Adaptive Cointegration Analysis and Modified RPCA With Continual Learning Ability for Monitoring Multimode Nonstationary Processes
Adaptive Cointegration Analysis and Modified RPCA With Continual Learning Ability for Monitoring Multimode Nonstationary Processes
复制标题
自适应协整分析和改进的具有持续学习能力的 RPCA 用于监测多模非平稳过程
DOI：
10.1109/tcyb.2021.3140065
复制
发表时间：
2022-02
期刊：
影响因子：
--
通讯作者：
Maoyin Chen
中科院分区：
文献类型：
--
作者：
Jingxin Zhang;Donghua Zhou;Maoyin Chen
本研究探讨了频繁变化模式下的非平稳过程监测，其中允许不断出现新的模式。然而，在目前的多模态过程监测方法中，对于多模态非平稳过程，通常需要从所有可能的模式中获取数据，并且通过先验知识实现模式识别。相反，递归方法基于连续的数据更新监控模型。然而，他们优雅地忘记了所学的知识，无法追踪剧烈的变化。针对每种模式下的非平稳数据，本文提出了一种自适应协整分析（CA）来区分真实故障和正常变化，一旦遇到正态样本就更新模型，并适应协整关系的逐渐变化。然后，提出了一种改进的具有持续学习能力的递归主成分分析（RPCA）来处理剩余的动态信息，其中，当出现新模式时，采用弹性权值巩固来巩固先前学习的知识。保留的信息有利于建立比传统RPCA更精确的模型，避免了未来类似模式的严重性能下降。此外，利用先验知识提出了新的统计量，并通过递归核密度估计计算阈值来提高性能。通过与递归CA和递归慢特征分析的深入比较，强调了递归CA在算法精度、存储性能和计算复杂度方面的优势。通过数值算例和实际工业系统的研究，与现有的递归算法进行了比较，证明了所提方法的有效性。
This study investigates nonstationary process monitoring under frequently varying modes, where new modes are allowed to emerge constantly. However, in current multimode process monitoring methods, generally, data are required from all possible modes and mode identification is realized by prior knowledge for multimode nonstationary processes. In contrast, recursive methods update a monitoring model based on the successive data. However, they forget the learned knowledge gracefully and fail to track drastic variations. Aimed at nonstationary data in each mode, this article proposes an adaptive cointegration analysis (CA) to distinguish real faults from normal variations, which updates a model once a normal sample is encountered and adapts to the gradual change in the cointegration relationship. Then, a modified recursive principal component analysis (RPCA) with continual learning ability is developed to deal with the remaining dynamic information, wherein elastic weight consolidation is adopted to consolidate the previously learned knowledge when a new mode appears. The preserved information is beneficial for establishing a more accurate model than traditional RPCA and avoiding drastic performance degradation for future similar modes. In addition, novel statistics are proposed with prior knowledge and thresholds are calculated by recursive kernel density estimation to enhance the performance. An in-depth comparison with recursive CA and recursive slow feature analysis is conducted to emphasize the superiority, in terms of the algorithm accuracy, memory properties, and computational complexity. Compared with state-of-the-art recursive algorithms, the effectiveness of the proposed method is shown by studying on a numerical case and a practical industrial system.
登录
查看更多内容
基于结构字典学习的多模式过程监控及其在铝电解过程中的应用
DOI：
10.1109/tase.2020.2984334
发表时间：
2020
影响因子：
5.6
作者：
Keke Huang;Yiming Wu;Chunhua Yang;Gongzhuang Peng;Weiming Shen
通讯作者：
Weiming Shen
基于递归全原理分量回归的故障检测及其在车载信息物理系统中的应用
影响因子：
12.3
作者：
Jiang, Yuchen;Yin, Shen
通讯作者：
Yin, Shen
基于切换自回归动态潜变量模型的多模式过程监控
影响因子：
7.7
作者：
Zhou Le;Zheng Jiaqi;Ge Zhiqiang;Song Zhihuan;Shan Shengdao
通讯作者：
Shan Shengdao
适用于大范围非平稳和瞬态连续过程的条件驱动数据分析和监控
DOI：
10.1109/tase.2020.3010536
发表时间：
2021-10
影响因子：
5.6
作者：
Chunhui Zhao;Junhao Chen;Hua Jing
通讯作者：
Hua Jing
影响因子：
4.2
作者：
Q. Chen;U. Kruger;A. Leung
通讯作者：
Q. Chen;U. Kruger;A. Leung