Nonlinear feature extraction for soft sensor modeling based on weighted probabilistic PCA

Yuan, Xiaofeng; Ye, Lingjian; Li, Bao; Ge, Zhiqiang

doi:10.1016/j.chemolab.2015.08.014

Cited by 55 publications

(30 citation statements)

References 29 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…It can be defined as follows:

R^{2} = 1 - \frac{\sum_{i = 1}^{N} {(y_{i} - \overset{\land}{y_{i}})}^{2}}{\sum_{i = 1}^{N} {(y_{i} - \bar{y_{i}})}^{2}},

where

\overset{y}{true}

is the average of output. According to Yuan et al, the R 2 index reflects how good the model can determine the total variance in the output. The closer the R 2 value to 1, the better the correlation between the estimated and the actual values will be.…”

Section: Preliminariesmentioning

confidence: 99%

Missing data treatment for locally weighted partial least square‐based modelling: A comparative study

Yeo

Saptoro

Perumal

2020

Asia-Pacific J Chem Eng

View full text Add to dashboard Cite

Adaptive soft sensors including widely used locally weighted partial least square (LW‐PLS) have been established for online prediction, fault detection, and process monitoring. Nevertheless, majority of these existing adaptive soft sensors have zero tolerance to missing data, and the presence of missing data is inevitable due to sensor failures, routine maintenance, changes in sensor equipment over time, merging data from different system, and so forth. In the literature, limited studies could be found on the effects of missing data and the existing missing data imputation methods on the predictive performances of adaptive soft sensors. This work reports combined use of different missing data imputation techniques on LW‐PLS and the nonadaptive soft sensor, the partial least square (PLS). Well known trimmed score regression (TSR) and singular value decomposition (SVD) were employed in this study, and thus, the newly integrated TSR‐LW‐PLS and SVD‐LW‐PLS algorithms were proposed. Meanwhile, both existing TSR‐PLS and SVD‐PLS were used, and their results compared with the novel TSR‐LW‐PLS and SVD‐LW‐PLS algorithms. These algorithms were tested and evaluated using two examples having different percentages of missing data ranging from 5% to 40%. Results showed that TSR‐LW‐PLS model was superior compared with SVD‐LW‐PLS, TSR‐PLS, and SVD‐PLS as indicated by more than 100% improvements in prediction accuracy. It was also evident that TSR‐LW‐PLS is able to cope well with up to 20% of missing data.

show abstract

“…It can be defined as follows:

R^{2} = 1 - \frac{\sum_{i = 1}^{N} {(y_{i} - \overset{\land}{y_{i}})}^{2}}{\sum_{i = 1}^{N} {(y_{i} - \bar{y_{i}})}^{2}},

where

\overset{y}{true}

Section: Preliminariesmentioning

confidence: 99%

Missing data treatment for locally weighted partial least square‐based modelling: A comparative study

Yeo

Saptoro

Perumal

2020

Asia-Pacific J Chem Eng

View full text Add to dashboard Cite

show abstract

“…Especially, data‐driven soft sensor methods have been extensively researched and used during the past years because mountains of process data can be collected in modern industrial plants. A lot of soft sensor methods, like principal component regression (PCR), Gaussian process regression, and support vector machine, have been successfully applied to areas like chemical engineering, biochemical engineering, metallurgical industrial, and pharmaceuticals industry . Some reviews on soft sensors can be found in several literatures …”

Section: Introductionmentioning

confidence: 99%

“…A lot of soft sensor methods, like principal component regression (PCR), 2 Gaussian process regression, 3 and support vector machine, 4 have been successfully applied to areas like chemical engineering, biochemical engineering, metallurgical industrial, and pharmaceuticals industry. [5][6][7][8][9] Some reviews on soft sensors can be found in several literatures. [10][11][12][13] Owing to the high-dimensional data characteristic, it is of great interest to reveal the underlying structure of data through a low-dimensional feature representation, which is also known as feature extraction, dimensionality reduction, or manifold learning.…”

Section: Introductionmentioning

confidence: 99%

Supervised neighborhood preserving embedding for feature extraction and its application for soft sensor modeling

Yuan

et al. 2016

Journal of Chemometrics

Self Cite

View full text Add to dashboard Cite

Neighborhood preserving embedding (NPE) is a useful tool for learning the manifold of high‐dimensional data. As a linear approximation of nonlinear locally linear embedding, NPE can be applied to dimensionality reduction by neighborhood preserving. However, the original NPE algorithm is an unsupervised method, which extracts features without any reference to the output information. In this paper, a supervised NPE framework is proposed for output‐related feature extraction in soft sensor applications. In the supervised NPE framework, the output information is utilized to guide the procedures for constructing the adjacent graph and calculating the weight matrix, with which the intrinsic structure of the data can be better described. For performance evaluation of the proposed method, experiments on a numerical example and an industrial debutanizer column process are carried out. The results show the effectiveness of the proposed framework.

show abstract

“…[1][2][3][4] By constructing a soft sensor model between these easy-to-measure variables and those difficult-to-measure ones, the key process variables can be continuously estimated. [14][15][16][17][18][19][20] However, once a soft sensor has been constructed, its prediction accuracy will deteriorate as a result of process state variations, degradation of catalyzer, raw material changes, sensor drifting, etc. [14][15][16][17][18][19][20] However, once a soft sensor has been constructed, its prediction accuracy will deteriorate as a result of process state variations, degradation of catalyzer, raw material changes, sensor drifting, etc.…”

Section: Introductionmentioning

confidence: 99%

Spatio‐temporal adaptive soft sensor for nonlinear time‐varying and variable drifting processes based on moving window LWPLS and time difference model

Yuan

Song

2015

Asia-Pacific J Chem Eng

Self Cite

View full text Add to dashboard Cite

Industrial plants often undergo different kinds of changes like variable drifts and time-variant problems, which may cause the degradation of soft sensors. In this paper, a spatio-temporal adaptive soft sensor modeling framework, which is based on the moving window and just-in-time learning (JITL) techniques, is proposed for nonlinear time-varying processes. The JITL (locally weighted partial least squares) can adapt the model by spatial weighting technique, and the moving window technique can adapt the soft sensor model to the new process state. Furthermore, time difference (TD) model is utilized to handle the process change of variable drifts. Case studies are carried out on a numerical example and two industrial processes. The results show the effectiveness and flexibility of the proposed soft sensor framework.

show abstract

Nonlinear feature extraction for soft sensor modeling based on weighted probabilistic PCA

Cited by 55 publications

References 29 publications

Missing data treatment for locally weighted partial least square‐based modelling: A comparative study

Missing data treatment for locally weighted partial least square‐based modelling: A comparative study

Supervised neighborhood preserving embedding for feature extraction and its application for soft sensor modeling

Spatio‐temporal adaptive soft sensor for nonlinear time‐varying and variable drifting processes based on moving window LWPLS and time difference model

Contact Info

Product

Resources

About