离度 贡献率 |
DOI:10.11887/j.cn.201706019 |
投稿日期:2016-07-13 |
基金项目:国家自然科学基金资助项目(61773021, 61703408);湖南省研究生科研创新资助项目(CX2014B010) |
|
General process model for unanticipated fault diagnosis of complex system based on data driven |
CHEN Yuyun1, HOU Bowen1, HE Zhangming1,2, WANG Jiongqi1,2 |
(1. College of Liberal Arts and Sciences, National University of Defense Technology, Changsha 410073, China;2.
2. Beijing Institute of Control Engineering, Beijing 100080, China)
|
Abstract: |
The unanticipated fault diagnosis for complex system is a difficult problem. A general process model was proposed. The model adopted a four-layer structure and included four models, i.e. an anticipated fault detection model, an anticipated fault identification model, an unanticipated fault detection model and an unanticipated fault identification model. Several key problems and the corresponding algorithms in each layer were analyzed, including the establishment of the fault detection statistic, the extraction of the fault character, the design of the fault isolation criterion and the construction of the fault contribution rate. The general process model regularized the diagnosis process of unanticipated fault for complex system and defined the data driven fault diagnosis framework. The effectiveness of the proposed general process model was validated by a satellite control system. |
Keywords: unanticipated fault diagnosis general process model data-driven detection statistic deviation degree contribution rate |
|
|