Distributed monitoring of nonlinear plant-wide processes based on GA-regularized kernel canonical correlation analysis

Fault detection and diagnosis is important for ensuring process safety and is gaining increasing attention in the system safety field. A regularized kernel canonical correlation analysis (RKCCA) approach is proposed for monitoring nonlinear plantwide processes. For each local unit, genetic algorithm (GA)-based regularization is performed to determine the communication variables from neighboring units, which preserves the maximum correlations and eliminates the irrelevant variables. Then variables from a local unit and the communication variables are mapped into high-dimensional feature spaces, and the feature space of the local unit is decomposed into three orthogonal subspaces, namely the residual subspace, the inner subspace, and the outer-related subspace. Monitoring statistics to identify both the process status and the characteristic of a detected fault are constructed. The proposed RKCCA-based monitoring method considers both the information of a local unit and the beneficial information of related units to facilitate fault detection, thereby exhibiting superior performance to some state-of-the-arts methods. Applications on the Tennessee Eastman benchmark process and an industrial tail gas treatment process demonstrate the superiority of RKCCA monitoring.