Abstract
The variational autoencoder (VAE) has garnered extensive attention in the field of soft sensor modeling due to its superior capabilities in probabilistic data description and feature extraction. However, a single-layer VAE is challenging to extract higher-level features in the face of strong nonlinear process data. This paper proposes a gated stacked target-supervised VAE with variable weights (W-GSTVAE) to improve the modeling prediction performance of VAE. First, a stacked VAE is employed to enhance the feature extraction capability. In the pretraining phase, to enhance the correlation between the features and the target variable, feature learning is guided by incorporating the prediction error of target values into the loss function as well as calculating the maximum information coefficient between input and target variables. Meanwhile, in the fine-tuning phase, to make full use of shallow features, gated linear units are used to integrate the output features of each layer, fully exploiting the information from all layers. Finally, the effectiveness and superiority of the proposed model is demonstrated through two real industrial cases.
Published Version
Talk to us
Join us for a 30 min session where you can share your feedback and ask us any queries you have
Schedule a call