Statistical process monitoring via independent component analysis and learning vector quantization method

In this paper, a new method, ICA-LVQ, which integrates two data driven techniques, independent component analysis (ICA) and learning vector quantization (LVQ), for process monitoring is presented. ICA is a recently developed method in which the goal is to decompose observed data into linear combinations of statistically independent components. This method is used as a preprocessing for LVQ neural network (NN) to reduce dimension of observations. LVQ is a supervised learning technique that can be used for classification. The Tennessee Eastman process benchmark is then utilized to evaluate the developed method.