Fault Detection Algorithm Based on Dynamic Global–Local Preserving Projection
Source abstract
Abstract
Industrial system operations usually have dynamic characteristics. If these characteristics are ignored, the performance of fault detection degrades. Herein, the fault-detection algorithm of dynamic global–local preserving projection (DGLPP) is employed to solve the problem mentioned. First, time-delay data are added to the sample to form an augmentation matrix and characterize the system dynamics. Second, the dimensionality of the augmented matrix is reduced using global–local preserving projection. The dimensionality-reduction method can preserve the data’s global and local structures. Then, a DGLPP model is built using the dimensionality-reduced data. Moreover, Hotelling’s T2 and squared prediction error (SPE) statistics are used for fault detection. Finally, this method is used to detect the fault in the Tennessee Eastman (TE) process. The experimental results show that the DGLPP method has an enhanced fault detection rate. Moreover, the fault-detection effects of the DGLPP method are better than those of the principal component analysis (PCA), local preserving projection (LPP), and global–local preserving projection (GLPP) methods.
Source: crossref · Quality: baseline
Research context
OpenAlex topics: Fault Detection and Control Systems · Spectroscopy and Chemometric Analyses · Mineral Processing and Grinding
SciVX discovery tags are terminology-based. OpenAlex topics are source-provided classifications.
Affiliations
College of Marine Electrical Engineering, Dalian Maritime University, Dalian 116026, China
Funding
National Natural Science Foundation of China
References (40)
Show source-provided references
1. Fault detection and diagnosis of large-scale HVAC systems in buildings using data-driven methods: A comprehensive review10.1016/j.enbuild.2020.110492 ↗
2. Review on data-driven modeling and monitoring for plant-wide industrial processes10.1016/j.chemolab.2017.09.021 ↗
3. Reis, M.S., and Gins, G. (2017). Industrial process monitoring in the big data/industry 4.0 era: From detection, to diagnosis, to prognosis. Processes, 5.10.3390/pr5030035 ↗
4. Overview on hybrid approaches to fault detection and diagnosis: Combining data-driven, physics-based and knowledge-based models10.1016/j.procir.2021.03.041 ↗
5. Data-driven models of crude distillation units for production planning and for operations monitoring10.1016/j.compchemeng.2023.108322 ↗
6. Using thermal load matching strategy to locate historical benchmark data for moving-window PCA based fault detection in air handling units
7. Fault detection and classification in kinematic chains by means of PCA extraction-reduction of features from thermographic images10.1016/j.measurement.2022.111340 ↗
8. Fault detection for NOx emission process in thermal power plants using SIP-PCA10.1016/j.isatra.2023.06.004 ↗
9. Batch process monitoring based on multiple-phase online sorting principal component analysis10.1016/j.isatra.2016.04.022 ↗
10. Fault diagnosis and classification framework using multi-scale classification based on kernel Fisher discriminant analysis for chemical process system10.1016/j.asoc.2017.09.019 ↗
11. Performance monitoring method based on balanced partial least square and statistics pattern analysis10.1016/j.isatra.2018.07.038 ↗
12. Fault detection of uncertain chemical processes using interval partial least squares-based generalized likelihood ratio test10.1016/j.ins.2019.03.068 ↗
13. Online reduced kernel PLS combined with GLRT for fault detection in chemical systems10.1016/j.psep.2019.05.018 ↗
14. Combined classification models for bearing fault diagnosis with improved ICA and MFCC feature set10.1016/j.advengsoft.2022.103249 ↗
15. Enhanced chiller faults detection and isolation method based on independent component analysis and k-nearest neighbors classifier10.1016/j.buildenv.2022.109010 ↗
16. An independent component analysis based correlation coefficient method for internal short-circuit fault diagnosis of battery-powered intelligent transportation systems10.1016/j.conengprac.2023.105606 ↗
17. Improved PCA model for multiple fault detection, isolation and reconstruction of sensors in nuclear power plant10.1016/j.anucene.2020.107662 ↗
18. Modified LPP based on Riemannian metric for feature extraction and fault detection10.1016/j.measurement.2022.110923 ↗
19. Improved key performance indicator-partial least squares method for nonlinear process fault detection based on just-in-time learning10.1016/j.jfranklin.2022.11.029 ↗
20. Incipient fault detection and diagnosis of nonlinear industrial process with missing data10.1016/j.jtice.2021.10.015 ↗
21. Fault detection and quantitative assessment method for process industry based on feature fusion10.1016/j.measurement.2022.111267 ↗
22. A modified neighborhood preserving embedding-based incipient fault detection with applications to small-scale cyber–physical systems10.1016/j.isatra.2019.08.022 ↗
23. Global–local structure analysis model and its application for fault detection and identification10.1021/ie102564d ↗
24. Local and global principal component analysis for process monitoring10.1016/j.jprocont.2012.06.008 ↗
25. Process monitoring with global-local preserving projections10.1021/ie4039345 ↗
26. Nonlocal and local structure preserving projection and its application to fault detection10.1016/j.chemolab.2016.07.014 ↗
27. Fault detection via local and nonlocal embedding10.1016/j.cherd.2014.09.015 ↗
28. Industrial process monitoring based on Fisher discriminant global-local preserving projection10.1016/j.jprocont.2019.05.010 ↗
29. Disturbance detection and isolation by dynamic principal component analysis10.1016/0169-7439(95)00076-3 ↗
30. Fault detection and diagnosis based on residual dissimilarity in dynamic principal component analysis
31. Fault detection for chemical process based on nonlinear dynamic global-local preserving projections
32. Neighborhood preserving embedding based on temporal extension and its application in fault detection
33. Complex multi-stage process fault detection based on TSNS and KNN rules
34. Sensitivity analysis of scalable data on three PCA related fault detection methods considering data window and thermal load matching strategies10.1016/j.eswa.2023.121024 ↗
35. Improved deep PCA and Kullback–Leibler divergence based incipient fault detection and isolation of high-speed railway traction devices
36. Improved process monitoring using the CUSUM and EWMA-based multiscale PCA fault detection framework10.1016/j.cjche.2020.08.035 ↗
37. Fault feature extraction method for rotating machinery based on a CEEMDAN-LPP algorithm and synthetic maximum index10.1016/j.measurement.2021.110636 ↗
38. Non-convex logarithm embedding subspace weighted graph approach to fault detection with missing measurements10.1016/j.neucom.2021.12.065 ↗
39. Plant-wide control of the Tennessee Eastman problem10.1016/0098-1354(94)00057-U ↗
40. A plant-wide industrial process control problem10.1016/0098-1354(93)80018-I ↗