引用本文:李 元,马雨含,张成,冯立伟.局部近邻标准化偏最小二乘的多模态间歇过程故障检测[J].控制理论与应用,2020,37(5):1109~1117.[点击复制]
LI Yuan,MA Yu-han,ZHANG Cheng,FENG Li-wei.Fault detection for multi-modal batch process based on the local neighborhood standardization partial least squares[J].Control Theory and Technology,2020,37(5):1109~1117.[点击复制]
局部近邻标准化偏最小二乘的多模态间歇过程故障检测
Fault detection for multi-modal batch process based on the local neighborhood standardization partial least squares
摘要点击 1849  全文点击 730  投稿时间：2018-09-24  修订日期：2019-11-05
查看全文  查看/发表评论  下载PDF阅读器
DOI编号  10.7641/CTA.2019.80725
  2020,37(5):1109-1117
中文关键词  局部近邻标准化  偏最小二乘  多模态间歇过程  故障检测
英文关键词  local neighborhood standardization  partial least squares  multi-modal batch process  fault detection
基金项目  国家自然科学基金项目(61490701, 61673279)资助.
作者单位E-mail
李 元* 沈阳化工大学信息工程学院 li-yuan@mail.tsinghua.edu.cn 
马雨含 沈阳化工大学信息工程学院  
张成 沈阳化工大学数理系  
冯立伟 沈阳化工大学数理系  
中文摘要
      本文针对多模态间歇过程数据多中心和模态方差差异明显的问题, 提出了一种基于局部近邻标准化偏最 小二乘方法. 首先, 采用统计模量方法处理间歇过程数据, 再利用局部近邻标准化方法将统计模量后的训练数据进 行高斯化处理, 建立偏最小二乘监控模型, 确定控制限; 然后, 同样对统计模量后的测试数据进行局部近邻标准化处 理, 再计算测试数据的高斯偏最小二乘监控指标, 进行过程监视及故障检测. 最后, 通过数值实例和青霉素发酵过 程验证方法有效性. 实验结果表明所提方法解决了故障样本近邻集跨模态问题, 对多模态数据具有更好的故障检 测能力.
英文摘要
      In this paper, a local neighborhood standardization partial least squares (LNS-PLS) method is proposed to solve the problem of multi center and the distinctly different modal variance in multi-modal batch process data. Firstly, statistical pattern method is used for batch process data, and the local nearest neighbor standardization (LNS) method is used to transform the training data after statistical pattern into Gaussian distribution. The partial least squares (PLS) model is established and the control limits of T2 and squared prediction error (SPE) are determined. Next, the LNS standardized is performed on the test data of statistical pattern, and the new Gaussian PLS monitoring indexes are calculated for process monitoring and fault detection. Finally, the effectiveness of the algorithm is verified by the simulation experiment of numerical example and penicillin fermentation process. The results show that the proposed method solves the problem of the neighbor set of fault samples spanning two modes and has better fault detection ability for multi-modal data.