计算机应用 ›› 2018, Vol. 38 ›› Issue (4): 965-970.DOI: 10.11772/j.issn.1001-9081.2017092310

• 人工智能 • 上一篇    下一篇

基于统计模量和局部近邻标准化的局部离群因子故障检测方法

冯立伟1,2, 张成1,2, 李元1, 谢彦红1,2   

  1. 1. 沈阳化工大学 数理系, 沈阳 110142;
    2. 沈阳化工大学 过程故障诊断研究中心, 沈阳 110142
  • 收稿日期:2017-09-25 修回日期:2017-12-08 出版日期:2018-04-10 发布日期:2018-04-09
  • 通讯作者: 李元
  • 作者简介:冯立伟(1980-),男山东青州人,讲师,硕士,主要研究方向:过程故障检测;张成(1979-),男辽宁沈阳人,副教授,硕士,主要研究方向:过程故障诊断分析;李元(1964-),女,辽宁沈阳人,教授,博士,主要研究方向:基于数据驱动的复杂过程故障诊断;谢彦红(1964-),女,辽宁沈阳人,教授,博士,主要研究方向:过程控制、故障诊断。
  • 基金资助:
    国家自然科学基金资助项目(61673279);辽宁省教育厅基金资助项目(L2015432);辽宁省自然科学基金资助项目(2015020164)。

Local outlier factor fault detection method based on statistical pattern and local nearest neighborhood standardization

FENG Liwei1,2, ZHANG Cheng1,2, LI Yuan1, XIE Yanhong1,2   

  1. 1. Department of Science, Shenyang University of Chemical Technology, Shenyang Liaoning 110142, China;
    2. Research Center for Technical Process Fault Diagnosis and Safety, Shenyang University of Chemical Technology, Shenyang Liaoning 110142, China
  • Received:2017-09-25 Revised:2017-12-08 Online:2018-04-10 Published:2018-04-09
  • Supported by:
    This work is partially supported by the National Natural Science Foundation of China (61673279), the Project of Education Department in Liaoning (L2015432), the Natural Science Foundation of Liaoning Province (2015020164).

摘要: 针对多工况过程数据的批次不等长、中心漂移、工况结构不同等特点,提出基于统计模量和局部近邻标准化的局部离群因子故障检测方法(SP-LNS-LOF)。首先计算每个训练样本的统计模量;然后使用局部近邻集标准化统计模量,得到标准样本;最后计算标准化样本的局部离群因子,并将其作为检测指标,将局部离群因子的分位点作为检测控制限,当在线样本的局部离群因子大于检测控制限时,判定其为故障;否则为正常。统计模量提取过程的主要信息,且消除批次不等长的影响;局部近邻标准化克服工况中心漂移和工况结构不同的困难;局部离群因子度量样本的相似度,实现故障样本和正常样本的分离。进行了半导体蚀刻过程故障检测仿真实验,实验结果表明SP-LNS-LOF检测出了全部21个故障,比主元分析(PCA)、核主元分析(kPCA)、基于k近邻的故障检测(FD-kNN)、局部离群因子(LOF)方法具有更高的检测率。理论分析和仿真实验说明SP-LNS-LOF方法适用于多工况过程故障检测,具有较高的故障检测效率,能保证多工况生产过程的安全性。

关键词: 统计模量, 局部近邻标准化, 局部离群因子, 多工况, 半导体过程

Abstract: A Local Outlier Factor fault detection method based on Statistics Pattern and Local Nearest neighborhood Standardization (SP-LNS-LOF) was proposed to deal with the problem of unequal batch length, mean drift and different batch structure of multi-process data. Firstly, the statistical pattern of each training sample was calculated; secondly, each statistical modulus was standardized as standard sample by using the set of local neighbor samples; finally the local outlier factor of standard sample was calculated and used as a detection index. The quintile of the local outlier factor was used as the detection control limit, when the local outlier factor of the online sample was greater than the detection control limit, the online sample was identified as a fault sample, otherwise it was a normal sample. The statistical pattern was used to extract the main information of the process and eliminate the impact of unequal length of batches; the local neighborhood normalization was used to overcome the difficulties of mean shift and different batch structure of process data; the local outlier factor was used to measure the similarity of samples and separate the fault samples from the normal samples. The simulation experiment of semiconductor etching process was carried out. The experimental results show that SP-LNS-LOF detects all 21 faults, and has higher detection rate than that of Principal Component Analysis (PCA), kernel PCA (kPCA), Fault Detection using k Nearest Neighbor rule (FD-kNN) and Local Outlier Factor (LOF) methods. The theoretical analysis and simulation result show that SP-LNS-LOF is suitable for fault detection of multimode process, and has high fault detection efficiency and ensures the safety of the production process.

Key words: statistical pattern, local neighborhood standardization, Local Outlier Factor (LOF), multimode, semiconductor process

中图分类号: