混沌分形特征与支持向量数据域描述辨识机械动态系统异常

为了在微弱故障征兆出现时能通过正常状态对异常进行辨识,针对通常动态系统故障状态样本缺乏的单值分类问题,提出混沌分形特征组合及支持向量数据域描述（support vector data description,SVDD）的动态系统振动异常辨识方法。该方法采用误诊和漏诊两种分类错误的SVDD接受者操作特征（receiver operating characteristic,ROC）曲线,通过分析振动混沌分形特征,选取最大Lyapunov指数和关联维数的最优组合,进而建立正常状态样本单值SVDD分类器,并对可提高分类精度的试验验证法优选核函数参数进行了探讨。试验及测试表明,SVDD-ROC方法避免了...

Full description

Saved in:
Bibliographic Details
Published in农业工程学报 Vol. 31; no. 10; pp. 211 - 218
Main Author 李兆飞 柴毅 任小洪
Format Journal Article
LanguageChinese
Published 四川理工学院自动化与电子信息学院,自贡,643000%重庆大学自动化学院,重庆,400044 2015
Subjects
分形
动态系统
异常辨识
接受者操作特征
支持向量数据域描述
混沌理论
chaos theory
dynamical systems
support vector data description
分形
动态系统
接受者操作特征
异常辨识
fractal
混沌理论
支持向量数据域描述
receiver operating characteristic
abnormal indentification
Online AccessGet full text
ISSN1002-6819
DOI10.11975/j.issn.1002-6819.2015.10.028

Cover

More Information
Summary:为了在微弱故障征兆出现时能通过正常状态对异常进行辨识,针对通常动态系统故障状态样本缺乏的单值分类问题,提出混沌分形特征组合及支持向量数据域描述（support vector data description,SVDD）的动态系统振动异常辨识方法。该方法采用误诊和漏诊两种分类错误的SVDD接受者操作特征（receiver operating characteristic,ROC）曲线,通过分析振动混沌分形特征,选取最大Lyapunov指数和关联维数的最优组合,进而建立正常状态样本单值SVDD分类器,并对可提高分类精度的试验验证法优选核函数参数进行了探讨。试验及测试表明,SVDD-ROC方法避免了传统特征选取对具体故障类型样本的依赖性,选取的特征组合对正常和故障样本有较好的自聚类性,SVDD方法仅需要正常状态样本就能辨识异常状态,并且对未知故障也有较好的异常辨识能力。该研究可为动态系统异常状态提供建模与检测的理论基础和设计依据,有效预防突发事故,节约维修成本,提高动态系统的利用率,保障其安全运行,有效降低成本。
Bibliography:11-2047/S
chaos theory;fractal;dynamical systems;receiver operating characteristic;support vector data description;abnormal indentification
Li Zhaofei, Chai Yi, Ren Xiaohong （1.College of Automation and Electronic Information, Siehuan University of Science ＆ Engineering, Zigong 643000, China; 2. College of Automation, Chongqing University, Chongqing 400044, China）
In order to extract the features of fault signals of dynamic system polluted and modulated by background noise, and solve anomaly detection problem of slight fault based on the generated normal patterns, this paper considers the one-class classification problem of insufficient fault samples and class imbalanced in intelligent monitoring and diagnosis for dynamic systems. Besides, it is well known that the conventional feature selection methods always depend on specific fault types. If some features are chosen to identify one fault, their performance may be poor for other fault cases. Compared with other classifiers, support vector data description （SVD
ISSN:1002-6819
DOI:10.11975/j.issn.1002-6819.2015.10.028