Process monitoring method based on novel dynamic neighbor preserving embedding algorithm

Abstract

The invention discloses a process monitoring method based on a novel dynamic neighbor preserving embedding algorithm, and aims to solve the problem of how to mine hidden autocorrelation features and local neighbor structure features in training data at the same time and monitor the running state of a production process based on the mining of the hidden autocorrelation features and the local neighbor structure features. The method has the advantages that firstly, the novel dynamic neighbor preserving embedding algorithm involved in the method is a brand-new algorithm, autocorrelation characteristics and local neighbor characteristics are considered at the same time, and hidden useful information in training data can be mined more comprehensively; and secondly, in a specific embodiment, compared with a traditional dynamic process monitoring method, the method provided by the invention can achieve a more excellent effect on fault monitoring. Therefore, the method provided by the inventionis a more optimal dynamic process monitoring method.

Description

technical field [0001] The invention relates to a data-driven process monitoring method, in particular to a process monitoring method based on a novel dynamic neighbor-keeping embedding algorithm. Background technique [0002] Monitoring the operating status of the production process has important scientific research significance to ensure the safe operation of the production process and maintain the stability of product quality. Both academia and industry have invested a lot of manpower and material resources in the research of fault monitoring as the core task. Process monitoring methods. In the past ten years, research on fault detection methods, especially data-driven fault detection methods, has become one of the research hotspots in the field of industrial automation. Generally speaking, the core idea of ​​the data-driven fault detection method is: how to effectively mine the normal data of the process to extract potentially useful information that can reflect the ope...

AI Technical Summary

Problems solved by technology

The disadvantage of using an augmented matrix is ​​that the time-series autocorrelation is confused with the cross-correlation, and the latent feature components extracted are not interpretable

Images