Rectification process real-time monitoring method based on online sampling data driving

Abstract

The invention discloses a rectification process real-time monitoring method based on on-line sampling data driving, and aims to drive characteristic transformation in real time according to on-line sampling data so as to realize real-time monitoring of the operation state of a rectification tower by using most representative characteristics. Specifically, the method does not use a fixed projectiontransformation vector to extract features, but uses online data to drive feature analysis and extraction in real time. Compared with the traditional method, the method provided by the invention is very simple and clear to implement, and almost has no off-line modeling stage. The offline modeling stage mainly relates to standardization processing and basis matrix calculation. Secondly, according to the method, aiming at each piece of online measurement sample data, a projection transformation vector which can most distinguish the online measurement sample data from normal working condition data is searched. From this point, the characteristic components extracted by the method are most beneficial to monitoring the fault data. And finally, the superiority of the method in real-time monitoring of the rectifying tower process is verified through a specific embodiment.

Description

technical field [0001] The invention relates to a method for monitoring the running state of a chemical process, in particular to a real-time monitoring method for a rectification process driven by online sampling data. Background technique [0002] Distillation towers are widely used in the petrochemical industry, and their main function is to realize the gas-liquid separation of substances. The control and optimization of rectification towers have been greatly developed in recent years. From the perspective of ensuring the stability of production, the separation of substances in the rectification tower plays a key role in the connection. Therefore, it is very important to maintain the operation of the rectification column under the expected normal working conditions, because it will directly affect the subsequent processing procedures. In recent years, under the background of intelligent manufacturing, the use of chemical big data to realize intelligent chemical productio...

AI Technical Summary

Problems solved by technology

However, it is not known whether these data characteristics play a role in process monitoring

This is mainly because the normal working condition data is abundant and the fault data is seriously lacking. It seems that we can only analyze and extract the characteristics of the normal data.

Images