|Table of Contents|

Industrial process fault classification based on t-distributed random neighborhood embedding algorithm

《南京理工大学学报》(自然科学版)[ISSN:1005-9830/CN:32-1397/N]

Issue:
2020年03期
Page:
332-347
Research Field:
Publishing date:

Info

Title:
Industrial process fault classification based on t-distributed random neighborhood embedding algorithm
Author(s):
Tao Fei1Miao Aimin2Li Peng1Cao Min3Li Wei3
1.School of Information,Yunnan University,Kunming 650500,China; 2.School of Automation,Zhongkai University of Agriculture and Engineering,Guangzhou 510225,China; 3.Electric Power Research Institute,Yunnan Power Grid Co.,Ltd.,Kunming 650217,China
Keywords:
t-distributed random neighborhood embedding industrial process Fisher discriminant analysis support vector machines Tenessee Eastman process kernel principal component analysis Laplace eigenmap
PACS:
TP277
DOI:
10.14177/j.cnki.32-1397n.2020.44.03.011
Abstract:
Aiming at the nonlinear characteristics of data in industrial process,and based on the influence of local correlation of data on classification,a data feature extraction and fault classification method based on t-distributed stochastic neighborhood embedding(t-SNE)is proposed. The method makes full use of the advantages of nonlinear and non-parametric dimension reduction of t-SNE algorithm,and combines with Fisher discriminant analysis(FDA)or support vector machines(SVM)classifier to establish fault classification models. The t-SNE algorithm is used to extract the nonlinear features of the fault data,and the key distinguishing features of the data are obtained. The FDA and SVM algorithms are used to classify and identify faults. The experimental simulation analysis is carried out by Tenessee Eastman(TE)process,and is compared with the KPCA-FDA,LE-FDA,KPCA-SVM,LE-SVM four fault classification based on the kernel principal component analysis(KPCA)and Laplace eigenmap(LE). The quantitative evaluation results show that:even based on different classifiers,compared with the other two methods,the classification accuracy of the proposed method is improved by 2% and 7% respectively,and the average classification accuracy can be maintained above 97%.

References:

[1] 景晨. 基于多分类支持向量机的工业故障分类[D]. 锦州:渤海大学工学院,2016.
[2]Ge Zhiqiang,Liu Yue. Analytic hierarchy process based fuzzy decision fusion system for model prioritization and process monitoring application[J]. IEEE Transactions on Industrial Informatics,2019,15(1),357-365.
[3]Ge Zhiqiang. Distributed predictive modeling frame-work for prediction and diagnosis of key performance index in plant-wide processes[J]. Journal of Process Control,2018,65:107-117.
[4]Zhu Jinlin,Ge Zhiqiang,Song Zhihuan. Distributed parallel PCA for modeling and monitoring of large-scale plant-wide processes with big data[J]. IEEE Transactions on Industrial Informatics,2017,13(4):1877-1885.
[5]高学星,侯保林,孙华刚. 基于FDA和神经网络的弹药协调器故障诊断[J]. 南京理工大学学报,2015,39(6):711-716.
Gao Xuexing,Hou Baolin,Sun Huagang. Fault diagnosis of shell transfer arm based on FDA and neural network[J]. Journal of Nanjing University of Science and Technology,2015,39(6):711-716.
[6]王树彬,韩笑冬,王执铨,等. 基于OPC技术的快速故障诊断实时数据平台设计[J]. 南京理工大学学报,2007,31(6):668-672.
Wang Shubin,Han Xiaodong,Wang Zhiquan,et al. Design of fast fault diagnosis real-time data platform by OPC technology[J]. Journal of Nanjing University of Science and Technology,2007,31(6):668-672.
[7]Miao Aimin,Zhuang Jiajun,Tang Yu,et al. Hyperspectral image-based variety classification of waxy maize seeds by the t-SNE model and Procrustes analysis[J]. Sensors,2018,18(12):4391.
[8]钟世勇. 基于费舍尔判别分析的半监督故障分类方法研究[D]. 杭州:浙江大学控制科学与工程学院,2015.
[9]李巍华,史铁林,杨叔子. 基于非线性判别分析的故障分类方法研究[J]. 振动工程学报,2005,18(2):134-138.
Li Weihua,Shi Tielin,Yang Shuzi. Research on fault classification method based on nonlinear discriminant analysis[J]. Journal of Vibration Engineering,2005,18(2):134-138.
[10]古玉海,韩秋实,徐小力,等. T分布随机近邻嵌入机械故障特征提取方法研究[J]. 机械科学与技术,2016,35(12):1901-1905.
Gu Yuhai,Han Qiushi,Xu Xiaoli,et al. Research on feature extraction method of t-distributed stochastic neighbor embedded mechanical fault[J]. Mechanical Science and Technology,2016,35(12):1901-1905.
[11]梁伟阁,佘博,田福庆. 基于DTCWPT和t-SNE的去燥方法及在故障诊断中的应用[J]. 电子测量,2018,32(5):74-80.
Liang Weige,She Bo,Tian Fuqing. De-drying method based on DTCWPT and t-SNE and its application in fault diagnosis[J]. Electronic Measurement,2018,32(5):74-80.
[12]郑首易,骆德汉,温腾腾,等. t-SNE-LDA算法在仿生嗅觉中的应用研究[J]. 计算机应用研究,2018,35(11):3316-3321.
Zheng Shouyi,Luo Dehan,Wen Tengteng,et al. Application of t-SNE-LDA algorithm in bionic olfaction[J]. Application Research of Computers,2018,35(11):3316-3321.
[13]史东宇,胡文强,李刚,等. 基于t-SNE的电力系统电气距离可视化方法研究[J]. 电力工程技术,2018,37(2):79-81.
Shi Dongyu,Hu Wenqiang,Li Gang,et al. Research on visualization method of electric distance of power system based on t-SNE[J]. Electric Engineering Technology,2018,37(2):79-81.
[14]Laurens V D M,Hinton G. Visualizing data using t-SNE[J]. Journal of Machine Learning Research,2008,9:2579-2605.
[15]Wu Jinlong,Wang Jianxun,Xiao Heng,et al. Visualization of high dimensional turbulence simulation data using t-SNE[C]//Proceedings of the 19th AIAA Non-Deterministic Approaches Conference. Grapevine,TX,USA:AIAA,2017:1-10.
[16]Li Wentian,Cerise J E,Yang Yaning,et al. Application of t-SNE to human genetic data[J]. Bioinf Comput Biol,2017,15:1750017.
[17]Song Weijing,Wang Lizhe,Liu Peng,et al. Improved t-SNE based manifold dimensional reduction for remote sensing data processing[J]. Multimed Tools Appl,2018,3:1-16.
[18]徐森,花小朋,徐静,等. 一种基于T-分布随机近邻嵌入的聚类集成方法[J]. 电子与信息学报,2018,40(6):1317-1322.
Xu Sen,Hua Xiaopeng,Xu Jing,et al. A clustering integration method based on T-distribution stochastic neighbor embedding[J]. Journal of Electronics & Information Technology,2018,40(6):1317-1322.
[19]Downs J J,Vogel E F. A plant-wide industrial process control problem[J]. Computers & Chemical Engineering,1993,17(3):245-255.
[20]GitHub Enterprise. The Fortran 77 codes for the open-loop and the closed-loop simulations for the Tennessee Eastman process(TEP)as well as the training and testing data files used for evaluating the data-driven methods(PCA,PLS,FDA,and CVA)[EB/OL]. https://github.com/camaramm/tennessee-eastman-profBraatz,2020-06-17.
[21]张雨晨. 基于改进的SVM和t-SNE高速列车走行部故障诊断[D]. 成都:西南交通大学信息科学与技术学院,2016.
[22]王雒瑶,高炜欣,王欣. 一种基于SVM及LE降维的X射线焊缝缺陷分类算法研究[J]. 西安石油大学学报(自然科学版),2017,32(5):97-106.
Wang Luoyao,Gao Weixin,Wang Xin. A classification algorithm for X-ray weld defects based on SVM and LE dimensionality reduction[J]. Journal of Xi'an Shiyou University(Natural Science Edition),2017,32(5):97-106.

Memo

Memo:
-
Last Update: 2020-06-30