Data supplement for a soft sensor using a new generative model based on a variational autoencoder and Wasserstein GAN. (January 2020)

• Record Type: Journal Article
• Authors: Wang, Xiao; Liu, Han
• Is Part Of: Journal of process control. Volume 85(2020)
• Page Start: 91
• Page End: 99
• Publication Date: 2020-01
• Subjects: Soft sensor -- VAE -- GANs -- Generative model; Process control -- Periodicals; Fabrication -- Contrôle -- Périodiques; Process control; Periodicals; Electronic journals; 660.281
• DOI: 10.1016/j.jprocont.2019.11.004
• Languages: English
• ISSNs: 0959-1524

Abstract

Highlights: We propose a generative model named VA-WGAN by integrating a VAE with WGAN to supplement training data for soft sensor modeling. The VA-WGAN generates the same distributions of real data from industrial processes, which is hard to achieve by traditional regression methods. We merge and improve the optimization objectives of the VAE and WGAN to be the loss function of the model. In addition, the training procedure is improved to obtain stable convergence and high-quality generated samples. Abstract: In industrial process control, measuring some variables is difficult for environmental or cost reasons. This necessitates employing a soft sensor to predict these variables by using the collected data from easily measured variables. The prediction accuracy and computational speed in the modeling procedure of soft sensors could be improved with adequate training samples. However, the rough environment of some industrial fields makes it difficult to acquire enough samples for soft sensor modeling. Generative adversarial networks (GANs) and the variational autoencoder (VAE) are two prominent methods that have been employed for learning generative models. In the current work, the VA-WGAN combining VAE with Wasserstein generative adversarial networks (WGAN) as a generative model is established to produce new samples for soft sensors by using the decoder of VAE as the generator in WGAN. An actual industrial soft sensor with insufficient data is used to verify the data generation capability of the proposed model. According to the experimental results, the samples obtained with the proposed model more closely resemble the true samples compared with the other four common generative models. Moreover, the insufficiency of the training data and the prediction precision of soft sensors could be improved via these constructed samples.