Nonlinear process monitoring based on linear subspace and Bayesian inference

Ge, Zhiqiang; Zhang, Muguang; Song, Zhihuan

doi:10.1016/j.jprocont.2010.03.003

Cited by 153 publications

(120 citation statements)

References 24 publications

Supporting

Mentioning

119

Contrasting

Unclassified

Order By: Relevance

“…To provide an intuitionistic indication of the process status, the statistics can be combined with a global statistic. The Bayesian inference strategy by Ge et al [66] is used in the current study for statistics combination. In Bayesian inference statistics combination, the conditional fault probability of x b concerning T 2 is calculated as [66] The conditional probabilities p T 2 (x b |N) and p T 2 (x b |F) are defined as (22) where N and F represent normal and abnormal conditions, respectively; when the significance level is determined as ˛, p T 2 (N) and p T 2 (F) is defined as 1 − ˛ and ˛, respectively; T 2 b,new is the T 2 statistic of the current sample in the bth sub-block; and T 2 b,lim is the confidence limit of the T 2 statistics in the bth sub-block obtained by KDE.…”

Section: Multiblock Kpca For Process Monitoringmentioning

confidence: 99%

“…More details on the Bayesian inference can found in Refs. [66,67]. It is worth mentioning that the when the T 2 and Q are used for monitoring, a fault would be detected if either of the two statistics violates the threshold.…”

Section: Multiblock Kpca For Process Monitoringmentioning

confidence: 99%

“…The missed detection rates for each fault in the TE process using GPCA [4,12], GKPCA [35], and BSPCA by Ge et al [66], DPCA by Ge et al [27], FSCB by Tong et al [40], MSMBPCA, and MSMBKPCA are summarized in Table 1. Faults 3, 9 and 15 are not used for comparison because there is no observable change in the mean or the variance compared with the normal condition.…”

Section: Case Study On the Te Benchmark Processmentioning

confidence: 99%

See 2 more Smart Citations

Nonlinear plant-wide process monitoring using MI-spectral clustering and Bayesian inference-based multiblock KPCA

Jiang

Yan

2015

Journal of Process Control

View full text Add to dashboard Cite

Section: Multiblock Kpca For Process Monitoringmentioning

confidence: 99%

Section: Multiblock Kpca For Process Monitoringmentioning

confidence: 99%

Section: Case Study On the Te Benchmark Processmentioning

confidence: 99%

See 1 more Smart Citation

Nonlinear plant-wide process monitoring using MI-spectral clustering and Bayesian inference-based multiblock KPCA

Jiang

Yan

2015

Journal of Process Control

View full text Add to dashboard Cite

“…The following assumptions are needed in PCA monitoring: first, the data collected from chemical processes are Gaussian distributed; second, process variables are linearly related. These assumptions are easily violated in reality, particularly in plant-wide process monitoring, which is usually complex and has many different operation units; therefore, PCA may therefore not function well 6,11,[15][16][17] .…”

Section: Introductionmentioning

confidence: 99%

“…Ge et al 15 proposed a method that uses linear subspace PCA and Bayesian inference (BSPCA) for nonlinear process monitoring, and the PCA decomposition is employed to construct linear subspaces.…”

Section: Introductionmentioning

confidence: 99%

Multiblock Independent Component Analysis Integrated with Hellinger Distance and Bayesian Inference for Non-Gaussian Plant-Wide Process Monitoring

Jiang

Wang

Yan

2015

Ind. Eng. Chem. Res.

View full text Add to dashboard Cite

A novel multiblock plant-wide process monitoring method based on Hellinger distance (HD), Bayesian inference, and independent component analysis (ICA) (HDBICA) is proposed in this paper.Multiblock methods are usually employed for plant-wide process monitoring; however, block division is usually based on prior process knowledge that may not always be available. This paper proposes a totally data-driven multiblock monitoring method that employs HD to divide blocks automatically.Variables with similar probability distributions are divided into the same block on the basis of HD, and sub-ICA models are built for sub-block status monitoring. Finally, the monitoring results from all blocks are combined on the basis of Bayesian inference. HDBICA is exemplified by using a numerical study and the Tennessee-Eastman benchmark process. The monitoring results indicate that the performance of HDBICA is superior to the performances of ICA, Kernel ICA, and other state-of-the-art variant-based methods.

show abstract

Adaptive control and signal processing literature survey (No. 20)

2010

Adaptive Control & Signal

View full text Add to dashboard Cite

In order to keep the readers up-to-date, the journal will contain a list of recently published journal articles relevant to the fields of adaptive control and signal processing six times a year. This list is compiled from a wide range of journals. Please note that although the list has been broadly categorized, these classifications are by no means strict and are there to assist the reader. Please also note that inclusion in the list is not an endorsement of a paper's quality. If you have any suggestions or comments, please e-mail Erfu Yang at erfu.yang@eee.strath.ac.uk. ADAPTIVE SYSTEMSAbramovich Y, Frazer G, Johnson B. Iterative adaptive Kronecker MIMO radar beamformer: description and convergence analysis. IEEE Transactions on Signal Processing 2010; 58(7):3681-3691. Badwe A, Singh A, Patwardhan S, Gudi R. A constrained recursive pseudo-linear regression scheme for on-line parameter estimation in adaptive control. Journal of Process Control 2010; 20(5):559-572. Cassimatis N, Bignoli P, Bugajska M, Dugas S, Kurup U, Murugesan A, Bello P. An architecture for adaptive algorithmic hybrids. IEEE Transactions on Systems, Man and Cybernetics Part B: Cybernetic 2010; 40(3):903-914. Cheah C, Hou S, Zhao Y, Slotine J-J. Adaptive vision and force tracking control for robots with constraint uncertainty. IEEE/ASME Transactions on Mechatronics 2010; 15(3): 389-399. Cheah C, Liu C, Slotine J. Adaptive Jacobian vision based control for robots with uncertain depth information. Automatica 2010; 46(7):1228-1233. De Maio A, Conte E. Adaptive detection in Gaussian interference with unknown covariance after reduction by invariance. IEEE Transactions on Signal Processing 2010; 58(6):2925-2934. Fei J. Robust adaptive vibration tracking control for a micro-electro-mechanical systems vibratory gyroscope with bound estimation. control allocation for non-linear systems with internal dynamics. IET Control Theory and Applications 2010; 4(6):909-922. Liu L, Xie X-J. Decentralized adaptive stabilization for interconnected systems with dynamic input-output and nonlinear interactions. Automatica 2010; 46(6):1060-1067. Malloci I, Daafouz J, Iung C. Stability and stabilization of two time scale switched systems in discrete time. IEEE Transactions on Automatic Control 2010; 55(6):1434-1438. Mileounis G, Babadi B, Kalouptsidis N, Tarokh V. An adaptive greedy algorithm with application to nonlinear communications. IEEE Transactions on Signal Processing 2010; 58(6):2998-3007. Nguyen H-X, Nguyen H-H. Adaptive relaying in noncoherent cooperative networks. IEEE Transactions on Signal Processing 2010; 58(7):3938-3945. Pigg S, Bodson M. Adaptive algorithms for the rejection of sinusoidal disturbances acting on unknown plants. IEEE Transactions on Control Systems Technology 2010; 18(4): 822-836. Tucci M, Raugi M. Adaptive FIR neural model for centroid learning in self-organizing maps. IEEE Transactions on Neural Networks 2010; 21(6):948-960. Wang L, de Lamare R, Yukawa M. Adaptive reducedrank constrained constant modulus algorithms based on

show abstract

Nonlinear process monitoring based on linear subspace and Bayesian inference

Cited by 153 publications

References 24 publications

Nonlinear plant-wide process monitoring using MI-spectral clustering and Bayesian inference-based multiblock KPCA

Nonlinear plant-wide process monitoring using MI-spectral clustering and Bayesian inference-based multiblock KPCA

Multiblock Independent Component Analysis Integrated with Hellinger Distance and Bayesian Inference for Non-Gaussian Plant-Wide Process Monitoring

Adaptive control and signal processing literature survey (No. 20)

Contact Info

Product

Resources

About