Classification of states and model order reduction of large scale Chemical Vapor Deposition processes with solution multiplicity. (2nd February 2019)

• Record Type: Journal Article
• Authors: Koronaki, E.D.; Gkinis, P.A.; Beex, L.; Bordas, S.P.A.; Theodoropoulos, C.; Boudouvis, A.G.
• Is Part Of: Computers & chemical engineering. Volume 121(2019)
• Page Start: 148
• Page End: 157
• Publication Date: 2019-02-02
• Subjects: Multiplicity of states -- Support Vector Machines -- Classification -- Reduced order modeling -- Artificial Neural Networks -- Data-driven models -- Chemical Vapor Deposition; Chemical engineering -- Data processing -- Periodicals; 660.0285
• DOI: 10.1016/j.compchemeng.2018.08.023
• Languages: English
• ISSNs: 0098-1354

Abstract

Highlights: A workflow is presented for data-driven equation-free Reduced Order Model. Principal Component Analysis/Artificial Neural Networks are combined for the ROM. Only data from simulations are used to derive the ROM. Data is first classified with the Support Vector Machine algorithm. Method produces fast and accurate results on nonlinear CVD process model. Abstract: This paper presents an equation-free, data-driven approach for reduced order modeling of a Chemical Vapor Deposition (CVD) process. The proposed approach is based on process information provided by detailed, high-fidelity models, but can also use spatio-temporal measurements. The Reduced Order Model (ROM) is built using the method-of-snapshots variant of the Proper Orthogonal Decomposition (POD) method and Artificial Neural Networks (ANN) for the identification of the time-dependent coefficients. The derivation of the model is completely equation-free as it circumvents the projection of the actual equations onto the POD basis. Prior to building the model, the Support Vector Machine (SVM) supervised classification algorithm is used in order to identify clusters of data corresponding to (physically) different states that may develop at the same operating conditions due to the inherent nonlinearity of the process. The different clusters are then used for ANN training and subsequent development of the ROM. The results indicate that the ROM is successful at predicting the dynamic behavior of the system in windows of operating parameters where steady states are not unique.