Just-in-time framework for robust soft sensing based on robust variational autoencoder

• Published in: Journal of process control Vol. 143; p. 103325
• Main Authors: Guo, Fan, Liu, Kun, Huang, Biao
• Format: Journal Article
• Language: English
• Published: Elsevier Ltd 01.11.2024
• Subjects: Just-in-time learning; Robust Kullback-Leibler divergence; Robust PPCR; VAE with Student’s t-prior; Robust Kullback-Leibler divergence; Robust PPCR; VAE with Student’s t-prior; Just-in-time learning
• ISSN: 0959-1524
• DOI: 10.1016/j.jprocont.2024.103325

Modeling with high-dimensional data subject to abnormal observations have always been a practical interest. In this paper, under the just-in-time learning (JITL) framework, a robust soft sensor modeling approach is developed based on robust Variational Autoencoder (VAE). Unlike the vanilla VAE that extracts features from the given dataset under the Gaussian prior assumption, robust VAE employs Student’s t-distribution as prior distribution to handle abnormal data. Under assumption of the Student’s t-prior, the proposed robust VAE model is capable of describing collected data contaminated with outliers. Once the robust VAE model is trained, each robust feature variable in the latent space can be determined. Subsequently, similarity measure is calculated using robust Kullback-Leibler divergence between two Student’s t-distributions, that is, the distribution of a new data sample and that of each historical data sample. After completing similarity measurement for a query sample, the weights for input-output historical data can be determined. Based on these weighted historical data samples, a robust probabilistic principal component regression (PPCR) is utilized to perform local modeling for prediction. Numerical simulations, including the Tennessee Eastman and Penicillin fermentation benchmark processes, are utilized to validate the proposed JITL-based robust soft sensor modeling method. •Under the JITL framework, a robust soft sensor modeling approach is developed based on robust VAE.•Once the robust VAE model is trained, each robust feature variable in the latent space can be determined.•Numerical simulations and two processes are utilized to validate the effectiveness of the proposed method.