Incorporate active learning to semi-supervised industrial fault classification

Yin, Lili; Wang, Huangang; Fan, Wenhui; Kou, Li; Lin, Ting-Yu; Yingying, Xiao

doi:10.1016/j.jprocont.2019.04.008

Cited by 27 publications

(16 citation statements)

References 23 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…This paper uses the S4VM parameters recommended by Li et al [26], as shown in Table 5. The parameter "a" is recommended by Yin et al [14]. The amount of labeled data and unlabeled data are determined based on experience and experiments.…”

Section: Identification Results and Discussionmentioning

confidence: 99%

“…The mutual influence includes four relations: control relation, reaction relation, type relation, and position relation [27]. In order to better demonstrate the effectiveness of the PCA-DAS4VM method, this method is also compared with those typical semi-supervised learning methods such as ALSemiFDA [14] and DSSAE [15]. The accuracy rate of each method when applied to TE process is shown in Figure 13.…”

Section: Methodsmentioning

confidence: 99%

“…However, the application of active learning and semi-supervised learning to chemical process fault identification is only a small presence in the literature. Wang et al [14] proposed an active learning based semi-supervised fisher discriminant analysis (SemiFDA) model with an average fault identification accuracy of 58.10% for the TE process. Song et al [15] proposed a dynamic spare stacked auto-encoders (DSSAE) model based semi-supervised framework.…”

Section: Background and Significancementioning

confidence: 99%

“…The process includes 22 continuous measured variables (Table 2) and 20 preset fault modes (Table 3). 3E Feed CMV (14) Separator underflow CMV 4A and C Feed CMV (15) Stripper level CMV (5) Recycle flow CMV (16) Stripper pressure CMV (6) Reactor feed CMV (17) Stripper underflow CMV 7Reactor pressure CMV (18) Stripper temperature CMV (8) Reactor level CMV (19) Stripper steam flow 5Recycle flow CMV (16) Stripper pressure CMV (6) Reactor feed CMV (17) Stripper underflow CMV 7Reactor pressure CMV (18) Stripper temperature CMV (8) Reactor level CMV (19) Stripper steam flow CMV (9) Reactor temperature CMV (20) Compressor work CMV (10) Purge flow CMV (21) Reactor cooling water outlet temperature CMV (11) Separator temperature CMV (22) Condenser cooling water outlet temperature Figure 4 shows that the total variance contribution rate of the first 12 principal components has reached 83.15% (more than 80%), so the first 12 principal components can reflect information about all variables. Figure 5 shows the eigenvalues of the first 12 principal components as well.…”

Section: Process Descriptionmentioning

confidence: 99%

See 3 more Smart Citations

A Dynamic Active Safe Semi-Supervised Learning Framework for Fault Identification in Labeled Expensive Chemical Processes

Jia

Tian

et al. 2020

Processes

View full text Add to dashboard Cite

A novel active semi-supervised learning framework using unlabeled data is proposed for fault identification in labeled expensive chemical processes. A principal component analysis (PCA) feature selection strategy is first given to calculate the weight of the variables. Secondly, the identification model is trained based on the obtained key process variables. Thirdly, the pseudo label confidence of identification model is dynamically optimized with an historical, current, and future pseudo label confidence mean. To increase the upper limit of the identification model that is self-learning with high entropy process data, active learning is used to identify process data and diagnosis fault causes by ontology. Finally, a PCA-dynamic active safe semi-supervised support vector machine (PCA-DAS4VM) for fault identification in labeled expensive chemical processes is built. The application in the Tennessee Eastman (TE) process shows that this hybrid technology is able to: (i) eliminate chemical process noise and redundant process variables simultaneously, (ii) combine historical pseudo label confidence with future pseudo label confidence to improve the identification accuracy of abnormal working conditions, (iii) efficiently select and diagnose high entropy unlabeled process data, and (iv) fully utilize unlabeled data to enhance the identification performance.

show abstract

Section: Identification Results and Discussionmentioning

confidence: 99%

Section: Methodsmentioning

confidence: 99%

Section: Background and Significancementioning

confidence: 99%

Section: Process Descriptionmentioning

confidence: 99%

See 2 more Smart Citations

A Dynamic Active Safe Semi-Supervised Learning Framework for Fault Identification in Labeled Expensive Chemical Processes

Jia

Tian

et al. 2020

Processes

View full text Add to dashboard Cite

show abstract

“…Recently, a few scholars have conducted research on semisupervised learning (SSL) methods in the field of fault diagnosis [25]. SSL can use a small number of labeled samples and a large number of unlabeled samples to train an accurate classifier [26], [27].…”

Section: Introductionmentioning

confidence: 99%

An Intelligent Fault Diagnosis for Rolling Bearing Based on Adversarial Semi-Supervised Method

Ren

Zhou

2020

IEEE Access

View full text Add to dashboard Cite

Intelligent fault diagnosis of rolling bearing issues have been well addressed with the rapid growth of data scale. However, the performance of most diagnostic algorithms heavily depends on sufficient labeled samples. How to ensure the fault diagnosis accuracy with scarce labeled samples is always a great challenge in real industrial scenarios. To alleviate this issue, a deep adversarial semi-supervised (DASS) method based on the prototype learning network is proposed for rolling bearing fault diagnosis in this study. First, the nine data augmentation methods are investigated to improve the ability of the network to extract discrepant features. Second, a cosine similarity-based classifier architecture is exploited to estimate prototypes of sample features. Third, the cross entropy and the adversarial entropy are introduced to improve diagnostic accuracy and reduce intra-class variation. Extensive experiments on two rolling bearing datasets verify that the proposed method owns a remarkable identification ability and great robustness under scarce labeled samples as training date. At the same time, the diagnostic performance under different number of labeled samples is extensively evaluated in noisy environment with different signal-to-noise ratio.INDEX TERMS Intelligent fault diagnosis, deep neural network, adversarial semi-supervised learning, rolling bearing.

show abstract

A novel two-step adaptive multioutput semisupervised soft sensor with applications in wastewater treatment

Liu

Huang

Liu

2021

Environ Sci Pollut Res

View full text Add to dashboard Cite

Incorporate active learning to semi-supervised industrial fault classification

Cited by 27 publications

References 23 publications

A Dynamic Active Safe Semi-Supervised Learning Framework for Fault Identification in Labeled Expensive Chemical Processes

A Dynamic Active Safe Semi-Supervised Learning Framework for Fault Identification in Labeled Expensive Chemical Processes

An Intelligent Fault Diagnosis for Rolling Bearing Based on Adversarial Semi-Supervised Method

A novel two-step adaptive multioutput semisupervised soft sensor with applications in wastewater treatment

Contact Info

Product

Resources

About