Batch process monitoring based on self-adaptive subspace support vector data description

Lv, Zhaomin; Yan, Xuefeng; Jiang, Qingchao

doi:10.1016/j.chemolab.2017.09.009

Cited by 26 publications

(16 citation statements)

References 21 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…In this case study, a contaminated training data set was generated by randomly replacing some samples in the normal data set with Gaussian distributed outliers. A total of 33 process variables were monitored, consisting of 11 manipulated variables (see XMV [1][2][3][4][5][6][7][8][9][10][11] in tab. 3 in Downs and Vogel 34 ) and 22 continuous process measurements (see XMEAS in tab.…”

Section: Process Descriptionmentioning

confidence: 99%

See 1 more Smart Citation

Monitoring of industrial processes using robust global–local preserving projection

Bao

Luo

2020

Journal of Chemometrics

View full text Add to dashboard Cite

Usual multivariate statistical analysis (MSA) techniques are highly sensitive to outliers because they are based on the least squares fitting or the empirical mean and covariance of the data. Data‐driven process monitoring methods based on usual MSA techniques may be unreliable when outliers are present in the training data. To overcome this deficiency, a robust global–local preserving projection (RGLPP) method is proposed for dimension reduction of the high‐dimensional data contaminated by outliers, and then it is applied to the robust monitoring of industrial processes. Despite the presence of outliers, RGLPP yields robust projection directions that can preserve both global and local structures of the high‐dimensional data. Moreover, based on the robust projection directions of RGLPP, a method is developed for identifying outliers in a multivariate data set. An RGLPP‐based robust process monitoring method is also developed to achieve high‐performance monitoring when the training data of industrial processes contain outliers. The effectiveness and advantages of the proposed method are illustrated using an industrial case study.

show abstract

Section: Process Descriptionmentioning

confidence: 99%

“…Data-driven process monitoring methods have been widely investigated in the past few decades. [1][2][3][4][5][6][7][8][9] A good review of these methods can be found in the reference. [1][2][3][4] Most of data-driven monitoring methods were developed based on multivariate statistical analysis (MSA) techniques.…”

Section: Introductionmentioning

confidence: 99%

Monitoring of industrial processes using robust global–local preserving projection

Bao

Luo

2020

Journal of Chemometrics

View full text Add to dashboard Cite

show abstract

“…By Equation (19), the fault probabilities for the DeSVDD models are obtained. The next is to combine them for a holistic index.…”

Section: Multiple Deep Models Ensemble With Bayesian Inference Strategymentioning

confidence: 99%

“…For dealing with the fault detection of rolling element bearings, Liu et al [17] proposed a semi-supervised SVDD method to overcome the limitation of labeling samples. Some other related studies can be seen in literature [18][19][20].…”

Section: Introductionmentioning

confidence: 99%

Nonlinear Chemical Process Fault Diagnosis Using Ensemble Deep Support Vector Data Description

Deng¹,

Zhang²

2020

Sensors

View full text Add to dashboard Cite

As one classical anomaly detection technology, support vector data description (SVDD) has been successfully applied to nonlinear chemical process monitoring. However, the basic SVDD model cannot achieve a satisfactory fault detection performance in the complicated cases because of its intrinsic shallow learning structure. Motivated by the deep learning theory, one improved SVDD method, called ensemble deep SVDD (EDeSVDD), is proposed in order to monitor the process faults more effectively. In the proposed method, a deep support vector data description (DeSVDD) framework is firstly constructed by introducing the deep feature extraction procedure. Different to the traditional SVDD with only one feature extraction layer, DeSVDD is designed with multi-layer feature extraction structure and optimized by minimizing the data-enclosing hypersphere with the regularization of the deep network weights. Further considering the problem that DeSVDD monitoring performance is easily affected by the model structure and the initial weight parameters, an ensemble DeSVDD (EDeSVDD) is presented by applying the ensemble learning strategy based on Bayesian inference. A series of DeSVDD sub-models are generated at the parameter level and the structure level, respectively. These two levels of sub-models are integrated for a holistic monitoring model. To identify the cause variables for the detected faults, a fault isolation scheme is designed by applying the distance correlation coefficients to measure the nonlinear dependency between the original variables and the holistic monitoring index. The applications to the Tennessee Eastman process demonstrate that the proposed EDeSVDD model outperforms the traditional SVDD model and the DeSVDD model in terms of fault detection performance and can identify the fault cause variables effectively.

show abstract

“…Relevant matrix based on mutual information (MI) and contribution matrix based on independent component analysis (ICA) Twelve faults based on the above simulation are designed to substantiate the JITL-MSSVDD. The design parameters 31 for all the test faults are listed in Table 2. One classic monitoring method, two dynamic monitoring methods, and one subspace-based dynamic monitoring method are compared with the proposed method.…”

Section: Figurementioning

confidence: 99%

Just‐in‐time learning–multiple subspace support vector data description used for non‐Gaussian dynamic batch process monitoring

Yan

Jiang

et al. 2019

Journal of Chemometrics

Self Cite

View full text Add to dashboard Cite

Batch process data are time‐varying dynamic and non‐Gaussian distributed. In addition, for multivariate statistical process monitoring, their variability can be overwhelmed when considering local variability behavior. To address the abovementioned issues, an improved batch process monitoring approach is presented that integrates just‐in‐time learning and multiple subspace support vector data description (JITL‐MSSVDD). A new multiple subspace segmentation method is proposed that classifies a contribution array that is calculated on the mixing matrix of independent component analysis (ICA). Offline, the variable subspace segmentation rule can be obtained from the proposed method. The subspace monitoring models can reduce the risk of the variability being overwhelmed. Online, local modeling samples are collected through JITL, which can reduce the impact of the time‐varying dynamic on modeling accuracy. Then, in accordance with the variable subspace segmentation rule, which is obtained offline, MSSVDD models are constructed to solve non‐Gaussian problems. The advantage of the proposed JITL‐MSSVDD is demonstrated through the standard test model fed‐batch penicillin fermentation process.

show abstract

Batch process monitoring based on self-adaptive subspace support vector data description

Cited by 26 publications

References 21 publications

Monitoring of industrial processes using robust global–local preserving projection

Monitoring of industrial processes using robust global–local preserving projection

Nonlinear Chemical Process Fault Diagnosis Using Ensemble Deep Support Vector Data Description

Just‐in‐time learning–multiple subspace support vector data description used for non‐Gaussian dynamic batch process monitoring

Contact Info

Product

Resources

About