Fault Diagnosis of Industrial Process Based on LLE and K-means Clustering Algorithm

doi:10.16182/j.issn1004731x.joss.20-0362

Abstract

Abstract: Because of the similarity of various types of data in the industrial process. The fault diagnosis using the K-means algorithm has a large error rate. A K-means clustering algorithm based on Locally Linear Embedding (LLE) is proposed. the normal data is reduced by the LLE algorithm and the projection matrix is obtained. The projection matrix is used to map the original fault data to the low-dimensional space and the K-means algorithm clusters is used to carry out the data to establish a detection and diagnosis model. The method is applied to the fault detection and diagnosis in the TE (Tennessee-Eastman) process and is compared with the traditional K-means algorithm and LLE algorithm. The results show that the proposed new method has a higher accuracy rate, and could effectively identify the unknown types of fault data.

Key words: K-means clustering, locally linear embedding,TE process, fault diagnosis

CLC Number:

TP277

Li Yuan, Geng Zewei. Fault Diagnosis of Industrial Process Based on LLE and K-means Clustering Algorithm[J]. Journal of System Simulation, 2021, 33(9): 2066-2073.

References

[1] 周东华, 李钢, 李元. 数据驱动的工业过程故障诊断技术[M]. 北京: 科学技术出版社, 2011.
Zhou Donghua, Li Gang, Li Yuan.Data Driven Industrial Process Fault Diagnosis Technology[M]. Beijing: Science and Technology Press, 2011.
[2] 李元, 马雨含, 郭金玉. 基于动态多向局部离群因子的在线故障检测[J]. 计算机应用研究, 2017, 34(11): 3259-3261, 3266.
Li Yuan, Ma Yuhan, Guo Jinyu.Online Fault Detection based on Dynamic Multidirectional Local Outliers[J]. Computer Application Research, 2017, 34(11): 3259-3261, 3266.
[3] 刘强, 柴天佑, 秦泗钊, 等. 基于数据和知识的工业过程监视及故障诊断综述[J]. 控制与决策, 2010, 25(6): 801-807.
Liu Qiang, Chai Tianyou, Qin Sizhao, et al.Overview of Industrial Process Monitoring and Fault Diagnosis Based on Data and Knowledge[J]. Control and Decision, 2010, 25(6): 801-807.
[4] Li Y, Zhang X M.Diffusion Maps based K-nearest-neighbor Rule Technique for Semiconductor Manufacturing Process Fault Detection[J]. Chemometrics and Intelligent Laboratory Systems (S0169-7439), 2014, 136(15): 47-57.
[5] Yu N, Luo J R.Study on Magneto-Hydro- Dynamics Disturbance Signal Feature Classification Using Improved S-Transform Algorithm and Radial Basis Function Neural Network[J]. Sensors & Transducers (S2306-8515), 2014, 178(9): 219-225.
[6] 毛茗茗. 基于KPCA-FCM的工业过程故障检测与诊断[D]. 北京: 北京化工大学, 2017.
Mao Mingming.KPCA-FCM-based Industrial Process Fault Detection and Diagnosis[D]. Beijing: Beijing University of Chemical Technology, 2017.
[7] 王英赫. 基于模糊聚类的间歇过程故障诊断的研究[D]. 哈尔滨: 哈尔滨理工大学, 2018.
Wang Yinghe.Research on Fault Diagnosis of Batch Process Based on Fuzzy Clustering[D]. Harbin: Harbin University of Science and Technology, 2018.
[8] 张勇, 钟建伟, 周文辉, 等. 基于K-means聚类分析的变压器故障诊断[J]. 湖北民族学院学报(自然科学版), 2018, 36(4): 452-455.
Zhang Yong, Zhong Jianwei, Zhou Wenhui, et al.Transformer Fault Diagnosis based on K-means Cluster Analysis[J]. Journal of Hubei University for Nationalities (Natural Science Edition), 2018, 36(4): 452-455.
[9] 管红立, 李亚芳, 郑文栋, 等. 基于相空间重构理论和k-means聚类算法电弧故障诊断[J]. 电器与能效管理技术, 2017(17): 1-8.
Guan Hongli, Li Yafang, Zheng Wendong, et al.Arc Fault Diagnosis Based on Phase Space Reconstruction Theory and K-means Clustering Algorithm[J]. Electrical Appliance and Energy Efficiency Management Technology, 2017(17): 1-8.
[10] 王晶, 刘莉, 曹柳林, 等. 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, et al.Fault Diagnosis of Batch Process Based on Nuclear Fisher Envelope Analysis[J]. Journal of Chemical Industry and Engineering, 2014, 65(4): 1317-1326.
[11] Jiang Qingchao, Yan Xuefeng.Nonlinear Plant-wide Process Monitoring Using MI-spectral Clustering and Bayesian Inference- based Multiblock KPCA[J]. Journal of Process Control (S0959-1524), 2015, 32(1): 38-50.
[12] Yang X F, Goh A, Qiu A Q.Locally Linear Diffeomorphic Metric Embedding (LLDME) for Surface-based Anatomical Shape Modeling[J]. Neuroimage (S1053-8119), 2011, 56(1): 149-161.
[13] Miao A M, Ge Z Q, Song Z H, et al.Nonlocal Structure Constrained Neighborhood Preserving Embedding Model and Its Application for Fault Detection[J]. Chemometrics and Intelligent Laboratory Systems (S0169-7439), 2015, 142(1): 184-196.
[14] Wang J.Real Local-linearity Preserving Embedding[J]. Neurocomputing (S0925-2312), 2014, 136(20): 7-13.
[15] Li B W, Zhang Y.Supervised Locally Linear Embedding Projection (SLLEP) for Machinery Fault Diagnosis[J]. Mechanical Systems and Signal Processing (S0888-3270), 2011, 25(8): 3125-3134.
[16] 王千, 王成, 冯振元, 等. K-means聚类算法研究综述[J]. 电子设计工程, 2012, 20(7): 21-24.
Wang Qian, Wang Cheng, Feng Zhenyuan, et al.Review of K-means Clustering Algorithm Research[J]. Electronic Design Engineering, 2012, 20(7): 21-24.
[17] 李元, 白岩松. 改进主成分分析的KNN故障检测研究[J]. 沈阳化工大学学报, 2018, 32(4): 366-371.
Li Yuan, Bai Yansong.Research on KNN Fault Detection with Improved Principal Component Analysis[J]. Journal of Shenyang University of Chemical Technology, 2018, 32(4): 366-371.
[18] 郭金玉, 韩建斌, 李元, 等. 基于局部Fisher判别分析的复杂化工过程故障诊断[J]. 计算机应用研究, 2018, 35(4): 1122-1125,1129.
Guo Jinyu, Han Jianbin, Li Yuan, et al.Fault Diagnosis of Complex Chemical Processes based on Local Fisher Discriminant Analysis[J]. Computer Application Research, 2018, 35(4): 1122-1125, 1129.
[19] 张凯林. 基于主元分析和偏最小二乘的TE过程监测方法的研究[D]. 天津: 天津理工大学, 2015.
Zhang Kailin.Research on TE Process Monitoring Method based on Principal Component Analysis and Partial Least Squares[D]. Tianjin: Tianjin University of Technology, 2015.
[20] 张姮. TE过程故障诊断方法比较研究[D]. 沈阳: 沈阳理工大学, 2014.
Zhang Heng.Comparative Study of Fault Diagnosis Methods in TE Process[D]. Shenyang: Shenyang University of Science and Technology, 2014.
[21] 薄翠梅, 韩晓春, 易辉, 等. 基于聚类选择k近邻的LLE算法及故障检测[J]. 化工学报, 2016, 67(3): 925-930.
Bo Cuimei, Han Xiaochun, Yi Hui, et al.LLE Algorithm and Fault Detection Based on Cluster Selection K-nearest Neighbor[J]. Journal of Chemical Industry and Engineering, 2016, 67(3): 925-930.