Chemical engineering system multi-working-condition fault detection method based on local adaptive standardization

Abstract

The invention relates to a chemical system multi-working-condition fault detection method based on local adaptive standardization and belongs to the technical field of chemical process monitoring, industrial data processing and process system engineering. According to the method, a local adaptive standardization method is provided, the variational automatic encoder technology of the deep neural network is applied, an average value of the data in the local moving window is calculated to serve as an average value parameter of local adaptive standardization, different average values are used fordifferent data, and the adaptive capacity is achieved. The method is advantaged in that local adaptive standardization processing is utilized, and fault detection is carried out by detecting whether the data in a local moving window deviates or not, and the method can be suitable for any working condition, has higher accuracy and stronger generalization ability, can meet the requirement of real-time detection, and avoids chemical accidents or reduces the harm caused by accidents through early warning of faults.

Description

technical field [0001] The invention relates to a multi-working-condition fault detection method for a chemical system based on local adaptive standardization, and belongs to the technical fields of chemical process monitoring, industrial data processing and process system engineering. Background technique [0002] Safety production in the petrochemical industry involves all aspects of the chemical life cycle. Due to the large-scale production of chemicals and the concentrated distribution of personnel, once an accident occurs, it will cause serious property losses, casualties and environmental damage. With the continuous progress and promotion of information technology, the chemical industry has entered the era of big data. Fault detection technology is the basic key technology in the field of chemical process safety. Its purpose is to distinguish whether the chemical system is in a normal operation state or a failure by collecting and analyzing real-time data of the indust...

AI Technical Summary

Problems solved by technology

Once the chemical process is running under a new working condition, there is no neighbor data in the historical data, and the fault detection task still cannot be completed

So far, there is no universal fault detection method capable of monitoring all operating conditions of chemical processes

Images