New Nonlinear Approach for Process Monitoring: Neural Component Analysis

• DOI: 10.1021/acs.iecr.0c02256
• Publication Date: 2020-08-26T18:49:11Z
• Authors: Zhijiang Lou; Youqing Wang
• Keywords: Component (thermodynamics); Component analysis

Nonlinearity is extremely common in industrial processes. For handling the nonlinearity problem, this paper combines artificial neural networks (ANN) with principal component analysis (PCA) and proposes a new (NCA). NCA has similar network structure as ANN adopts gradient descent method for training, hence it same nonlinear fitting ability ANN. Furthermore, PCA's dimension reduction strategy to extract uncorrelated components from process data constructs statistical indices monitoring. The simulation test results show that can successfully data, better performance than other approaches.