Identification of abnormal conditions in high-dimensional chemical process based on feature selection and deep learning

doi:10.1016/j.cjche.2020.05.003

中国化学工程学报 ›› 2020, Vol. 28 ›› Issue (7): 1875-1883.DOI: 10.1016/j.cjche.2020.05.003

• Process Systems Engineering and Process Safety • 上一篇下一篇

Identification of abnormal conditions in high-dimensional chemical process based on feature selection and deep learning

Wende Tian¹, Zijian Liu¹, Lening Li², Shifa Zhang¹, Chuankun Li³

1 College of Chemical Engineering, Qingdao University of Science&Technology, Qingdao 266042, China;
2 Qingdao NOVAN Electromechanical Technology, Qingdao 266100, China;
3 State Key Laboratory of Safety and Control for Chemicals, SINOPEC Qingdao Research Institute of Safety Engineering, Qingdao 266071, China

收稿日期:2019-12-20 修回日期:2020-04-02 出版日期:2020-07-28 发布日期:2020-08-31
通讯作者: Wende Tian
基金资助:
Financial support for carrying out this work was provided by the Shandong Provincial Key Research and Development Program (2018YFJH0802).

Identification of abnormal conditions in high-dimensional chemical process based on feature selection and deep learning

Wende Tian¹, Zijian Liu¹, Lening Li², Shifa Zhang¹, Chuankun Li³

1 College of Chemical Engineering, Qingdao University of Science&Technology, Qingdao 266042, China;
2 Qingdao NOVAN Electromechanical Technology, Qingdao 266100, China;
3 State Key Laboratory of Safety and Control for Chemicals, SINOPEC Qingdao Research Institute of Safety Engineering, Qingdao 266071, China

Received:2019-12-20 Revised:2020-04-02 Online:2020-07-28 Published:2020-08-31
Contact: Wende Tian
Supported by:
Financial support for carrying out this work was provided by the Shandong Provincial Key Research and Development Program (2018YFJH0802).

摘要/Abstract

摘要： Identification of abnormal conditions is essential in the chemical process. With the rapid development of artificial intelligence technology, deep learning has attracted a lot of attention as a promising fault identification method in chemical process recently. In the high-dimensional data identification using deep neural networks, problems such as insufficient data and missing data, measurement noise, redundant variables, and high coupling of data are often encountered. To tackle these problems, a feature based deep belief networks (DBN) method is proposed in this paper. First, a generative adversarial network (GAN) is used to reconstruct the random and non-random missing data of chemical process. Second, the feature variables are selected by Spearman's rank correlation coefficient (SRCC) from high-dimensional data to eliminate the noise and redundant variables and, as a consequence, compress data dimension of chemical process. Finally, the feature filtered data is deeply abstracted, learned and tuned by DBN for multi-case fault identification. The application in the Tennessee Eastman (TE) process demonstrates the fast convergence and high accuracy of this proposal in identifying abnormal conditions for chemical process, compared with the traditional fault identification algorithms.

关键词: Chemical process, Deep Belief Networks, Fault identification, Generative Adversarial Networks, Spearman Rank Correlation

Abstract: Identification of abnormal conditions is essential in the chemical process. With the rapid development of artificial intelligence technology, deep learning has attracted a lot of attention as a promising fault identification method in chemical process recently. In the high-dimensional data identification using deep neural networks, problems such as insufficient data and missing data, measurement noise, redundant variables, and high coupling of data are often encountered. To tackle these problems, a feature based deep belief networks (DBN) method is proposed in this paper. First, a generative adversarial network (GAN) is used to reconstruct the random and non-random missing data of chemical process. Second, the feature variables are selected by Spearman's rank correlation coefficient (SRCC) from high-dimensional data to eliminate the noise and redundant variables and, as a consequence, compress data dimension of chemical process. Finally, the feature filtered data is deeply abstracted, learned and tuned by DBN for multi-case fault identification. The application in the Tennessee Eastman (TE) process demonstrates the fast convergence and high accuracy of this proposal in identifying abnormal conditions for chemical process, compared with the traditional fault identification algorithms.

Key words: Chemical process, Deep Belief Networks, Fault identification, Generative Adversarial Networks, Spearman Rank Correlation

Wende Tian, Zijian Liu, Lening Li, Shifa Zhang, Chuankun Li. Identification of abnormal conditions in high-dimensional chemical process based on feature selection and deep learning[J]. 中国化学工程学报, 2020, 28(7): 1875-1883.

参考文献

[1] S. Dash, V. Venkatasubramanian, Challenges in the industrial applications of fault diagnostic systems, Comput. Chem. Eng. 24(2-7) (2000) 785-791.
[2] V. Venkatasubramanian, R. Rengaswamy, S.N. Kavuri, et al., A review of process fault detection and diagnosis:Part III:Process history based methods, Comput. Chem. Eng. 27(3) (2003) 327-346.
[3] Q. Zhu, Y. Jia, D. Peng, et al., Study and application of fault prediction methods with improved reservoir neural networks, Chin. J. Chem. Eng. 22(7) (2014) 812-819.
[4] X. Tang, L. Zhuang, J. Cai, et al., Multi-fault classification based on support vector machine trained by chaos particle swarm optimization, Knowl.-Based Syst. 23(5) (2010) 486-490.
[5] Peng Xu, Du. Rui, Predicting pipeline leakage in petrochemical system through GAN and LSTM, Knowl.-Based Syst. 175(2019) 50-61.
[6] Z. Ge, C. Yang, Z. Song, Improved kernel PCA-based monitoring approach for nonlinear processes, Chem. Eng. Sci. 64(9) (2009) 2245-2255.
[7] T. Rato, M. Reis, E. Schmitt, et al., A systematic comparison of PCA-based statistical process monitoring methods for high-dimensional, time-dependent processes, AIChE J. 62(5) (2016) 1478-1493.
[8] J. Fan, Y. Wang, Fault detection and diagnosis of non-linear non-Gaussian dynamic processes using kernel dynamic independent component analysis, Inf. Sci. 259(2014) 369-379.
[9] N. Zhong, X. Deng, Multimode non-Gaussian process monitoring based on local entropy independent component analysis, Can. J. Chem. Eng. 95(2) (2017) 319-330.
[10] Y. Zhou, K. Wu, Z. Meng, et al., Fault detection of aircraft based on support vector domain description, Computers & Electrical Engineering 61(2017) 80-94.
[11] P. Tang, T.W.S. Chow, Wireless sensor-networks conditions monitoring and fault diagnosis using neighborhood hidden conditional random field, IEEE Transactions on Industrial Informatics 12(3) (2016) 933-940.
[12] Y. Tian, W. Du, F. Qian, High dimension feature extraction based visualized SOM fault diagnosis method and its application in p-xylene oxidation process, Chin. J. Chem. Eng. 23(9) (2015) 1509-1517.
[13] G.E. Hinton, R.R. Salakhutdinov, Reducing the dimensionality of data with neural networks, Science 313(5786) (2006) 504-507.
[14] Y. LeCun, Y. Bengio, G. Hinton, Deep learning, Nature 521(7553) (2015) 436.
[15] A. Krizhevsky, I. Sutskever, G.E. Hinton, Imagenet Classification with Deep Convolutional Neural Networks Advances, in:Neural Information Processing Systems, 2012, 1097-1105.
[16] D. Silver, A. Huang, C.J. Maddison, et al., Mastering the game of Go with deep neural networks and tree search, Nature 529(7587) (2016) 484.
[17] P. Tamilselvan, P. Wang, Failure diagnosis using deep belief learning based health state classification, Reliability Engineering & System Safety 115(2013) 124-135.
[18] F. AlThobiani, A. Ball, An approach to fault diagnosis of reciprocating compressor valves using Teager-Kaiser energy operator and deep belief networks, Expert Syst. Appl. 41(9) (2014) 4113-4122.
[19] J. Sun, R. Wyss, A. Steinecker, et al., Automated fault detection using deep belief networks for the quality inspection of electromotors, Tm-Technisches Messen 81(5) (2014) 255-263.
[20] L. Luo, H. Su, L. Ban, Independent component analysis-based sparse autoencoder in the application of fault diagnosis,In:Proceeding of the 11th World Congress on Intelligent Control and Automation, IEEE (2014) 1378-1382.
[21] S.M. Erfani, S. Rajasegarar, S. Karunasekera, et al., High-dimensional and large-scale anomaly detection using a linear one-class SVM with deep learning, Pattern Recogn. 58(2016) 121-134.
[22] Z. Zhang, J. Zhao, A deep belief network based fault diagnosis model for complex chemical processes, Comput. Chem. Eng. 107(2017) 395-407.
[23] Y. Bengio, P. Lamblin, D. Popovici, et al., Greedy Layer-wise Training of Deep Networks, In:Advances in Neural Information Processing Systems, 2007, 153-160.
[24] Y. Wang, Z. Pan, X. Yuan, et al., A novel deep learning based fault diagnosis approach for chemical process with extended deep belief network, ISA Trans. 96(2019) 457-467.
[25] I. Goodfellow, J. Pouget-Abadie, M. Mirza, et al., Generative Adversarial Nets, In:Advances in Neural Information Processing Systems, 2014, 2672-2680.
[26] Z. Guo, Y. Wan, H. Ye, A data imputation method for multivariate time series based on generative adversarial network, Neurocomputing 360(2019) 185-197.
[27] R. He, X. Li, G. Chen, et al., Generative adversarial network-based semi-supervised learning for real-time risk warning of process industries, Expert Syst. Appl. 150(2020) 113244.
[28] K. Ghosh, M. Ramteke, R. Srinivasan, Optimal variable selection for effective statistical process monitoring, Comput. Chem. Eng. 60(2014) 260-276.
[29] W.Y. Zhang, Z.W. Wei, B.H. Wang, et al., Measuring mixing patterns in complex networks by Spearman rank correlation coefficient, Physica A:Statistical Mechanics and Its Applications 451(2016) 440-450.
[30] J.J. Downs, E.F. Vogel, A plant-wide industrial process control problem, Comput. Chem. Eng. 17(3) (1993) 245-255.
[31] C. Jing, J. Hou, SVM and PCA based fault classification approaches for complicated industrial process, Neurocomputing 167(2015) 636-642.
[32] M.F.S.V. D'Angelo, R.M. Palhares, M.C.O. Camargos Filho, et al., A new fault classification approach applied to Tennessee Eastman benchmark process, Appl. Soft Comput. 49(2016) 676-686.
[33] H. WuC, J. Zhao, Deep convolutional neural network model based chemical process fault diagnosis, Comput. Chem. Eng. 115(2018) 185-197.

Identification of abnormal conditions in high-dimensional chemical process based on feature selection and deep learning

Identification of abnormal conditions in high-dimensional chemical process based on feature selection and deep learning

PDF (PC)

可视化

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]	Xiongzhuo Zhu, Dali Gao, Chong Yang, Chunjie Yang. A blast furnace fault monitoring algorithm with low false alarm rate: Ensemble of greedy dynamic principal component analysis-Gaussian mixture model[J]. 中国化学工程学报, 2023, 57(5): 151-161.
[2]	Shuangfei Zhao, Yingying Nie, Wenyan Zhang, Runze Hu, Lianzhu Sheng, Wei He, Ning Zhu, Yuguang Li, Dong Ji, Kai Guo. Microfluidic field strategy for enhancement and scale up of liquid–liquid homogeneous chemical processes by optimization of 3D spiral baffle structure[J]. 中国化学工程学报, 2023, 56(4): 255-265.
[3]	Qingming Ma, Jianhong Xu. Green microfluidics in microchemical engineering for carbon neutrality[J]. 中国化学工程学报, 2023, 53(1): 332-345.
[4]	Minjie Shi, Hangtian Zhu, Cheng Yang, Jing Xu, Chao Yan. Chemical reduction-induced fabrication of graphene hybrid fibers for energy-dense wire-shaped supercapacitors[J]. 中国化学工程学报, 2022, 47(7): 1-10.
[5]	Ruoshi Qin, Jinsong Zhao. Adaptive multiscale convolutional neural network model for chemical process fault diagnosis[J]. 中国化学工程学报, 2022, 50(10): 398-411.
[6]	Yanqiang Shi, Yuetong Xia, Guangtong Xu, Langyou Wen, Guohua Gao, Baoning Zong. Hydrogen peroxide and applications in green hydrocarbon nitridation and oxidation[J]. 中国化学工程学报, 2022, 41(1): 145-161.
[7]	Yuyang Kang, Yiqing Luo, Xigang Yuan. Recent progress on equation-oriented optimization of complex chemical processes[J]. 中国化学工程学报, 2022, 41(1): 162-169.
[8]	Xifan Duan, Zhiguo Yuan, Youzhi Liu, Hangtian Li, Weizhou Jiao. Numerical simulation and experimental study of the characteristics of packing feature size on liquid flow in a rotating packed bed[J]. 中国化学工程学报, 2021, 34(6): 22-31.
[9]	Zhen Wang, Aimin An, Qianrong Li. Distributed model predictive control based on adaptive sampling mechanism[J]. 中国化学工程学报, 2021, 39(11): 193-204.
[10]	Muhammad Nawaz, Abdulhalim Shah Maulud, Haslinda Zabiri, Syed Ali Ammar Taqvi, Alamin Idris. Improved process monitoring using the CUSUM and EWMA-based multiscale PCA fault detection framework[J]. 中国化学工程学报, 2021, 29(1): 253-265.
[11]	Junjie Feng, Bin Zhang, Wei Xu, Bing Sun, Fan Zhang, Jie Jiang. Development of index system for inherently safer process design using an integrated approach[J]. 中国化学工程学报, 2019, 27(11): 2725-2733.
[12]	Kaixun He, Kai Wang, Yayun Yan. Active training sample selection and updating strategy for near-infrared model with an industrial application[J]. 中国化学工程学报, 2019, 27(11): 2749-2758.
[13]	Wende Tian, Guixin Zhang, Xiang Zhang, Yuxi Dong. PCA weight and Johnson transformation based alarm threshold optimization in chemical processes[J]. Chinese Journal of Chemical Engineering, 2018, 26(8): 1653-1661.
[14]	Tao Yang, Yiqing Luo, Yingjie Ma, Xigang Yuan. Optimal synthesis of compression refrigeration system using a novel MINLP approach[J]. Chinese Journal of Chemical Engineering, 2018, 26(8): 1662-1669.
[15]	Guozhu Wang, Jianchang Liu, Yuan Li, Cheng Zhang. Fault diagnosis of chemical processes based on partitioning PCA and variable reasoning strategy[J]. , 2016, 24(7): 869-880.