Variational PLS-Based Calibration Model Building With Semi-Supervised Learning for Moisture Measurement During Fluidized Bed Drying by NIR Spectroscopy

Mu, Guoqing; Liu, Tao; Chen, Junghui; Chen, Shang; Zhong, Chongquan

doi:10.1109/tim.2022.3205663

Cited by 6 publications

(3 citation statements)

References 34 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…In this section, two industrial cases are implemented to verify the soft sensing performance of the proposed methods, one of which is the Tennessee Eastman (TE) benchmark, and the other is a gasoline catalytic cracking process. For comparison, SFA [14], PPLS [13], SLDS [22] and their semi-supervised forms Ss-FA [15], Ss-PPLS [37], Ss-LDS [38] are also introduced. In addition, the regression evaluation index root means square error (RMSE), mean absolute error (MAE) and R-Squared (R 2 ) are employed to evaluate prediction accuracy.…”

Section: Case Studymentioning

confidence: 99%

“…For example, literature [34] proposed a semi-supervised soft sensing method based on a hierarchical extreme learning machine to combine both labeled and unlabeled data through sample similarity where the final latent layer serves as a integration of all information, so that accurate regression model can be established with the existing data [35]. In addition, semi-supervised learning can also be applied to static probabilistic generative models, such as the semi-supervised PPCA model [36] and the semi-supervised PPLS model [37], so as to capture the variable cross-correlation for soft sensing modeling. Alternatively, to prevent dynamic drift due to data incompleteness, [38] and [39] proposed dynamical soft sensor models for quality variable missing situations where the process global information can be learned from those incomplete samples.…”

Section: Introductionmentioning

confidence: 99%

See 1 more Smart Citation

A Quality-Related Concurrent Dual-Latent Variable Model and Its Semi-Supervised Soft Sensor Applications

Wang

Ying

2023

IEEE Access

View full text Add to dashboard Cite

To provide accurate key variable prediction, data-driven soft sensing techniques have extracted much attention in recent years. Due to different control strategies in industrial processes, it is noticed that the variables in the control loops can be autocorrelated while the others may be static, which needs to be considered simultaneously. In this paper, a quality-related concurrent dual-latent variable (CDLV) model is proposed for soft sensing construction. Two different kinds of latent variables are adopted to learn quality-related dynamic information and quality-related static information respectively. Both quality-related variables are then applied for quality prediction purposes. On this basis, the CDLV model is extended to a semi-supervised form to provide a comprehensive description for the soft sensor design with insufficient quality information. The proposed models are demonstrated by two industrial cases which show superiority over other relative methods in the accuracy of key quality variables prediction.

show abstract

Section: Case Studymentioning

confidence: 99%

Section: Introductionmentioning

confidence: 99%

A Quality-Related Concurrent Dual-Latent Variable Model and Its Semi-Supervised Soft Sensor Applications

Wang

Ying

2023

IEEE Access

View full text Add to dashboard Cite

show abstract

“…11 However, compared with the sample size, NIR spectroscopy has a high dimensionality of variables. 12 Although the spectral data contains rich and effective information regarding the organic content, it also contains noise, interference information, and collinearity problems. Using all wavelengths (informative, uninformative, and interfering variables) 13,14 of the NIR spectra leads to poor predictions.…”

Section: Introductionmentioning

confidence: 99%

Development of feature extraction method for near infrared spectroscopy using stepwise bayesian linear regression

Chen

Pan

Wu³

et al. 2023

Journal of Near Infrared Spectroscopy

View full text Add to dashboard Cite

Near infrared (NIR) spectra contain information regarding the analyte as well as uninformative wavelengths. To build high-performance data-driven models, key wavelengths with a strong correlation to the analyte must be selected. This study proposes a feature selection method called stepwise Bayesian linear regression (SBLR) for eliminating unrelated wavelengths, thereby enhancing the robustness of the constructed model. First, a random wavelength is selected from an optimal variable set, and the other wavelengths are placed in a candidate variable set. A Bayesian linear regression (BLR) is implemented by adding a new variable from the candidate set or removing a variable from the optimal set in each step. Furthermore, the BLR model is utilized to perform the F-test. Comparing with the critical value of the F-test with a significance level of α, the test determines whether the variable is retained in the optimal set. Finally, the extracted variables are used to construct a BLR model. The performance and generalization ability of the proposed method were validated. The physical explanation of extracted wavelengths is consistent with the perspective of chemical analysis based on the experiment, which provides a good understanding of the collected NIR spectral data. In addition, compared with traditional algorithms, such as partial least squares regression, least absolute shrinkage and selection operator, and stepwise regression, the proposed method reserves only a few of the effective wavelengths from the full NIR spectra. The proposed method demonstrates potential for key wavelength selection in NIR spectroscopy.

show abstract

A concise subspace projection based meta-learning method for fast modeling and monitoring in multi-grade semiconductor process

Liu,

Zhu,

et al. 2024

Computers & Industrial Engineering

View full text Add to dashboard Cite

Variational PLS-Based Calibration Model Building With Semi-Supervised Learning for Moisture Measurement During Fluidized Bed Drying by NIR Spectroscopy

Cited by 6 publications

References 34 publications

A Quality-Related Concurrent Dual-Latent Variable Model and Its Semi-Supervised Soft Sensor Applications

A Quality-Related Concurrent Dual-Latent Variable Model and Its Semi-Supervised Soft Sensor Applications

Development of feature extraction method for near infrared spectroscopy using stepwise bayesian linear regression

A concise subspace projection based meta-learning method for fast modeling and monitoring in multi-grade semiconductor process

Contact Info

Product

Resources

About