Noise adaptive filtering model integrating spatio-temporal feature for soft sensor

Abstract

Due to uncertain production conditions and external disturbances, there are a lot of noise in the industrial process dataset. Traditional denoising models can only solve a single noise problem. However, the noise in industrial process data has diversity and inhomogeneity. Therefore, the noise adaptive filtering (NAF) model integrating spatio-temporal feature (ST) (ST-NAF) is proposed for the soft sensor, which achieves a balance between noise and data features to reduce the influence of noise on soft sensor results. The gated recurrent unit extracts temporal features of the industrial process data. Then, the dynamically gated graph attention extracts the interaction relationship between monitoring points to obtain spatio-temporal features. Moreover, the NAF converts time-domain features into frequency-domain features, and adaptively selects frequency-domain components with important information through the noise filtering matrix. The selected frequency-domain components are converted to the temporal domain to obtain the denoised spatio-temporal features. Finally, the self-attention learns the dynamic relationships between denoised spatio-temporal features and output variables to predict the key indicator. Compared with other denoising soft sensor models in a public dataset and an actual industrial process dataset, the ST-NAF achieves state-of-the-art results. And the prediction accuracy of the proposed model improved by 4.5% and 10.0% in terms of R2, respectively. Furthermore, the experimental results show that the ST-NAF can adaptively select useful information from industrial noise data to achieve accurate prediction of key indicators.