Slow feature analysis-independent component analysis based integrated monitoring approach for industrial processes incorporating dynamic and static characteristics

Considering dynamic and static characteristics in industrial processes, this paper proposed an integrated monitoring approach based on slow feature analysis and independent component analysis (SFA-ICA), which can fully take advantage of SFA and ICA in extracting dynamic features and static non-Gaussian features. A sequential correlation-based matrix for each variable is first calculated to evaluate the dynamics of the process variable, in which, the variables with weak autocorrelation and cross-correlation are considered as static variables, while the others are dynamic variables. Then, the ICA and SFA algorithms are built for the static and dynamic subspaces. The statistics from each of the subspaces are combined using Bayesian inference to give a final comprehensive statistic. The proposed SFA-ICA monitoring approach is applied to a numerical example, the Tennessee Eastman (TE) process and the continuous stirred tank reactor (CSTR) process. Results show that the SFA-ICA achieves the better fault detection rates for the numerical example, the CSTR process, and several typical faults for TE process.