Print Email Facebook Twitter Multi-mode industrial soft sensor method based on mixture Laplace variational auto-encoder Title Multi-mode industrial soft sensor method based on mixture Laplace variational auto-encoder Author Zhang, Tianming (Taiyuan University of Technology) Yan, Gaowei (Taiyuan University of Technology; Shanxi Research Institute of Huairou Laboratory) Li, Rong (Taiyuan University of Technology) Xiao, Shuyi (Taiyuan University of Technology) Pang, Y. (TU Delft Transport Engineering and Logistics) Date 2024 Abstract The industrially collected process data usually exhibit non-Gaussian and multi-mode characteristics. Due to sensor failures, irregular disturbances, and transmission problems, there are unavoidable outliers that make the data exhibit heavy-tailed characteristics. To this end, a variational auto-encoder regression method based on the mixture Laplacian distribution (MLVAER) is proposed, by introducing a type-II multivariate Laplacian distribution in the latent variable space for robust modeling, and further extending it to the mixture form to accommodate multi-mode processes, the corresponding reparameterization trick is finally proposed for the mixture form of this distribution for neural network gradient descent training. The model based on this distribution assumption has higher degrees of freedom than the model based on the traditional multivariate Laplace distribution assumption when the network structure is the same. Numerical simulation and experiments on two industrial examples demonstrate that the proposed algorithm reduces the root mean square error by over 15% compared to other algorithms. Subject Heavy tailMixture LaplaceMulti-modeSoft sensorVariational auto-encoder To reference this document use: http://resolver.tudelft.nl/uuid:37765bba-314a-43f5-a909-2a731e307d70 DOI https://doi.org/10.1016/j.measurement.2024.114435 Embargo date 2024-09-05 ISSN 0263-2241 Source Measurement, 229 Bibliographical note Green Open Access added to TU Delft Institutional Repository 'You share, we take care!' - Taverne project https://www.openaccess.nl/en/you-share-we-take-care Otherwise as indicated in the copyright section: the publisher is the copyright holder of this work and the author uses the Dutch legislation to make this work public. Part of collection Institutional Repository Document type journal article Rights © 2024 Tianming Zhang, Gaowei Yan, Rong Li, Shuyi Xiao, Y. Pang Files file embargo until 2024-09-05