Adversarial autoencoder concurrent projection to latent structure and its application

• Published in: Canadian journal of chemical engineering Vol. 102; no. 1; pp. 274 - 290
• Main Authors: Liu, Dongyu, Zhou, Jinglin, Jiang, Huixia
• Format: Journal Article
• Language: English
• Published: Hoboken, USA John Wiley & Sons, Inc 01-01-2024; Wiley Subscription Services, Inc
• Subjects: adversarial autoencoder; concurrent projection to latent structure; Fault diagnosis; Monitoring; Multivariate analysis; non‐Gaussian; Normal distribution; Orthogonality; Performance indices; process monitoring; Quality control; Statistical analysis; Statistical methods; Tennessee‐Eastman process
• ISSN: 0008-4034; 1939-019X
• DOI: 10.1002/cjce.25025

Multivariate monitoring plays an important role in process monitoring. Among the multivariate monitoring methods, the projection to latent structure method (PLS) has been most widely used in the fields of quality control and fault diagnosis. To improve the monitoring capability of traditional PLS methods in nonlinear and non‐Gaussian multivariate systems, this paper proposes an innovative multivariate monitoring strategy, which combines adversarial autoencoder (AAE) and the concurrent projection to latent structure method (CPLS). In the proposed strategy, the original data are mapped to the high‐dimensional space using the AAE method with the Gaussian prior distribution to realize data transformation. The mapped data are linearly divisible and approach the Gaussian distribution. Then, the projection with orthogonality is realized using the CPLS method. In addition, the reconstruction error and distribution properties are used as evaluation indexes of the high‐dimensional mapping performance. The corresponding monitoring strategy is established using the traditional statistical method based on the Gaussian distribution. Finally, the simulations are performed on the Tennessee‐Eastman process platform, and the results show that the proposed method could efficiently extract the principal components, especially in quality‐relevant fault monitoring.