Comprehensive monitoring of nonlinear processes based on concurrent kernel projection to latent structures

Projection to latent structures (PLS) and concurrent PLS are approaches for solving quality-relevant process monitoring. In this paper, a new approach called concurrent kernel PLS (CKPLS) is presented to detect faults comprehensively for nonlinear processes. The new model divides the nonlinear process and quality spaces into five subspaces: the co-varying, process-principal, process-residual, quality-principal, and quality-residual subspaces. The co-varying subspace reflects nonlinear relationship between quality variables and original process variables. The process-principal and process-residual subspaces reflect the principal variations and residuals, respectively, in the nonlinear process space. Further, the quality-principal and quality-residual subspaces reflect the principal variations and residuals, respectively, in the quality space. The proposed approach is demonstrated by a numerical simulation and an application of the Tennessee Eastman process.

I. Introduction

Data-Driven multivariate statistical process monitoring (MSPM) has been successfully applied to industrial processes for more than twenty years [1]–[10]. Among the well-known MSPM approaches, projection to latent structures (PLS) or partial least squares is commonly used for quality relevant process monitoring. In recent years, the development of concurrent PLS (CPLS) has provided an approach which can comprehensively detect the process faults for linear systems using the division of five subspaces. However, the CPLS cannot reveal nonlinear relationship between process data and quality data.