Although the model based on an autoencoder (AE) exhibits strong feature extraction capability without data labeling, such model is less likely to consider the structural distribution of the original data and the extracted feature is uninterpretable. In this study, a new stacked sparse AE (SSAE) based on the preservation of local and global feature structures is proposed for fault detection. Two additional loss terms are included in the loss function of SSAE to retain the local and global structures of the original data. The preservation of the local feature considers the nearest neighbor of data in space, while that of the global feature considers the variance information of data. The final feature is not only a deep representation of data, but it also retains structural information as much as possible. The proposed model demonstrates remarkable detection performance in case studies of a numerical process and the Tennessee Eastman process.
BounouaWBenkaraABKouadriA, et al. (2020) Online monitoring scheme using principal component analysis through Kullback-Leibler divergence analysis technique for fault detection. Transactions of the Institute of Measurement & Control42(6): 1225–1238.
2.
ChenSYuJWangS (2020) One-dimensional convolutional auto-encoder-based feature learning for fault diagnosis of multivariate processes. Journal of Process Control87: 54–67.
3.
DengZLiYZhuH, et al. (2020) Sparse stacked autoencoder network for complex system monitoring with industrial applications. Chaos, Solitons & Fractals137: 109838.
4.
DownsJJVogelEF (1993) A plant-wide industrial process control problem. Computers and Chemical Engineering17(3): 245–255.
5.
FuYLuoCBiZ (2021) Low-rank joint embedding and its application for robust process monitoring. IEEE Transactions on Instrumentation and Measurement70: 1–13.
6.
GeZ (2017) Review on data-driven modeling and monitoring for plant-wide industrial processes. Chemometrics and Intelligent Laboratory Systems171: 16–25.
7.
GuoRZhangN (2020) A process monitoring scheme for uneven-duration batch process based on sequential moving principal component analysis. IEEE Transactions on Control Systems Technology28(2): 583–592.
8.
HintonGESalakhutdinovRR (2006) Reducing the dimensionality of data with neural networks. Science313(5786): 504–507.
9.
HuiYZhaoX (2020) Sparse representation preserving embedding based on extreme learning machine for process monitoring. Transactions of the Institute of Measurement and Control42(10): 1895–1907.
10.
JiangQYanX (2013) Non-Gaussian chemical process monitoring with adaptively weighted independent component analysis and its applications. Journal of Process Control23(9): 1320–1331.
11.
JiangQYanXTongC (2013) Double-weighted independent component analysis for non-gaussian chemical process monitoring. Industrial & Engineering Chemistry Research52(40): 14396–14405.
12.
KongDYanX (2020) Adaptive parameter tuning stacked autoencoders for process monitoring. Soft Computing24(17): 12937–12951.
13.
KullbackSLeiblerRA (1951) On information and sufficiency. The Annals of Mathematical Statistics22(1): 79–86.
14.
LeeJHShinJRealffMJ (2018) Machine learning: Overview of the recent progresses and implications for the process systems engineering field. Computers & Chemical Engineering114: 111–121.
15.
LiWLiHGuS, et al. (2020a) Process fault diagnosis with model- and knowledge-based approaches: Advances and opportunities. Control Engineering Practice105: 104637.
16.
LiYFengC (2020) A nonlinear method for monitoring industrial process. Transactions of the Institute of Measurement and Control. 43(2): 400–411.
17.
LiYLekamalageCKLLiuT, et al. (2020b) Learning representations with local and global geometries preserved for machine fault diagnosis. IEEE Transactions on Industrial Electronics67(3): 2360–2370.
18.
McAvoyTJYeN (1994) Base control for the Tennessee Eastman problem. Computers and Chemical Engineering18(5): 383–413.
19.
MarcosQ-GAlbertoP-MCristinaV, et al. (2019) Data-driven monitoring of multimode continuous processes: A review. Chemometrics & Intelligent Laboratory Systems189: 56–71.
20.
RobertoMSErickGSNUbatanAM, et al. (2020) Deep learning for diagnosis and classification of faults in industrial rotating machinery. Computers & Industrial Engineering153: 107060.
21.
RumelhartDEHintonGEWilliamsRJ (1986) Learning representations by back-propagating errors. Nature323(6088): 533–536.
22.
TianWRenYDongY, et al. (2019) Fault monitoring based on mutual information feature engineering modeling in chemical process. Chinese Journal of Chemical Engineering27(10): 2491–2497.
23.
WangYSiYLouZ, et al. (2018) Survey on the theoretical research and engineering applications of multivariate statistics process monitoring algorithms: 2008–2017. Canadian Journal of Chemical Engineering96(10): 2073–2085.
24.
WuJTangZLvF, et al. (2018) Ultrasonic guided wave-based switch rail monitoring using independent component analysis. Measurement Science & Technology29(11): 1.
25.
WuPLouSZhangX, et al. (2020) Data-driven fault diagnosis using deep canonical variate analysis and Fisher discriminant analysis. IEEE Transactions on Industrial Informatics 17(5): 3324–3334
26.
YangQLiuTWuX, et al. (2020) A planetary gear reducer backlash identification based on servo motor current signal and optimized fisher discriminant analysis. ISA Transactions 112: 350–362.
27.
YuJYanX (2018) Layer-by-layer enhancement strategy of favorable features of the deep belief network for industrial process monitoring. Industrial & Engineering Chemistry Research57(45): 15479–15490.
28.
ZengJLuoXLiangJ (2018) Online process monitoring using recursive mutual information-based variable selection and dissimilarity analysis with no prior information. IEEE Access6: 58662–58672.
29.
ZhangMGeZSongZ, et al. (2011) Global–local structure analysis model and its application for fault detection and identification. Industrial and Engineering Chemistry Research50(11): 6837–6848.
30.
ZhangZJiangTLiS, et al. (2018) Automated feature learning for nonlinear process monitoring – An approach using stacked denoising autoencoder and k-nearest neighbor rule. Journal of Process Control64: 49–61.
31.
ZhaoXJiaMDingP, et al. (2020) Intelligent fault diagnosis of multichannel motor–rotor system based on multimanifold deep extreme learning machine. IEEE/ASME Transactions on Mechatronics25(5): 2177–2187.
32.
ZhouFYangSFujitaH, et al. (2020) Deep learning fault diagnosis method based on global optimization GAN for unbalanced data. Knowledge-Based Systems187: 104837.
33.
ZhouJLRenYWWangJ (2019) Quality-relevant fault monitoring based on locally linear embedding orthogonal projection to latent structure. Industrial and Engineering Chemistry Research58(3): 1262–1272.
