Continuous and Discrete Variables-Concurrent Analysis-Based Nonstationary and Non-Gaussian Industrial Process Anomaly Detection

CAI Mei-ling; LUO Di; XIAO Jing-ri; LI Jing-yan; LIU Jin-ping

doi:10.12263/DZXB.20240466

您当前的位置：

首页 >

文章列表页 >

Continuous and Discrete Variables-Concurrent Analysis-Based Nonstationary and Non-Gaussian Industrial Process Anomaly Detection

PAPERS | 更新时间：2026-05-07

- Continuous and Discrete Variables-Concurrent Analysis-Based Nonstationary and Non-Gaussian Industrial Process Anomaly Detection
- ACTA ELECTRONICA SINICA Vol. 52, Issue 10, Pages: 3291-3300(2024)
- 作者机构：
  
  1.湖南师范大学信息科学与工程学院，湖南长沙 410081
  2.湘江实验室，湖南长沙 410205
  3.湖南师范大学数学与统计学院，湖南长沙 410081
- 作者简介：
- 基金信息：
  
  National Natural Science Foundation of China(62371187);Major Program Project of Xiangjiang Laboratory(22XJ01013)
- DOI：10.12263/DZXB.20240466
  CLC： TP273
- Received：20 May 2024，
  
  Revised：2024-08-30，
  
  Published：25 October 2024
- 稿件说明：
移动端阅览
蔡美玲, 罗迪, 肖敬日, 等. 连续与离散变量协同分析的非平稳非高斯工业过程异常检测[J]. 电子学报, 2024, 52(10): 3291-3300.

CAI Mei-ling, LUO Di, XIAO Jing-ri, et al. Continuous and Discrete Variables-Concurrent Analysis-Based Nonstationary and Non-Gaussian Industrial Process Anomaly Detection[J]. Acta Electronica Sinica, 2024, 52(10): 3291-3300.
蔡美玲, 罗迪, 肖敬日, 等. 连续与离散变量协同分析的非平稳非高斯工业过程异常检测[J]. 电子学报, 2024, 52(10): 3291-3300. DOI：10.12263/DZXB.20240466

CAI Mei-ling, LUO Di, XIAO Jing-ri, et al. Continuous and Discrete Variables-Concurrent Analysis-Based Nonstationary and Non-Gaussian Industrial Process Anomaly Detection[J]. Acta Electronica Sinica, 2024, 52(10): 3291-3300. DOI：10.12263/DZXB.20240466

摘要

工业过程数据涵盖离散和连续变量，它们之间内在的统计分布特性是揭示系统运行状况的关键.然而，现有的监测模型多聚焦于高斯假设下的连续过程变量，忽略了离散变量、连续变量的多模分布特性以及数据中的噪声、离群点对模型的影响，难以精准反映数据的真实分布特性，对非高斯、非平稳过程的异常检测效果欠佳.因此，本文提出一种鲁棒的工业过程异常检测方法——连续和离散变量协同分析的变分贝叶斯混合判别方法（Continuous and Discrete Variables-Concurrent Analysis-based Variational Bayesian Mixture Discriminant，CDVCA-VBMD）.通过构建基于变分贝叶斯推断的面向连续变量的混合学生分布模型与面向离散多变量的混合多项分布模型，有效解决过程变量非高斯分布特性难以有效提取的问题，实现了过程变量复杂相关性的高效处理与分析；同时，在过程监测中引入了持续学习的理念，确保对非平稳时变工业过程异常的有效检测.以数值仿真系统和田纳西·伊斯曼过程为例，进行了大量验证性和对比性实验.结果表明，CDVCA-VBMD能准确估计非平稳工业过程多变量的混合多模分布特性，并对数据中的噪声和离群点具有较强的鲁棒性，从而实现工业异常的准确检测，为非高斯复杂工业过程的长期、鲁棒监测提供了有力支持.

Abstract

Industrial process data encompasses continuous and discrete variables

whose underlying statistical characteristics are crucial for revealing operational conditions. However

current process monitoring models predominantly focus on continuous variables with Gaussian assumptions

which often overlook the significant effects of the multimodal distribution characteristics of process variables

as well as the noises and outliers in process data. These limitations hinder the models' ability to capture complex statistical characteristics

leading to low detection performance particularly in non-Gaussian and nonstationary processes. This article introduces a robust anomaly detection method termed continuous and discrete variables-concurrent analysis-based variational Bayesian mixture discriminator (CDVCA-VBMD). It models continuous variables with a mixed student's t-distribution and discrete variables with a mixed multinomial distribution based on variational Bayesian inference

which can adeptly manage and analyze the complex interdependencies between process variables and overcome the non-Gaussian nature of continuous variables effectively. Furthermore

CDVCA-VBMD incorporates continuous learning to ensure the effective detection of nonstationary industrial processes. Extensive validation and comparative experiments were conducted on a numerical simulation system and the Tennessee Eastman (TE) process. The outcomes demonstrate that CDVCA-VBMD can accurately characterize the mixed multimodal distribution characteristics of time-varying industrial processes

facilitating accurate anomaly detection. Additionally

the method exhibits robustness against noise and outliers in process data

supporting long-term and reliable monitoring of complex and non-Gaussian industrial processes.

关键词

Keywords

references

ALDRINI J , CHIHI I , SIDHOM L . Fault diagnosis and self-healing for smart manufacturing: A review [J ] . Journal of Intelligent Manufacturing , 2024 , 35 ( 6 ): 2441 - 2473 .

MELO A , CÂMARA M M , PINTO J C . Data-driven process monitoring and fault diagnosis: A comprehensive survey [J ] . Processes , 2024 , 12 ( 2 ): 251 .

杨明 , 周斯维 , 谷健 . 基于数据驱动的城市居民出行OD预测 [J ] . 长沙理工大学学报(自然科学版) , 2022 , 19 ( 1 ): 73 - 80 .

YANG M , ZHOU S W , GU J . Traffic OD prediction of urban residents based on data driven [J ] . Journal of Changsha University of Science & Technology (Natural Science) , 2022 , 19 ( 1 ): 73 - 80 . (in Chinese)

柴蓉 , 陈米铃 , 李锦红 . 基于效用优化的星地融合网络联合用户关联及资源块调度算法 [J ] . 电子学报 , 2023 , 51 ( 12 ): 3483 - 3495 .

CHAI R , CHEN M L , LI J H . Utility optimization-based joint user association and resource allocation algorithm for integrated satellite-terrestrial network [J ] . Acta Electronica Sinica , 2023 , 51 ( 12 ): 3483 - 3495 . (in Chinese)

FENG L J , ZHAO C H . Fault description based attribute transfer for zero-sample industrial fault diagnosis [J ] . IEEE Transactions on Industrial Informatics , 2021 , 17 ( 3 ): 1852 - 1862 .

WANG M , ZHOU D H , CHEN M Y , et al . Anomaly detection in the fan system of a thermal power plant monitored by continuous and two-valued variables [J ] . Control Engineering Practice , 2020 , 102 : 104522 .

CHEN J H , ZHAO C H . Exponential stationary subspace analysis for stationary feature analytics and adaptive nonstationary process monitoring [J ] . IEEE Transactions on Industrial Informatics , 2021 , 17 ( 12 ): 8345 - 8356 .

HASTIE T , TIBSHIRANI R . Discriminant analysis by Gaussian mixtures [J ] . Journal of the Royal Statistical Society Series B: Statistical Methodology , 1996 , 58 ( 1 ): 155 - 176 .

HUANG C C , CHEN T , YAO Y . Mixture discriminant monitoring: A hybrid method for statistical process monitoring and fault diagnosis/isolation [J ] . Industrial & Engineering Chemistry Research , 2013 , 52 ( 31 ): 10720 - 10731 .

WANG M , SHENG L , ZHOU D H , et al . A feature weighted mixed naive Bayes model for monitoring anomalies in the fan system of a thermal power plant [J ] . CAA Journal of Automatica Sinica , 2022 , 9 ( 4 ): 719 - 727 .

WANG M , ZHOU D H , CHEN M Y . Adjustable multimode monitoring with hybrid variables and its application in a thermal power plant [J ] . IEEE Transactions on Industrial Informatics , 2023 , 19 ( 2 ): 1425 - 1435 .

李友云 , 陈佳 , 王硕 , 等 . 沥青混合料劈裂疲劳损伤力学特性多尺度研究 [J ] . 长沙理工大学学报(自然科学版) , 2022 , 19 ( 1 ): 1 - 11, 80 .

LI Y Y , CHEN J , WANG S , et al . Multi-scale research on mechanical characteristics of splitting fatigue damage of asphalt mixture [J ] . Journal of Changsha University of Science & Technology (Natural Science) , 2022 , 19 ( 1 ): 1 - 11, 80 . (in Chinese)

裴洪 , 司小胜 , 胡昌华 , 等 . 零寿命标签下退化设备剩余寿命预测方法 [J ] . 电子学报 , 2023 , 51 ( 7 ): 1939 - 1948 .

PEI H , SI X S , HU C H , et al . Prognostic method of remaining useful life for degraded equipment under zero life label [J ] . Acta Electronica Sinica , 2023 , 51 ( 7 ): 1939 - 1948 . (in Chinese)

刘金平 , 王杰 , 唐朝晖 , 等 . 基于自适应滑窗递归稀疏主成分分析的工业过程故障监测 [J ] . 电子学报 , 2020 , 48 ( 9 ): 1795 - 1803 .

LIU J P , WANG J , TANG Z H , et al . Industrial process fault monitoring based on adaptive sliding window-recursive sparse principal component analysis [J ] . Acta Electronica Sinica , 2020 , 48 ( 9 ): 1795 - 1803 . (in Chinese)

ZHAO C H . Perspectives on nonstationary process monitoring in the era of industrial artificial intelligence [J ] . Journal of Process Control , 2022 , 116 : 255 - 272 .

蒋晓玲 , 吴映波 , 陈蒙 , 等 . 基于跨域结构保持投影的异构在线多源迁移学习方法 [J ] . 电子学报 , 2023 , 51 ( 8 ): 1983 - 1994 .

JIANG X L , WU Y B , CHEN M , et al . Heterogeneous online multi-source transfer learning with cross-domain structure preserving projection [J ] . Acta Electronica Sinica , 2023 , 51 ( 8 ): 1983 - 1994 . (in Chinese)

柴铮 , 汪嘉业 , 赵春晖 , 等 . 面向工业监控典型监督任务的深度迁移学习方法: 现状、挑战与展望 [J ] . 中国科学: 信息科学 , 2023 , 53 ( 5 ): 821 - 840 .

CHAI Z , WANG J Y , ZHAO C H , et al . Deep transfer learning methods for typical supervised tasks in industrial monitoring: State-of-the-art, challenges, and perspectives [J ] . Scientia Sinica (Informationis) , 2023 , 53 ( 5 ): 821 - 840 . (in Chinese)

DENG H Q , LI X Y . Anomaly detection via reverse distillation from one-class embedding [C ] // 2022 IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR) . Piscataway : IEEE , 2022 : 9737 - 9746 .

BLEI D M , KUCUKELBIR A , MCAULIFFE J D . Variational inference: A review for statisticians [J ] . Journal of the American Statistical Association , 2017 , 112 ( 518 ): 859 - 877 .

BISHOP C M . Pattern Recognition and Machine Learning [M ] . New York : Springer , 2006 .

CHEN J H , ZHAO C H , DING J L . A flexible probabilistic framework with concurrent analysis of continuous and categorical data for industrial fault detection and diagnosis [J ] . IEEE Transactions on Industrial Informatics , 2023 , 19 ( 10 ): 10578 - 10590 .

ALCALA C F , QIN S JOE . Analysis and generalization of fault diagnosis methods for process monitoring [J ] . Journal of Process Control , 2011 , 21 ( 3 ): 322 - 330 .

SIREGAR S M , PURWANTO Y , WIBOWO S A . Enhancing network anomaly detection with optimized one-class SVM (OCSVM) [C ] // 2023 3rd International Conference on Intelligent Cybernetics Technology & Applications (ICICyTA) . Piscataway : IEEE , 2023 : 84 - 88 .

AHMED M R , MYO T , BAROOMI B AL . Outlier detection to secure wireless sensor networks based on iForest [C ] // 2022 10th International Symposium on Digital Forensics and Security (ISDFS) . Piscataway : IEEE , 2022 : 1 - 6 .

MICHELUCCI U . An introduction to autoencoders [EB/OL ] . ( 2022-01-11 )[ 2024-04-12 ] . https://doi.org/10.48550/arXiv.2201.03898 https://doi.org/10.48550/arXiv.2201.03898 .

REINARTZ C , KULAHCI M , RAVN O . An extended Tennessee Eastman simulation dataset for fault-detection and decision support systems [J ] . Computers & Chemical Engineering , 2021 , 149 : 107281 .

Views

下载量

CSCD

Alert me when the article has been cited

提交

Tools

Publicity Resources

No data

Related Author

No data

Related Institution

No data

⁰