Batch Process Fault Diagnosis Method Based on KECA-IGWO-KELM

ZHANG Min; WANG Ruiqi; ZHANG Xunjie

doi:10.13976/j.cnki.xk.2021.0327

Volume 50 Issue 3

Jun. 2021

Turn off MathJax

Article Contents

Abstract

References

INFORMATION AND CONTROL > 2021 > 50(3): 321-328. > DOI: 10.13976/j.cnki.xk.2021.0327 CSTR: 32166.14.xk.2021.0327

ZHANG Min, WANG Ruiqi, ZHANG Xunjie. Batch Process Fault Diagnosis Method Based on KECA-IGWO-KELM[J]. INFORMATION AND CONTROL, 2021, 50(3): 321-328. DOI: 10.13976/j.cnki.xk.2021.0327

Citation:

ZHANG Min, WANG Ruiqi, ZHANG Xunjie. Batch Process Fault Diagnosis Method Based on KECA-IGWO-KELM[J]. INFORMATION AND CONTROL, 2021, 50(3): 321-328. DOI: 10.13976/j.cnki.xk.2021.0327

Citation:

ZHANG Min, WANG Ruiqi, ZHANG Xunjie. Batch Process Fault Diagnosis Method Based on KECA-IGWO-KELM[J]. INFORMATION AND CONTROL, 2021, 50(3): 321-328. DOI: 10.13976/j.cnki.xk.2021.0327

PDF (2089 KB)

Batch Process Fault Diagnosis Method Based on KECA-IGWO-KELM

1.
School of Mechanical Engineering, Southwest Jiaotong University, Chengdu 610031, China
2.
Technology and Equipment of Rail Transit Operation and Maintenance Key Laboratory of Sichuan Province, Chengdu 610031, China

More Information

Received Date: July 13, 2020
Revised Date: December 20, 2020
Accepted Date: November 16, 2020
Available Online: December 01, 2022
Published Date: June 19, 2021

Graphical Abstract

Abstract

Abstract

In view of the multistage, strong coupling, and nonlinearity of batch process data, we propose a fault diagnosis method for the batch process based on kernel entropy component analysis (KECA), improved gray wolf optimization, and the kernel extreme learning machine (KELM). Considering the multistage nature of batch process data, the K-means algorithm is used to cluster these data, and the whole process period is divided into several sub-periods. Based on the strong coupling and nonlinearity of batch process data, we introduce the KECA algorithm to extract the features of the original fault data and obtain their deep features. Using KELM as a classifier and the improved gray wolf algorithm, which improves the initialization strategy and convergence factor, the parameters of the classifier are intelligently optimized and the optimal classifier is obtained by diagnosing the faults of each period of the batch process. We verified the feasibility and superiority of this method based on the results of a simulation experiment and a contrast experiment with penicillin.

FullText(HTML)

References (24)

References

[1]	赵小强, 周文伟. 基于MAGMM-KECA的间歇过程故障诊断方法[J]. 兰州理工大学学报, 2018, 44(4): 76-83. doi: 10.3969/j.issn.1673-5196.2018.04.014 Zhao X Q, Zhou W W. Fault diagnosis method for batch process based on MAGMM-KECA[J]. Journal of Lanzhou University of Technology, 2018, 44(4): 76-83. doi: 10.3969/j.issn.1673-5196.2018.04.014
[2]	Peng C, Wei L R, Kang O, et al. Batch process fault detection for multi-stage broad learning system[J]. Neural Networks, 2020, 129, 298-312. doi: 10.1016/j.neunet.2020.05.031
[3]	Onel M, Kieslich C, Guzman Y, et al. Big data approach to batch process monitoring: Simultaneous fault detection and diagnosis using nonlinear support vector machine-based feature selection[J]. Computers & Chemical Engineering, 2018, 115(7): 46-63. http://www.ncbi.nlm.nih.gov/pubmed/30386002
[4]	吕宁, 颜鲁齐, 白光远. 分段多向核主元分析的啤酒发酵过程故障检测[J]. 计算机科学, 2016, 43(1): 25-27. https://www.cnki.com.cn/Article/CJFDTOTAL-JSJA2016S1006.htm LÜ N, Yan L Q, Bai G Y. Fault detection for beer fermentation process based on segmentation multiway kernel principal component analysis[J]. Computer Science, 2016, 43(1): 25-27. https://www.cnki.com.cn/Article/CJFDTOTAL-JSJA2016S1006.htm
[5]	邓晓刚, 张琛琛, 王磊. 基于多阶段多向核熵成分分析的间歇过程故障检测方法[J]. 化工学报, 2017, 68(5): 1961-1968. https://www.cnki.com.cn/Article/CJFDTOTAL-HGSZ201705027.htm Deng X G, Zhang C C, Wang L. Fault detection in batch process by multistage multiway kernel entropy component analysis[J]. CIESC Journal, 2017, 68(5): 1961-1968. https://www.cnki.com.cn/Article/CJFDTOTAL-HGSZ201705027.htm
[6]	Yi H, Ma H, Shi H. Enhanced batch process monitoring using just-in-time-learning based kernel partial least squares[J]. Chemometrics & Intelligent Laboratory Systems, 2013, 123(3): 15-27. http://www.sciencedirect.com/science/article/pii/S0169743913000312
[7]	Zhang M, Cheng W. Recognition of mixture control chart pattern using multi-class support vector machine and genetic algorithm based on statistical and shape features[J]. Mathematical Problems in Engineering, 2015, 2015(19): 1-10. http://www.researchgate.net/publication/282890645_Recognition_of_Mixture_Control_Chart_Pattern_Using_Multiclass_Support_Vector_Machine_and_Genetic_Algorithm_Based_on_Statistical_and_Shape_Features/download
[8]	Scholkopf B, Smola A, Muller K. Nonlinear component analysis as a kernel eigenvalue problem[J]. Neural Computation, 1998, 10(5): 1299-1319. doi: 10.1162/089976698300017467
[9]	Jenssen R. Kernel entropy component analysis[J]. IEEE Transactions on Pattern Analysis and Machine Intelligence, 2010, 32(5): 847-860. doi: 10.1109/TPAMI.2009.100
[10]	Zhang H, Qi Y, Wang L, et al. Fault detection and diagnosis of chemical process using enhanced KECA[J]. Chemometrics and Intelligent Laboratory Systems, 2017, 161: 61-69. doi: 10.1016/j.chemolab.2016.12.013
[11]	Bo C, Qiao X, Zhang G, et al. ICA-SVM based fault diagnosis method for complex chemical process[J]. Journal of Chemical Industry and Engineering, 2009, 60(9): 2259-2264. http://en.cnki.com.cn/Article_en/CJFDTOTAL-HGSZ200909021.htm
[12]	张雷, 张小刚, 陈华. 基于Gath-Geva算法和核极限学习机的多阶段间歇过程软测量[J]. 化工学报, 2018, 69(6): 2576-2585. https://www.cnki.com.cn/Article/CJFDTOTAL-HGSZ201806030.htm Zhang L, Zhang X G, Chen H. Soft sensors for multi-stage batch processes based on Gath-Geva algorithm and kernel extreme learning machine[J]. CIESC Journal, 2018, 69(6): 2576-2585. https://www.cnki.com.cn/Article/CJFDTOTAL-HGSZ201806030.htm
[13]	Lu S, Yu H, Dong H, et al. Single-step prediction method of burning zone temperature based on real-time wavelet filtering and KELM[J]. Engineering Applications of Artificial Intelligence, 2018, 70: 142-148. doi: 10.1016/j.engappai.2018.01.010
[14]	李军, 李大超. 基于CEEMDAN-FE-KELM方法的短期风电功率预测[J]. 信息与控制, 2016, 45(2): 135-141. doi: 10.13976/j.cnki.xk.2016.0135 Li J, Li D C. Short-term wind power forecasting based on CEEMDAN-FE-KELM method[J]. Information and Control, 2016, 45(2): 135-141. doi: 10.13976/j.cnki.xk.2016.0135
[15]	章勇高, 高彦丽, 马迪. 基于GA-KELM的光伏短期出力预测研究[J]. 控制工程, 2018, 25(7): 1155-1159. https://www.cnki.com.cn/Article/CJFDTOTAL-JZDF201807003.htm Zhang Y G, Gao Y L, Ma D. Research of photo-voltaic short-term output power prediction based on GA-KELM[J]. Control Engineering of China, 2018, 25(7): 1155-1159. https://www.cnki.com.cn/Article/CJFDTOTAL-JZDF201807003.htm
[16]	涂异, 汪金能, 朱曲平, 等. 应用PSO-KELM模型预测水文时间序列[J]. 中国农村水利水电, 2018, (7): 21-24. doi: 10.3969/j.issn.1007-2284.2018.07.005 Tu Y, Wang J N, Zhu Q, et al. Research on the prediction of hydrological time series based on PSO-KELM model[J]. China Rural Water and Hydropower, 2018, (7): 21-24. doi: 10.3969/j.issn.1007-2284.2018.07.005
[17]	Abdelshafy A M, Hamdy H, Jakub J. Optimal design of a grid-connected desalination plant powered by renewable energy resources using a hybrid PSO-GWO approach[J]. Energy Conversion and Management, 2018, 173(10): 331-347. http://www.sciencedirect.com/science/article/pii/S0196890418308185
[18]	胡亚红, 方豪达, 江大川, 等. 基于AHP和k-means算法的电力用户信用度评价[J]. 浙江工业大学学报, 2018, 46(5): 515-521. doi: 10.3969/j.issn.1006-4303.2018.05.008 Hu Y H, Fang H D, Jing D C, et al. Credit evaluation of power consumers based on AHP and k-means algorithms[J]. Journal of Zhejiang University of Technology, 2018, 46(5): 515-521. doi: 10.3969/j.issn.1006-4303.2018.05.008
[19]	Huang G B. An insight into extreme learning machine: Random neurons, random features and kernels[J]. Congnitive Computation, 2014, 6(3): 376-390. doi: 10.1007/s12559-014-9255-2
[20]	Mirjalili S, Mirjalili S M, Lewis A. Grey wolf optimizer[J]. Advances in Engineering Software, 2014, 69: 46-61. doi: 10.1016/j.advengsoft.2013.12.007
[21]	张新明, 王霞, 康强. 改进的灰狼优化算法及其高维函数和FCM优化[J]. 控制与决策, 2019, 34(10): 2073-2084. https://www.cnki.com.cn/Article/CJFDTOTAL-KZYC201910004.htm Zhang X M, Wang X, Kang Q. Improved grey wolf optimizer and its application to high-dimensional function and FCM optimization[J]. Control and Decision, 2019, 34(10): 2073-2084. https://www.cnki.com.cn/Article/CJFDTOTAL-KZYC201910004.htm
[22]	龙文, 伍铁斌. 协调探索和开发能力的改进灰狼优化算法[J]. 控制与决策, 2017, 32(10): 1749-1757. https://www.cnki.com.cn/Article/CJFDTOTAL-KZYC201710003.htm Long W, Wu T B. Improved grey wolf optimization algorithm coordinating the ability of exploration and exploitation[J]. Control and Decision, 2017, 32(10): 1749-1757. https://www.cnki.com.cn/Article/CJFDTOTAL-KZYC201710003.htm
[23]	张海南, 游晓明, 刘升. 动态进化与交互学习机制融合的蚁群算法[J]. 信息与控制, 2020, 49(3): 297-305. doi: 10.13976/j.cnki.xk.2020.9322 Zhang H N, You X M, Liu S. Ant colony algorithm based on dynamic evolution and interactive learning mechanism[J]. Information and Control, 2020, 49(3): 297-305. doi: 10.13976/j.cnki.xk.2020.9322
[24]	蔡振宇, 张敏, 包珊珊. 基KECA和FWA-SVM的间歇过程分时段故障诊断方法[J]. 计算机应用研究, 2019, 36(5): 1409-1414. https://www.cnki.com.cn/Article/CJFDTOTAL-JSYJ201905029.htm Cai Z Y, Zhang M, Bao S S. Time division fault diagnosis method based on KECA and FWA-SVM for batch process[J]. Application Research of Computers, 2019, 36(5): 1409-1414. https://www.cnki.com.cn/Article/CJFDTOTAL-JSYJ201905029.htm