基于核Fisher包络分析的间歇过程故障诊断

doi:10.3969/j.issn.0438-1157.2014.04.023

化工学报 ›› 2014, Vol. 65 ›› Issue (4): 1317-1326.DOI: 10.3969/j.issn.0438-1157.2014.04.023

基于核Fisher包络分析的间歇过程故障诊断

王晶, 刘莉, 曹柳林, 靳其兵

北京化工大学信息科学与技术学院, 北京 100029

收稿日期:2013-07-03 修回日期:2013-11-21 出版日期:2014-04-05 发布日期:2013-12-20
通讯作者: 刘莉
作者简介:王晶（1972—），女，博士，教授。
基金资助:
国家自然科学基金项目（61174128，51375038）；北京市自然科学基金项目（4132044）。

Fault diagnosis based on kernel Fisher envelope surface for batch processes

WANG Jing, LIU Li, CAO Liulin, JIN Qibing

School of Information Science & Technology, Beijing University of Chemical Technology, Beijing 100029, China

Received:2013-07-03 Revised:2013-11-21 Online:2014-04-05 Published:2013-12-20
Supported by:
supported by the National Natural Science Foundation of China(61174128, 51375038) and the Natural Science Foundation of Beijing (4132044).

摘要/Abstract

摘要： 随着间歇过程越来越受重视，其过程监控和故障诊断技术也成为研究热点。以核Fisher判别分析为基础，提出了基于核Fisher的正常工况与故障包络面模型，给出了基于该模型的在线故障诊断流程。此方法利用了Fisher判别分析对类别的划分特点，分别针对正常工况数据和各故障类型数据建立包络曲面模型。与多向Fisher判别分析相比，该方法按批次方向将数据展开，能够解决生产周期不一致问题，在线故障诊断时也不需要预报完整的生产轨迹，并且加入核函数来处理复杂的非线性。最后在青霉素发酵过程的仿真平台上对该方法进行测试，与改进多向Fisher判别分析方法进行对比，该方法获得了满意的诊断效果：能够及早诊断出故障的发生，并在有效识别已有故障的同时还具有对新故障的自学习能力。

关键词: 间歇过程, 故障诊断, 核Fisher, 包络面模型

Abstract: With increasing importance of batch processes, its monitoring and fault diagnosis technology has become a research focus. An envelope surface model of normal and fault operation conditions based on kernel Fisher analysis technique was proposed, and also an online fault diagnosis program was presented in this paper. With kernel Fisher discriminant analysis's characteristics for classification, envelope surface models for normal data and each fault data were built. Compared with multiway Fisher discriminant analysis (MFDA), the proposed method unfolded the process data batch-wise, so it could deal with unequal batch length and did not require to predict the whole production trajectory when implementing online fault diagnosis. Also kernel function could deal with nonlinear problems. Finally, the proposed method was tested in the simulation platform of penicillin fermentation process. The simulation results comparing with the improved MFDA showed that the proposed method could diagnose the fault early, and also had self-learning ability for new fault.

Key words: batch processes, fault diagnosis, kernel Fisher analysis, envelope surface model

中图分类号:

TP277

王晶, 刘莉, 曹柳林, 靳其兵. 基于核Fisher包络分析的间歇过程故障诊断[J]. 化工学报, 2014, 65(4): 1317-1326.

WANG Jing, LIU Li, CAO Liulin, JIN Qibing. Fault diagnosis based on kernel Fisher envelope surface for batch processes[J]. CIESC Journal, 2014, 65(4): 1317-1326.

参考文献

[1] Yang Zhicai(杨志才). Batch Process—Principles, Process and Equipment in Chemical Production (化工生产中的间歇过程—— 原理、工艺及设备) [M]. Beijing: Chemical Industry Press, 2001: 1-5
[2] Venkatasubramanian V, Rengaswamy R, Yin K, Kavuri S N. A review of process fault detection and diagnosis(Ⅰ): Quantitative model-based methods[J]. Computers & Chemical Engineering, 2003, 27(3): 293- 311
[3] MacGregor J F, Kourti T. Statistical process control of multivariate processes[J]. Control Engineering Practice, 1995, 3(3): 403-414
[4] Yang Yinghua(杨英华). Process monitoring and fault diagnosis based on a nonlinear principal component regression method [J]. Information and Control(信息与控制), 2002, 31(3): 272-276
[5] Komulainen T, Sourander M, Jamsa-Jounela S L. An online application of dynamic PLS to a de-aromatization process[J]. Computers &Chemical Engineering, 2004, 28(12): 2611-2619
[6] Russell E L, Chiang L H, Braatz R D. Fault detection in industrial processes using canonical variate analysis and dynamic principal component analysis[J]. Chemometrics and Intelligent Laboratory Systems, 2000, 51(1): 81-93
[7] Jiang Liying(蒋丽英). Researches on fault diagnosis for process industry with FDAD/PLS methods[D]. Hangzhou: Zhejiang University, 2005
[8] Nomikos P, MacGregor J F. Monitoring batch process using multiway principal component analysis[J]. AIChE. J., 1994, 40: 1361-1375
[9] Nonikos P, MacGregor J E. Multiway partial least squares in monitoring batch process[J]. Chem. Intell. Lab. Sys., 1995, 30: 97-115
[10] Chen Yahua(陈亚华). Monitoring batch processes using multiway Fisher discriminnant analysis[J]. Journal of Jilin University: Information Science Edition(吉林大学学报:信息科学版), 2004, 22(4): 384-387
[11] Jiang L Y, Xie L, Wang S Q. Monitoring and fault diagnosis of batch process using multi-model Fisher discriminant analysis// Fifth World Congress on Intelligent Control and Automation[C]. Hangzhou, 2004, 2: 1780-1784
[12] Kassidas A, MaeGregor J F, Taylor P A. Synchronization of batch trajectories using dynamic time warping[J]. AIChE J., 1998, 44: 864-875
[13] Undey C, Ertunc S, Cinar A. Online batch/fed-batch process performance monitoring, quality prediction, and variable- contribution analysis for diagnosis[J]. Ind. Eng. Chem. Res., 2003, 42: 4645-4658
[14] Jiang L Y, Xie L, Wang S Q. Fault diagnosis for batch processes by improved multi-model Fisher discriminant analysis[J]. Chinese Journal of Chemical Engineering, 2006, 14(3): 343-348
[15] Mika S, Ratsch G, Weston J, Scholkopf B, Mullers K R. Fisher discriminant analysis with kernels//Proceeding of the IEEE International Workshop on Neural Networks for Signal Processing[C]. 1999: 41-48
[16] Christianini N, Shawe-Taylor J. An Introduction to Support Vector Machines and Other Kernel Based Learning Methods[M]. UK: Cambridge University Press, 2000
[17] Birol G, Undey C, Cinar A. A modular simulation package for fed-batch fermentation: penicillin production[J]. Computers＆Chemical Engineering, 2002, 26(11): 1553-1565
[18] Bajpai R, Reuss M. A mechanistic model for penicillin production[J]. Journal of Chemical Technology and Biotechnology, 1980, 30: 332-344
[19] Undey C, Tatara E, Cinar A. Intelligent real-time performance monitoring and quality prediction for batch/fed-batch cultivations[J]. Journal of Biotechnology, 2004, 108(1): 61-77

基于核Fisher包络分析的间歇过程故障诊断

Fault diagnosis based on kernel Fisher envelope surface for batch processes

PDF (PC)

可视化

被引次数

摘要/Abstract

引用本文

使用本文

参考文献

相关文章 15

编辑推荐

Metrics

本文评价

[1]	明迁, 高逸, 胡剑, 李盛杰, 王金江. 热交换器泄漏故障虚拟感知方法研究[J]. 化工学报, 2023, 74(4): 1836-1846.
[2]	高学金, 程琨, 韩华云, 高慧慧, 齐咏生. 基于中心损失的条件生成式对抗网络的冷水机组故障诊断[J]. 化工学报, 2022, 73(9): 3950-3962.
[3]	杨静, 林振康, 汤君, 樊铖, 孙克宁. 电池系统的故障特征以及多故障的诊断与识别[J]. 化工学报, 2022, 73(8): 3394-3405.
[4]	孙哲, 金华强, 李康, 顾江萍, 黄跃进, 沈希. 基于知识数据化表达的制冷空调系统故障诊断方法[J]. 化工学报, 2022, 73(7): 3131-3144.
[5]	张成, 潘立志, 李元. 基于加权统计特征KICA的故障检测与诊断方法[J]. 化工学报, 2022, 73(2): 827-837.
[6]	张弛, 李浩, 胡海涛, 朱翀, 张玉莹, 南国鹏, 舒悦. 基于自动特征工程的飞行器轴承故障诊断[J]. 化工学报, 2021, 72(S1): 430-436.
[7]	郑必鸣, 史彬, 鄢烈祥. 多因素不确定条件下的间歇生产调度优化[J]. 化工学报, 2020, 71(3): 1246-1253.
[8]	于蕾, 邓晓刚, 曹玉苹, 路凯琪. 基于变量分组DTW-MCVA的不等长间歇过程故障检测方法[J]. 化工学报, 2019, 70(9): 3441-3448.
[9]	邓佳伟, 邓晓刚, 曹玉苹, 张晓玲. 基于加权统计局部核主元分析的非线性化工过程微小故障诊断方法[J]. 化工学报, 2019, 70(7): 2594-2605.
[10]	杨新, 麻哲瑞, 申赫男, 陈鸿伟. 基于多尺度特征能量-核极限学习机的双循环流化床气流堵塞故障智能诊断[J]. 化工学报, 2019, 70(7): 2616-2625.
[11]	彭开香, 张传放, 马亮, 董洁, 焦瑞华, 唐鹏. 面向系统层级的复杂工业过程全息故障诊断[J]. 化工学报, 2019, 70(2): 590-598.
[12]	顾炳斌, 熊伟丽. 基于多块信息提取的PCA故障诊断方法[J]. 化工学报, 2019, 70(2): 736-749.
[13]	郭孝正, 刘琳琳, 张磊, 都健. 基于截断器半连续操作的间歇过程性质集成[J]. 化工学报, 2019, 70(2): 516-524.
[14]	鲁春燕, 李炜. 基于深度置信网络的炼化空压机故障诊断方法[J]. 化工学报, 2019, 70(2): 757-763.
[15]	王立敏, 卢丽彬, 高福荣, 周东华. 多阶段间歇过程无穷时域优化线性二次容错控制[J]. 化工学报, 2019, 70(2): 541-547.