Multi-feature generation network-based imputation method for industrial data with high missing rate

The integrity of industrial data is of great significance to the related technology research in the industrial field. Aiming at the problem of high missing rate of time series data in industrial system, a multi-feature generation network-based imputation algorithm is proposed in this paper, which combines variational autoencoder with generative adversarial network and transforms industrial data sequence into Gaussian mixture distribution. In order to realize data imputation by using the generation idea, a reconstruction loss function is combined to the objective function in the model, and the generated sequence not only satisfies the target distribution, but also matches the target sequence. Considering the multi-scale characteristics of industrial data, a multi-feature generation method for imputation is designed, which decomposes the data into multi-scale series and imputes the subsequences under multiple time scales respectively. The experiments for the standard data sets and the actual production data of blast furnace gas system show that, the proposed method can reduce the complexity of data generation and improve the imputation accuracy, which has a good effect in the case of high missing rate, and provides an effective solution for the problem of industrial data missing.

Automated summary

This paper proposes a multi-feature generation network-based imputation algorithm, which transforms industrial data sequence into Gaussian mixture distribution and imputes the multi-scale features. The experimental results show that the proposed method can reduce the complexity of data generation and improve the imputation accuracy, providing an effective solution for the problem of industrial data missing in the case of high missing rate.