Stationarity test and Bayesian monitoring strategy for fault detection in nonlinear multimode processes

Both of multimode and nonlinear characteristics have been common in modern industrial processes. In the present work, an improved monitoring strategy on the basis of a modified discriminant locality preserving projections (DLPP) algorithm and stationary test is proposed for nonlinear multimode process monitoring to analyze both within-mode and cross-mode information. First, the adjoined multiple local models are constructed in high dimensional kernel space to extract within-mode information through kernel fuzzy c-means algorithm and kernel principal components. Afterwards, the weighted local representations are defined by integrating the local latent vectors within each mode and the corresponding posterior probabilities of data samples. Then, a modified DLPP algorithm is developed to preserve the local structure within each mode and separate different modes as far as possible by merging local models into a low-dimensional coordinated space. Augmented Dickey Fuller test (ADF test) strategy is utilized to decompose the final low-dimensional space into two subspaces including mode-specific subspace and mode-common subspace by checking the stability of the final global data. A Bayesian monitoring strategy is presented in mode-specific subspace and residual subspace to provide more reliable monitoring results. Finally, to illustrate the feasibility and effectiveness, the proposed algorithm is illustrated with multimode data generated from the Tennessee Eastman (TE) benchmark process and Three-phase flow process.