Pattern recognition based on dynamic time warping and classification using adaptive rank-order morphological transform

Dynamic Time Warping (DTW) can be used to minimize distance between two sequences which display the same trends but are not perfectly aligned with each other. This feature makes DTW an effective pattern classification method for sequence matching. In Ref. [1], a fault diagnosis method using pattern classification based on adaptive rank-order morphological transform has been proposed. It uses Euclidean distance for measuring the matching degree between two sequences. Based on the method proposed in Ref.[1], this paper substitutes DTW for Euclidean distance metric to measure the matching degree. The proposed pattern classification approaches are applied to studying deterministic fault diagnosis problem in Tennessee Eastman process. Comparative study among the proposed approaches and existing methods is given to provide a comprehensive insight.