The chemical process monitoring method based on temporal extended orthogonal neighbourhood preserving embedding (TONPE)

Abstract

Due to the high dimensionality, non‐linearity and dynamic characteristics of chemical process data, a fault monitoring method based on temporal extension orthogonal neighbourhood preserving embedding (TONPE) is proposed. In order to make up for the shortcomings of the orthogonal neighbourhood preserving embedding (ONPE) algorithm, an information extraction strategy based on spatio‐temporal structure is developed. First, a local neighbourhood set with spatio‐temporal characteristics is established, and a weight matrix with spatio‐temporal is reconstructed for each time point through the nearest neighbour in space and time. Then, a projection matrix with orthogonal constraints is obtained to establish a monitoring model. The TONPE algorithm can fully capture the local dynamic changes of high‐dimensional data by extracting two different manifold features, so that the low‐dimensional space has better performance capabilities. The simulation results of the continuous stirred tank reactor process and the Tennessee Eastman process verify the effectiveness of the TONPE algorithm in chemical process monitoring.