基于局部邻域标准化策略的多工况过程故障检测

摘要/Abstract

摘要：

摘要：为满足实际工业过程中的生产需求，复杂的化工过程往往会包含多种运行模态，而且过程数据不再单一地服从高斯分布或非高斯分布.过程数据的多工况分布特性以及同一工况下数据分布的不确定性使得传统的多元统计方法无法得到满意结果.针对复杂化工过程中多工况以及复杂数据分布的问题，提出一种基于局部邻域标准化策略（Local Neighborhood Standardization， LNS）的故障检测方法.首先，运用局部邻域标准化策略对历史数据集进行预处理，并充分考虑到邻域密度，再通过局部密度因子（Local Density Factor, LDF）构造监控统计量，进而对工业过程数据进行在线故障检测，最后通过数值例子和Tennessee Eastman（TE）过程验证本文方法的有效性.

关键词: 多工况过程监控, 局部密度因子, 局部邻域标准化

Abstract:

Abstract： Complex chemical processes often have multiple operating modes to meet the changes of production condition. The actual industrial processes often contain multiple operating modes and the process data is no longer solely Gaussian or nonGaussian distribution.The multimode characteristics and the uncertainty of data distribution within one single mode make the conventional multivariate statistical process monitoring methods unsuitable for fault detection.To solve the problem of multiple operating modes and complex data distribution, this paper proposed a novel multimode data processing method called local neighborhood standardization (LNS) and local density factor. The LNS was used in data preprocessing and the local density factor was used as a monitoring statistic value. The validity and effectiveness of the proposed method were illustrated through a numerical example and the Tennessee Eastman process.

Key words: multimode process monitoring, local density factor, local neighborhood standardization

中图分类号:

TP 277

郭红杰1，徐春玲2，侍洪波1. 基于局部邻域标准化策略的多工况过程故障检测[J]. 上海交通大学学报（自然版）, 2015, 49(06): 868-875.

GUO Hongjie1,XU Chunling2,SHI Hongbo1. Multimode Process Monitoring Based on Local Neighborhood Standardization Strategy[J]. Journal of Shanghai Jiaotong University, 2015, 49(06): 868-875.

参考文献

［1］Ge Zhiqiang, Song Zhihuan. Multimode process monitoring based on Bayesian method ［J］. Journal of Chemometrics, 2009, 23(12): 636650

［2］Zhao Shijian, Zhang Jie, Xu Yongmao. Monitoring of processes with multiple operation modes through multiple principle component analysis models ［J］. Industrial & Engineering Chemistry Research, 2004, 43(22):70257035

［3］Qin S J. Statistical process monitoring: basics and beyond ［J］. Journal of Chemometrics, 2003, 17(89)：480502

［4］Ge Zhiqiang, Gao Furong, Song Zhihuan. Twodimensional bayesian monitoring method for nonlinear multimode processes ［J］. Chemical Engineering Science, 2011, 66(21):51735183

［5］Yu Jie, Qin S J. Multimode process monitoring with bayesian inferencebased finite gaussian mixture models ［J］. AIChE Journal, 2008, 54(7):18111829

［6］Yu Jie. A particle filter driven dynamic gaussian mixture model approach for complex process monitoring and fault diagnosis ［J］. Journal of Process Control, 2012, 22(4):778788

［7］Yu Jie. A nonlinear kernel gaussian mixture model based inferential monitoring approach for fault detection and diagnosis of chemical processes ［J］. Chemical Engineering Science, 2011, 68(1):506519

［8］Xie Xiang, Shi Hongbo. Dynamic multimode process modeling and monitoring using adaptive gaussian mixture models ［J］. Industrial & Engineering Chemistry Research, 2012, 51(15):54975505

［9］Rashid M M, Yu Jie. Hidden markov model based adaptive independent component analysis approach for complex chemical process monitoring and fault detection ［J］. Industrial & Engineering Chemistry Research, 2012, 51(15):55065514

［10］Teppola P, Mujunen S P, Minkkinen P. Adaptive fuzzy cmeans clustering in process monitoring ［J］. Chemometrics and Intelligent Laboratory Systems, 1999, 45(12):2338

［11］Ge Zhiqiang, Song Zhihuan. Online monitoring of nonlinear multiple mode processes based on adaptive local model approach ［J］. Control Engineering Practice, 2008, 16(12):14271437

［12］Lee Y H, Jin H D, Han Chonghun. Online process state classification for adaptive monitoring ［J］. Industrial & Engineering Chemistry Research, 2006, 45(9):30953107

［13］Jin H D, Lee Y H, Lee G, et al. Robust recursive principal component analysis modeling for adaptive monitoring ［J］. Industrial & Engineering Chemistry Research, 2006, 45(2):696703

［14］Ma Yuxin, Ma Hehe, Shi Hongbo, et al. Dynamic process monitoring using adaptive local outlier factor ［J］. Chemometrics and Intelligent Laboratory Systems, 2013, 127:89101

［15］Hwang D H, Han Chonghun. Realtime monitoring for a process with multiple operating modes ［J］. Control Engineering Practice, 1999, 7(7):891902

［16］Lane S, Martin E B, Kooijmans R, et al. Performance monitoring of a multiproduct semibatch process ［J］. Journal of Process Control, 2001, 11(1): 111

［17］He Q P, Wang J. Fault detection using the knearest neighbor rule for semiconductor manufacturing processes ［J］. IEEE Transactions on Semiconductor Manufacturing, 2007, 20(4): 345354

［18］Ma Hehe, Hu Yi, Shi Hongbo. A novel local neighborhood standardization strategy and its application in fault detection of multimode processes ［J］. Chemometrics and Intelligent Laboratory Systems, 2012, 118: 287300

［19］Ma Hehe, Hu Yi, Shi Hongbo. Fault detection based on the neighborhood standardized local outlier factor method ［J］. Industrial &Engineering Chemistry Research, 2013, 52(6): 23892402

［20］Wang Guozhu, Liu Jianchang, Zhang Yingwei, et al. A novel multimode data processing method and its application in industrial process monitoring ［J］. Journal of Chemometrics, 2014, 29(2): 126138

［21］Latecki L J, Lazarevic A, Pokrajac D. Outlier detection with kernel density functions［J］. Lecture Notes in Computer Science, 2007, 4571: 6175

［22］Silverman B W. Density estimation for statistics and data analysis ［M］. New York: Chapman and Hall, 1986.

［23］Ricker N L. Decentralized control of the Tennessee Eastman Challenge Process ［J］. Journal of Process Control, 1996,6:205221

编辑推荐 0

Metrics

阅读次数

全文

123

HTML			PDF

最新录用	在线预览	正式出版	最新录用	在线预览	正式出版
0	0	0	0	0	123

	来源	其他网站

	次数	123
	比例	100%

摘要

最新录用	在线预览	正式出版

0	0	79

	来源	其他网站

	次数	79
	比例	100%

[1]	杨振，付庄，管恩广，徐建南，田仕禾，郑辉. MLattice模块机器人的运动学分析及构型优化[J]. 上海交通大学学报（自然版）, 2017, 51(10): 1153-1159.
[2]	赵君1,余海东2. 基于绝对节点坐标法的柔性双臂机构动力学分析[J]. 上海交通大学学报（自然版）, 2017, 51(10): 1160-1165.
[3]	赵子任1,杜世昌1,黄德林1，任斐2，梁鑫光2. 多工序制造系统暂态阶段产品质量马尔科夫建模与瓶颈分析[J]. 上海交通大学学报（自然版）, 2017, 51(10): 1166-1173.
[4]	黄炫圭. 小边概率条件下较小植入团的算法[J]. 上海交通大学学报（自然版）, 2017, 51(10): 1202-1206.
[5]	罗晶晶a,余海东a,赵春璋a,b,王皓a,b. 基于绝对节点坐标法变截面柔性梁运动稳定性研究[J]. 上海交通大学学报（自然版）, 2017, 51(10): 1174-1180.
[6]	汪一波1，黄亦翔1，李炳初1，凌晓1，赵帅1，刘成良1,张大庆2. 一种基于静力学预计算的开关磁阻电机模态仿真方法[J]. 上海交通大学学报（自然版）, 2017, 51(10): 1181-1188.
[7]	周炳海,黎明. 考虑机器人约束加工的制造单元调度方法[J]. 上海交通大学学报（自然版）, 2017, 51(10): 1214-1219.
[8]	陈进平1，张树生1，何卫平1，王明微1，黄晖2. 基于驱动参数建模的可行更改路径搜索和优选方法[J]. 上海交通大学学报（自然版）, 2017, 51(10): 1220-1227.
[9]	周鹏辉，马红占，陈东萍，陈梦月，褚学宁. 基于模糊随机故障模式与影响分析的产品再设计模块识别[J]. 上海交通大学学报（自然版）, 2017, 51(10): 1189-1195.
[10]	彭程,朱剑昀,陈俐. 基于模型参考控制的混合动力汽车模式切换 [J]. 上海交通大学学报（自然版）, 2017, 51(10): 1196-1201.
[11]	柳伟，杨超. 基于反向传播神经网络的注塑模具用零件报价模型[J]. 上海交通大学学报（自然版）, 2017, 51(10): 1207-1213.
[12]	陈苏婷，王卓，王奇. 基于非线性尺度空间的航拍场景分类[J]. 上海交通大学学报（自然版）, 2017, 51(10): 1228-1234.
[13]	陈宁，贺小滨，桂卫华，阳春华. 基于混沌离散序列的图像加密算法研究[J]. 上海交通大学学报（自然版）, 2017, 51(10): 1273-1280.
[14]	刘凯a，张立民b，周立军a. 随机受限玻尔兹曼机组设计[J]. 上海交通大学学报（自然版）, 2017, 51(10): 1235-1240.
[15]	朱信尧1，宋保维2，徐刚1，杨松林1. 支撑机构驻留水下航行器着陆策略及影响因素[J]. 上海交通大学学报（自然版）, 2017, 51(10): 1241-1251.