Litcius/Paper detail

Quality Regularization-Based Semisupervised Adversarial Transfer Model With Unlabeled Data for Industrial Soft Sensing

Yan‐Lin He, Lei Chen, Qun-Xiong Zhu

2023IEEE Transactions on Industrial Informatics35 citationsDOI

Abstract

Traditional soft sensors typically rely only on labeled data to predict key variables, despite the significant amount of unlabeled data that could provide valuable information. To solve this problem, a quality regularization-based semisupervised adversarial transfer model (QR-SATM) is proposed. The idea of transfer learning is used in QR-SATM. QR-SATM comprises a pretraining model and a regression model. The pretraining model is an unsupervised model. And the regression model is a supervised model with a similar structure to the pretraining model, allowing for easy transfer between the two models. First, the pretraining model is trained with unlabeled data to extract features. Then, the trained parameters of pretraining model are transferred to the regression model, and the regression model is fine-tuned with labeled data. During fine-tuning the regression model, an improved quality regularization is introduced in order to select useful features and prevent overfitting. QR-SATM is validated by a real industrial dataset of purified terephthalic acid. The experimental results show the effectiveness of the proposed QR-SATM in accurately predicting key variables.

Topics & Concepts

OverfittingRegularization (linguistics)Artificial intelligenceComputer scienceData modelingMachine learningRegressionRegression analysisTransfer of learningData miningPattern recognition (psychology)MathematicsStatisticsArtificial neural networkDatabaseFault Detection and Control SystemsMachine Learning and ELMDomain Adaptation and Few-Shot Learning
Quality Regularization-Based Semisupervised Adversarial Transfer Model With Unlabeled Data for Industrial Soft Sensing | Litcius