Condition-driven probabilistic adversarial autoencoder with nonlinear Gaussian feature learning for nonstationary process monitoring. (September 2022)

• Record Type: Journal Article
• Authors: Zhang, Jianfeng; Zhao, Chunhui
• Is Part Of: Journal of process control. Volume 117(2022)
• Page Start: 140
• Page End: 156
• Publication Date: 2022-09
• Subjects: Gaussian feature learning -- Probabilistic adversarial autoencoder -- Nonstationary processes -- Condition-driven mode division; Process control -- Periodicals; Fabrication -- Contrôle -- Périodiques; Process control; Periodicals; Electronic journals; 660.281
• DOI: 10.1016/j.jprocont.2022.07.012
• Languages: English
• ISSNs: 0959-1524

Abstract

Abstract: For industrial processes, the observed data usually has strong nonlinearity and non-Gaussian properties. The whole industrial process shows typical nonstationary characteristics due to frequent time-varying behaviors. This makes the nonstationary process monitoring a challenging task along time direction. It is recognized that the nonstationary process characteristic can change with a certain rule along condition direction instead of time direction. In the present work, a novel condition-driven probabilistic adversarial autoencoder (CPAAE) algorithm is designed to address this problem. CPAAE divides the whole nonstationary process into multiple condition slices by cutting the indicator variables of the industrial process into multiple equal intervals. Subsequently, probabilistic adversarial autoencoder (PAAE) models for different condition slices can be established to extract nonlinear Gaussian features. The condition slices will be aggregated into different condition modes by evaluating the similarity of Gaussian features, and multiple monitoring models can be established for different condition modes to replace the conventional time-driven method. In this way, the nonstationary changes along the time direction can be restored to different condition modes, revealing similar process characteristics in the same condition mode. Finally, the nonstationary industrial process can be monitored by checking the changes of both Gaussian features and reconstruction errors for different condition modes. A numerical case and a real thermal power plant process are adopted to validate the feasibility of the proposed method. Highlights: CPAAE is proposed for monitoring processes with non-Gaussian and nonstationary characteristics. The proposed CPAAE can effectively extract Gaussian manifold features from the nonstationary process. The condition-driven idea is introduced to divide the nonstationary process into condition modes to improve performance. The validity of the proposed method is illustrated with two cases.