Batch process monitoring based on just-in-time learning and multiple-subspace principal component analysis

Lv, Zhaomin; Yan, Xuefeng; Jiang, Qingchao

doi:10.1016/j.chemolab.2014.06.010

Cited by 38 publications

(28 citation statements)

References 27 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…An MI‐based subspace segmentation method is applied to normal batch data to obtain a relevant array, which can represent the correlation of any two process variables. The left side of Figure demonstrates the gray‐scale map of the relevant array, which is obtained from the MI‐based subspace segmentation method . The x‐ and y‐axes indicate the sequence number of the process variable.…”

Section: Application Examplementioning

confidence: 99%

“…JITL‐SVDD shows that the SVDD model is constructed on the local matrix obtained from JITL. To reflect the impact of subspace segmentation on monitoring performance, MI‐JITL‐MSSVDD represents the dynamic monitoring method, which uses the MI‐based subspace segmentation method . The ICA‐JITL‐MSSVDD represents the proposed dynamic monitoring method, which uses the proposed ICA‐based subspace segmentation method.…”

Section: Application Examplementioning

confidence: 99%

“…The ICA‐JITL‐MSSVDD represents the proposed dynamic monitoring method, which uses the proposed ICA‐based subspace segmentation method. Four monitoring performance indicators, namely, the false alarm rate, missed alarm rate, error rate, and the first time instant to detect the fault, are used to test the ICA‐JITL‐MSSVDD …”

Section: Application Examplementioning

confidence: 99%

“…The run time varies among different batches, which may lead to the inability of these approaches to track the time‐varying dynamic characteristics well and may cause a failure for the monitoring methods to ultimately detect the fault. Just‐in‐time learning (JITL)–based approaches are built online and only collect the most relevant modeling data on the basis of the similarity between the historical database and online samples, which can adapt to the different run times of the processes and trace the changing status of the batch process well . It is well known that many batch processes have multiphase characteristics.…”

Section: Introductionmentioning

confidence: 99%

“…Just-in-time learning (JITL)-based approaches are built online and only collect the most relevant modeling data on the basis of the similarity between the historical database and online samples, which can adapt to the different run times of the processes and trace the changing status of the batch process well. 21,22 It is well known that many batch processes have multiphase characteristics. When the multiphase characteristics and the dynamic characteristics are considered at the same time, a concurrent monitoring strategy is established.…”

Section: Introductionmentioning

confidence: 99%

See 4 more Smart Citations

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

Section: Application Examplementioning

confidence: 99%

Section: Application Examplementioning

confidence: 99%

Section: Application Examplementioning

confidence: 99%

Section: Introductionmentioning

confidence: 99%

Section: Introductionmentioning

confidence: 99%

See 3 more Smart Citations

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

show abstract

Double‐step block division plant‐wide fault detection and diagnosis based on variable distributions and relevant features

Huang

Yan

2015

Journal of Chemometrics

Self Cite

View full text Add to dashboard Cite

Large-scale process data in plant-wide process monitoring are characterized by two features: complex distributions and complex relevance. This study proposes a double-step block division plant-wide process monitoring method based on variable distributions and relevant features to overcome this limitation. First, the data distribution is considered, and the normality test method called the D-test is applied to classify the variables with the same distribution (i.e., Gaussian distribution or non-Gaussian distribution) in a block. Thus, the second block division is implemented on both blocks obtained in the previous step. The mutual information shared between two variables is used to generate relevant matrixes of the Gaussian and non-Gaussian blocks. The K-means method clusters the vectors of the relevant matrix. Principal component analysis is conducted to monitor each Gaussian subblock, whereas independent component analysis is conducted to monitor each non-Gaussian subblock. A composite statistic is eventually derived through Bayesian inference. The proposed method is applied to a numerical system and the Tennessee Eastman process data set. The monitoring performance shows the superiority of the proposed method.

show abstract

Machine Learning in Chemical Engineering: A Perspective

Schweidtmann

Esche

Fischer

et al. 2021

Chemie Ingenieur Technik

130

View full text Add to dashboard Cite

The transformation of the chemical industry to renewable energy and feedstock supply requires new paradigms for the design of flexible plants, (bio-)catalysts, and functional materials. Recent breakthroughs in machine learning (ML) provide unique opportunities, but only joint interdisciplinary research between the ML and chemical engineering (CE) communities will unfold the full potential. We identify six challenges that will open new methods for CE and formulate new types of problems for ML: (1) optimal decision making, (2) introducing and enforcing physics in ML, (3) information and knowledge representation, (4) heterogeneity of data, (5) safety and trust in ML applications, and (6) creativity. Under the umbrella of these challenges, we discuss perspectives for future interdisciplinary research that will enable the transformation of CE.

show abstract

Batch process monitoring based on just-in-time learning and multiple-subspace principal component analysis

Cited by 38 publications

References 27 publications

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

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

Double‐step block division plant‐wide fault detection and diagnosis based on variable distributions and relevant features

Machine Learning in Chemical Engineering: A Perspective

Contact Info

Product

Resources

About