Nonlinear Dynamic Process Robust Monitoring Based on Spatiotemporal Preserving Projections With Rank-Order Distance

The prevalence of nonlinear dynamic characteristics and the interference of outliers are common occurrences in modern industrial systems. However, previous studies have inadequately considered the impact of these factors on process monitoring. This article introduces a hybrid framework, referred to as spatiotemporal preserving projections (STPPs), for fault detection in complex processes. First, the conventional global and local preserving projection (GLPP) has been modified to address the constraints of hyperparameters and improve resilience. This is accomplished by proposing a strategy based on sparse representation to automatically determine local neighborhood in the global and local weight matrices. In addition, a rank-order distance (ROD)-based index is formulated to cope with outliers in the local weight matrix construction. Second, the modified GLPP is combined with slow feature analysis (SFA) to form the STPP method. This enables simultaneous preservation of spatial and temporal data structures in dimension reduction, further enhancing monitoring accuracy. Finally, a numerical case and a wastewater treatment process demonstrate that the proposed STPP-based approach outperforms other relevant methods in fault detection.