Spatio-Temporal View GAIN for Data Imputation and Dynamic Soft Sensor

Soft sensor plays a key role in the safe operation of industrial processes and product quality control. Affected by closed-loop feedback, process data often demonstrate certain dynamic characteristics. In addition, traditional soft sensor methods are often based on the assumption of completeness. Once part of the data is missing, the above methods will collapse. In this paper, we propose a Spatio-Temporal view Generative Adversarial Imputation Network (GAIN) for data imputation and apply dynamic soft sensor for block missing accompanied with completely random missing data. Initially, a data pre-imputed strategy is designed to first impute the missing data through GAIN from the perspective of data distribution. Secondly, on the basis of pre-imputation, a data imputation strategy that integrates time and space information is proposed to impute the data precisely, which can comprehensively consider the time series of process data and the correlation between variables, and further improve the accuracy of data imputation. Finally, we propose a dynamic soft sensor method to make real-time predictions of the data. The effectiveness of the proposed method is verified by the Tennessee Eastman (TE) process.