| 一种基于马氏距离建立简化多元统计模型的方法 |
| |
| 引用本文： | 高翔,王纲,马纪虎. 一种基于马氏距离建立简化多元统计模型的方法[J]. 信息与控制, 2001, 0(Z1) |
| |
| 作者姓名： | 高翔 王纲 马纪虎 |
| |
| 作者单位： | [1]中国科学院沈阳自动化研究所 [2]沈阳化工学院 [3]中国科学院沈阳自动化研究所 沈阳 |
| |
| 摘 要： | 提出一种基于样本之间最小马氏距离的样本平均方法 ,从总体正常历史采样数据样本集合中 ,构造新的数据样本集 ,建立简化多元统计模型 .然后通过判断两数据集的质心偏移和协方差的差异程度来检验新的数据样本集对总体样本集的可代表性 ,从而达到用较少的有效样本代表总体样本统计特征的目的 .仿真结果表明用本文提出的简化多元统计模型进行故障诊断的效果与传统模型相同 ,而降低了对系统存储量和计算量的要求
|
| 关 键 词： | 马氏距离 主元分析 多元统计模型 多元校验 可代表性 故障诊断 |
AN APPROACH OF BUILDING SIMPLIFIED MULTIVARIATE STATISTICAL MODEL BASED ON MAHALANOBIS DISTANCE |
| |
| GAO Xiang WANG Gang MA Ji hu. AN APPROACH OF BUILDING SIMPLIFIED MULTIVARIATE STATISTICAL MODEL BASED ON MAHALANOBIS DISTANCE[J]. Information and Control, 2001, 0(Z1) |
| |
| Authors: | GAO Xiang WANG Gang MA Ji hu |
| |
| Affiliation: | GAO Xiang 1 WANG Gang 2 MA Ji hu 1 |
| |
| Abstract: | An averaging sample approach based on the shortest Mahalanobis Distances (MD) among the samples is proposed. A new data set of samples is constructed from the data set of total normal historical samples for building multivariate statistical models. The representativity of the data set of new samples related to the total samples can be examined through comparing the deviation of centroids and difference of the covariance between the two data sets so that a goal is achieved which the statistical characteristic of total samples is represented by only using fewer effective samples from all samples. Simulation result proves the sameness between the simplified model and the previous model for fault diagnosis so that there are lower requirement for memory and computation in the system. |
| |
| Keywords: | mahalanobis distance principal component analysis multivariate statistical model multivariate calibration representativity fault diagnosis |
| 本文献已被 CNKI 维普 等数据库收录！ |
