Sparse Slow Feature Analysis for Enhanced Control Fault Isolation

This paper presents sparse slow feature analysis (SFA) for efficient process monitoring and fault isolation, which is a new latent variable model for time series data. We first recast sparse SFA in terms of a novel regression-type problem, and further incorporate l(1)-norm penalty into the objective in order to promote sparsity. To solve the induced nonconvex optimization problem, a tailored iterative algorithm is developed. With the sparse representation, process variables with insignificant contributions can be completely omitted, and each latent variable relates only to a fraction of crucial process variables in comparison with the generic SFA. A new process monitoring and fault isolation approach is developed based on the sparse SFA, which results in improved monitoring performance, easy-to-interpret diagnostics, and meaningful process, knowledge discovery. Case studies on the Tennessee Eastman process are carried out to address the applicability of the proposed approach.