Comprehensive Monitoring with Incremental Slow Feature Analysis

Recently, a concurrent monitoring scheme based on slow feature analysis (SFA) has been developed to differentiate operating point changes with process dynamics. The original SFA algorithm requires the data to be fed in as a whole in the training stage and is unsuitable for an increasingly tremendous data volume in modern industries. Other variations have also been developed such as recursive slow feature analysis (RSFA) to process data sequentially, which, however, requires storing, updating, and decomposing two covariance matrices, and increases computational and memory costs. In this work, a new process monitoring scheme is proposed based on a covariance free incremental slow feature analysis (IncSFA) method, which handles massive data efficiently and has a linear feature updating complexity with respect to data dimensionality. The effectiveness of IncSFA-based monitoring method is demonstrated with the Tennessee Eastman Process.