Fault Detection Based on Multivariate Trajectory Analysis

doi:10.7652/xjtuxb201703021

您当前的位置：

首页 >

文章列表页 >

Fault Detection Based on Multivariate Trajectory Analysis

更新时间：2025-07-09

- Fault Detection Based on Multivariate Trajectory Analysis
- Vol. 51, Issue 3, Pages: 122-128(2017)
- 作者机构：
  
  浙江大学工业控制技术国家重点实验室,杭州,310027
- 作者简介：
- 基金信息：
- DOI：10.7652/xjtuxb201703021
  CLC： TP277
- Online First：10 March 2017，
  
  Published：2017
- 稿件说明：
移动端阅览
Fault Detection Based on Multivariate Trajectory Analysis[J]. 2017, 51(3): 122-128.
DOI：

Fault Detection Based on Multivariate Trajectory Analysis[J]. 2017, 51(3): 122-128. DOI： 10.7652/xjtuxb201703021.

摘要

为了解决实际工业过程中的多变量动态过程监测问题

提出了一种基于多变量轨迹分析和主元分析的在线故障检测方法。通过构造过程轨迹向量实现了多变量动态信息的提取

结合主元分析算法对模型进行了改进

利用改进模型充分分析了过程数据的变化特征

同时将关键变量的轨迹趋势图作为参考实现了离线建模和在线故障检测。与传统的基于轨迹分析的方法相比

所提方法克服了变量个数限制

解决了统计量难以设计的问题

提取了过程动态特性

实现了更为可靠的动态过程监测。通过某企业合成氨生产中转化单元的实例验证表明

所提方法在处理多变量动态过程的故障检测问题上效果良好。

Abstract

To solve dynamic problems in industrial multivariable process monitoring

a novel fault detection method is proposed to describe process trajectories combining multivariate trajectory analysis with principal component analysis. The trajectory vectors are constructed to extract information in multivariate dynamic process

and then principal component analysis algorithm is adopted to develop the model and analyze the variation features of process data. The trajectory tendency charts of several critical variables involved with data variations are plotted

and offline modeling and online fault detection are finally realized. Compared with the traditional methods based on trajectory analysis

the proposed method breaks the limitation of variable number and solves the difficulty in developing monitoring statistics to better extract characters in process dynamics and more reliable dynamic process monitoring. A practical case of synthetic ammonia conversion unit verifies the effectiveness of the proposed method.

关键词

Keywords

references

QIN S J. Survey on data-driven industrial process monitoring and diagnosis [J]. Annual Reviews in Control, 2012, 36(2): 220-234.

TONG C, EL-FARRA N H, PALAZOGLU A, et al. Fault detection and isolation in hybrid process systems using a combined data-driven and observer-design methodology [J]. AIChE Journal, 2014, 60(8): 2805-2814.

GE Z, SONG Z, GAO F. Review of recent research on data-based process monitoring [J]. Industrial Engineering Chemistry Research, 2013, 52(10): 3543-3562.

GE Z, SONG Z. Semiconductor manufacturing process monitoring based on adaptive substatistical PCA [J]. IEEE Transactions on Semiconductor Manufacturing, 2010, 23(1): 99-108.

NOMIKOS P, MACGREGOR J F. Monitoring batch processes using multiway principal component analysis [J]. AIChE Journal, 1994, 40(8): 1361-1375.

NOMIKOS P, MACGREGOR J F. Multi-way partial least squares in monitoring batch processes [J]. Chemometrics and Intelligent Laboratory Systems, 1995, 30(1): 97-108.

WEN Q, GE Z, SONG Z. Data-based linear Gaussian state-space model for dynamic process monitoring [J]. AIChE Journal, 2012, 58(12): 3763-3776.

CHOI S W, MORRIS J, LEE I B. Dynamic model-based batch process monitoring [J]. Chemical Engineering Science, 2008, 63(3): 622-636.

YU J. Multiway discrete hidden Markov model-based approach for dynamic batch process monitoring and fault classification [J]. AIChE Journal, 2012, 58(9): 2714-2725.

BOGOMOLOV A. Multivariate process trajectories: capture, resolution and analysis [J]. Chemometrics and Intelligent Laboratory Systems, 2011, 108(1): 49-63.

CIMANDER C, MANDENIUS C F. Bioprocess control from a multivariate process trajectory [J]. Bioprocess and Biosystems Engineering, 2004, 26(6): 401-411.

WAN J, MARJANOVIC O, LENNOX B. Trajectory tracking of batch product quality using intermittent measurements and moving window estimation [C]∥UKACC International Conference on Control. Piscataway, NJ, USA: IEEE, 2012: 115-128.

SHEN F, GE Z, SONG Z. Multivariate trajectory-based local monitoring method for multiphase batch processes [J]. Industrial Engineering Chemistry Research, 2015, 54(4): 1313-1325.

蒋少华, 桂卫华, 阳春华, 等. 基于核主元分析与多支持向量机的监控诊断方法及其应用 [J]. 中南大学学报(自然科学版), 2009, 40(5): 1323-1328.

JIANG Shaohua, GUI Weihua, YANG Chunhua, et al. Method based on kernel principal component analysis and support vector machine and its application [J]. Journal of Central South University(Science and Technology), 2009, 40(5): 1323-1328.

王海清, 宋执环, 李平. 改进PCA及其在过程监测与故障诊断中的应用 [J]. 化工学报, 2001, 52(6): 471-475.

WANG Haiqing, SONG Zhihuan, LI Ping. Improved PCA with application to process monitoring and fault diagnosis [J]. Journal of Chemical Industry and Engineering, 2001, 52(6): 471-475.

Views

下载量

CSCD

Alert me when the article has been cited

提交

Tools

Publicity Resources

Fault Detection Method for Lithium-Ion Battery Sensors in Electric Vehicles Using Likelihood Ratio Test

Automotive Lithium-ion Battery Sensor Fault Diagnosis Method Based on Likelihood Ratio Test

Fault Detection for a Class of Markov Jump Systems with Unknown Disturbances

Data-Driven Research on Health Monitoring Algorithms for the Liquid Rocket Engine

Numerical Simulation of the Energy Conversion Process in Thermoacoustic Engines with Different Stack Materials

Related Author

LIU Panzhi

WU Chunling

LI Yanbo

GUO Guofang

LIU Panzhi

WU Chunling

LI Yanbo

GUO Guofang

Related Institution

School of Energy and Electrical Engineering, Chang'an University

Shaanxi Key Laboratory of New Transportation Energy Development, Application and Vehicle Energy Saving Technology, Chang'an University

Shaanxi Heavy Duty Automobile Co., Ltd.

Key Laboratory of Shaanxi Provincial Development and Application of New Transportation Energy , Chang 'an University, Xi 'an

School of Energy and Electrical Engineering,Chang 'an University, Xi 'an

⁰