Blackout Missing Data Recovery in Industrial Time Series Based on Masked-Former Hierarchical Imputation Framework

In industrial processes, frequent communication failures and information corruption may result in the loss of entire blocks of industrial process data, which is also known as blackout missing data. The imperfect data of industrial time series impede the performance of subsequent modeling and control tasks. However, traditional matrix factorization or supervised learning data imputation methods are hardly applicable to the challenging task of recovering blackout missing data. The difficulty in imputing the blackout data stems from two major factors: the imputation process lacks the reference of co- evolutionary variables, and the blackout data have strong autocorrelation and drift in distribution. To address these issues, this paper develops a novel hierarchical imputation framework for recovering blackout data based on the masked transformer network (Masked-Former). First, a reconstruction block strategy with random masked points is innovatively proposed to improve the ability of the model to recover missing values under different working conditions for incomplete datasets. Then, based on the masked incomplete data set, the proposed method utilizes the local feature capture capability of convolutional networks and the sample-level long-range dependency capture capability of the self-attention mechanism to complete coarse-grained and fine-grained missing data imputation, respectively. Finally, extensive experiments are conducted to verify the superior performance of the proposed method on two real-world industrial data sets. Note to Practitioners—Inspired by the phenomenon that industrial process data often have missing data, this paper proposes a novel hierarchical imputation Masked-Former method for blackout missing data recovery. The method combines local data features with long-term time series dependency performance to improve completion performance. Then, the obtained completed data can help practitioners monitor the status of industrial field conditions. In addition, it is helpful to perform subsequent quality prediction and process monitoring tasks, allowing practitioners to quickly take preventative measures to avoid disasters and take corrective operations to return the plant to its normal operating range.

I. Introduction

Effective monitoring, modeling and optimization are crucial to the safe, efficient and clean production of industrial processes, and all of these rely on the collection of high-quality process data [1], [2], [3], [4]. However, the harsh industrial environment often gives rise to issues such as sensor sampling failure, sensor damage, and data transmission failure, leading to missing values in the collected data. The incomplete dataset not only lacks important system information and increases system uncertainty, but it can also cause confusion in the modeling process, produce unreliable results, and even result in modeling failure [5], [6]. Hence, missing value imputation (MVI) is a very challenging and urgent task.