Long-term dependency slow feature analysis for dynamic process monitoring

Industrial processes are large scale, highly complex systems. The flow of mass and energy, as well the compensation effects closed-loop control systems, cause significance cross-correlation autocorrelation between process variables. To operate systems stably efficiently, it is crucial to uncover inherent characteristics both variance structure dynamic relationship. Long-term dependency slow feature analysis (LTSFA) proposed in this paper overcome Markov assumption original understand long-term dynamics processes, based on which a monitoring procedure designed. A simulation example Tennessee Eastman benchmark studied show performance LTSFA. method can better extract system monitor variations using fewer features.