A Mixture of Variational Canonical Correlation Analysis for Nonlinear and Quality-Relevant Process Monitoring

Liu, Yiqi; Liu, Bin; Zhao, Xiujie; Xie, Min

doi:10.1109/tie.2017.2786253

Cited by 116 publications

(52 citation statements)

References 26 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…However, for a small sample of time-varying data, the adaptive soft-sensors would often reduce the prediction performance during the process of updating the models. Therefore, in the proposed model, MRPLS and MLSTM can be replaced by other linear or nonlinear models [29], and the recursive method can also be used in others, such as just-in-time learning (JITL) and so on [30].…”

Section: Discussionmentioning

confidence: 99%

Learning Adaptive Semi-Supervised Multi-Output Soft-Sensors With Co-Training of Heterogeneous Models

Liu

Huang

et al. 2020

IEEE Access

Self Cite

View full text Add to dashboard Cite

Soft-sensors are widely utilized for predictions of important but hard-to-measure variables in industrial processes. However, significant variations, process uncertainties, negative influence of external environment and insufficient use of unlabeled data always cause the attenuation of prediction performance. Thus, this paper proposed an adaptive semi-supervised multi-output soft-sensor by co-training recursive heterogeneous models. In the proposed strategy, a linear multi-output model, called recursive partial least square (MRPLS), and a nonlinear multi-output, called long short-term memory recurrent neural network (MLSTM), are co-trained to deal with inefficient use of label data adaptively. Ensemble of both models are not only able to address the linear and nonlinear hybrid behaviors in different time scale, but also able to deal with multiple tasks learning issues. In addition, the model proposed an odd-even grouping strategy to equalize two parts of the labeled data, which is able to capture the global variations of a process. To validate the prediction performance of the proposed soft-sensor, it was verified through a simulation benchmark platform (BSM1) and a real sewage treatment plant (UCI database). The results meant that co-training MRPLS-MLSTM achieved better performance compared with other existing co-training models in terms of the hard-to-measure variables. INDEX TERMS Soft-sensors, semi-supervised, co-training, multi-output, recursive partial least square (RPLS), long short-term memory recurrent neural network (LSTM).

show abstract

Section: Discussionmentioning

confidence: 99%

Learning Adaptive Semi-Supervised Multi-Output Soft-Sensors With Co-Training of Heterogeneous Models

Liu

Huang

et al. 2020

IEEE Access

Self Cite

View full text Add to dashboard Cite

show abstract

“…And it is a kind of unsupervised multiple feature extraction and low-dimension features can be extracted from any two variables of a data set [37]. The objective of CCA is to study the linear relations of two vectors by maximizing correlations among them [38], [39]. Suppose X , Y are the sets of sample pairs with length N .…”

Section: B Canonical Correlation Analysis(cca)mentioning

confidence: 99%

Nonlinear Soft Fault Diagnosis of Analog Circuits Based on RCCA-SVM

Zhang

Guo

et al. 2020

IEEE Access

View full text Add to dashboard Cite

In the soft fault diagnosis of nonlinear analog filter circuits, the single feature can't maximally reveal the behaviors hidden in signals. In order to overcome such shortcomings, a fusion algorithm weighted feature from multi-group is proposed. This method use reliefF algorithm to optimize canonical correlation analysis combines support vector machine(RCCA-SVM) for diagnosis. The fault characteristics used in this method are extracted from the time-domain, statistical features and frequency-domain by wavelet packet transform (WPT). And then the CCA algorithm is used to improve the correlation of features according to the weights of the features. Finally, the fusion features are dimension reduced by principal component analysis(PCA), support vector machine(SVM) is the classifier of the diagnosis. The simulations show that the proposed method has a good diagnostic effect on circuit fault diagnosis of non-linear analog circuits. INDEX TERMS Nonlinear analog circuit fault diagnosis, WPT, RCCA-SVM.

show abstract

“…However, the nonlinear issue needs to be handled more efficiently in CVDA, since processes are inherently nonlinear in practice. One way to address this is to represent the system in a set of multiple local linear models, such as the recent application of locality preserving projections (LPP) to CVA by Lu et al (2018) and the mixture variational Bayesian CCA by Liu et al (2018b). Alternatively, kernel-based learning can be introduced in CVDA for nonlinear pattern discovery.…”

Section: Introductionmentioning

confidence: 99%

Mixed kernel canonical variate dissimilarity analysis for incipient fault monitoring in nonlinear dynamic processes

Pilario

Cao

Shafiee

2019

Computers & Chemical Engineering

View full text Add to dashboard Cite

Incipient fault monitoring is becoming very important in large industrial plants, as the early detection of incipient faults can help avoid major plant failures. Recently, Canonical Variate Dissimilarity Analysis (CVDA) has been shown to be an efficient technique for incipient fault detection, especially under dynamic process conditions. CVDA can be extended to nonlinear processes by introducing kernel-based learning. Incipient fault monitoring requires kernels with both good interpolation and extrapolation abilities. However, conventional single kernels only exhibit one ability or the other, but not both. To overcome this drawback, this study presents a Mixed Kernel CVDA method for incipient fault monitoring in nonlinear dynamic processes. Due to the use of mixed kernels, both enhanced detection sensitivity and a better depiction of the growing fault severity in the monitoring charts are achieved. Looking ahead, this work takes a step towards understanding the impact of kernel behavior in process monitoring performance.

show abstract

A Mixture of Variational Canonical Correlation Analysis for Nonlinear and Quality-Relevant Process Monitoring

Cited by 116 publications

References 26 publications

Learning Adaptive Semi-Supervised Multi-Output Soft-Sensors With Co-Training of Heterogeneous Models

Learning Adaptive Semi-Supervised Multi-Output Soft-Sensors With Co-Training of Heterogeneous Models

Nonlinear Soft Fault Diagnosis of Analog Circuits Based on RCCA-SVM

Mixed kernel canonical variate dissimilarity analysis for incipient fault monitoring in nonlinear dynamic processes

Contact Info

Product

Resources

About