Abstract
Traditional centralized multivariate statistical methods are no longer suitable for monitoring complex industrial processes. A distributed process monitoring framework based on independent component analysis (ICA), principal component analysis (PCA) and Bayesian inference is proposed in this paper. It overcomes the shortcoming that the monitoring variables of the PCA method are required to satisfy the assumption of independent Gaussian distribution. First, the performance-driven multiblock ICA method and genetic optimization (GA) algorithm are used for optimal process decomposition. Then, Bayesian comprehensive inference statistics is calculated to fuse the information of local ICA-PCA models. System anomalies can be discovered using the decisions made by the fusion center. The practicability of the distributed method is verified based on Tennessee Eastman process in the end.
Talk to us
Join us for a 30 min session where you can share your feedback and ask us any queries you have
Schedule a callDisclaimer: All third-party content on this website/platform is and will remain the property of their respective owners and is provided on "as is" basis without any warranties, express or implied. Use of third-party content does not indicate any affiliation, sponsorship with or endorsement by them. Any references to third-party content is to identify the corresponding services and shall be considered fair use under The CopyrightLaw.
