电子测量与仪器学报

石怀涛,周乾,王雨桐,李颂华.基于相对变换的ICA故障检测方法[J].电子测量与仪器学报,2017,31(7):1040-1046

基于相对变换的ICA故障检测方法

Fault detection method based on relative transformation ICA

DOI：10.13382/j.jemi.2017.07.008

英文关键词:electric spindle fault detection relative transformation Euclidean distance ICA

基金项目:沈阳市科技计划（17 231 1 28）、辽宁省自然科学基金(2016010623)和中国博士后科学基金（2016M601335）资助项目

作者	单位
石怀涛	沈阳建筑大学国家地方联合工程实验室沈阳110168
周乾	沈阳建筑大学国家地方联合工程实验室沈阳110168
王雨桐	沈阳建筑大学国家地方联合工程实验室沈阳110168
李颂华	沈阳建筑大学国家地方联合工程实验室沈阳110168

Author	Institution
Shi Huaitao	NationalLocal Joint Engineering Laboratory, Shenyang Jianzhu University, Shenyang 110168, China
Zhou Qian	NationalLocal Joint Engineering Laboratory, Shenyang Jianzhu University, Shenyang 110168, China
Wang Yutong	NationalLocal Joint Engineering Laboratory, Shenyang Jianzhu University, Shenyang 110168, China
Li Songhua	NationalLocal Joint Engineering Laboratory, Shenyang Jianzhu University, Shenyang 110168, China

摘要点击次数: 2819

全文下载次数: 12355

中文摘要:

针对传统独立主元分析方法(independent component analysis,ICA)在标准化处理后导致特征值大小近似相等，难以提取有代表性变量等问题，提出了一种基于相对变换的独立主元分析（relative transformation ICA,RTICA）故障检测方法。该方法引入欧氏距离相对变换理论，将原始空间数据变换得到相对空间，然后在相对空间进行独立主元分析，降低相对空间的数据维数，使提取的独立主元特征具有更大的适应性，建立故障检测模型，最终实现在线故障检测。该方法通过田纳西伊斯曼过程仿真加以验证，并应用到电主轴裂纹故障的状态监测中，实验结果表明该方法能有效减少独立主元个数，简化故障检测模型的复杂度，增强状态检测性能。

英文摘要:

Aiming at the problems that the eigenvalues of independent component analysis(ICA) are approximately equal and the representative variables cannot be extracted effectively after dimensionless standardization processing, a fault detection method based on relative transformation ICA (RTICA) is proposed. The method introduces the relative transformation based on Euclidean distance. Firstly, the RTICA approach transfers the original data space into relative space by computing the Euclidean distance. Secondly, ICA approach is used to reduce the dimensions of the data in the relative space, extract the independent PCs possess greater adaptability, build the fault detection model and implement on line fault detection. The proposed method has been applied to Tennessee Eastman (TE) and the fault simulation experiment in electric spindle system. The results show that the method can effectively reduce the number of independent principal components, simplify the complexity of fault detection model, and enhance the performance of state detection.

查看全文查看/发表评论下载PDF阅读器