Density peaks clustering‐based steady/transition mode identification and monitoring of multimode processes

Abstract

AbstractMultimode is the characteristic of industrial manufacturing processes due to different production strategies and environments. For multimode process monitoring, it is a challenge to identify different steady modes and transition modes. In this paper, a k nearest neighbours (KNN)‐based density peaks clustering (DPC) method is applied to identify different modes. First, the local density of each sample, which is obtained with a KNN constraint and its minimum distance to the higher local density points are calculated as two indicators of the DPC algorithm to find the cluster centres of the training data. Then, the transition modes are identified by combining the moving window strategy and the DPC algorithm, where an index called the local density‐distance ratio (LDDR) is employed. Finally, the monitoring algorithm is used to detect the faults for each operation mode. The effectiveness and advantages of the proposed method are illustrated by a numerical example and a Tennessee Eastman (TE) benchmark process.