A multi-brand chemical process soft sensor modeling method for automatically generating samples

Abstract

A multi-brand chemical process soft-sensing modeling method for automatically generating samples, comprising the following steps: (1) using data collected from multi-brand chemical processes as original data, and dividing them into training sets and test sets; (2) establishing The generated confrontation network AGAN based on gradient penalty and Wasserstein distance input the divided training set into the established generative confrontation network to train the network; (3) use the trained AGAN to generate virtual samples, and combine them with the original training set Form a new training set; (4) Use the new training set as the driving data to conduct soft sensor modeling training, adjust the soft sensor model parameters to adapt to the new training set, and use the trained soft sensor model to carry out multi-brand chemical process Prediction of key quality variables. The invention utilizes the automatically generated confrontation network to generate data to make up for the lack of data volume, and improves the prediction accuracy of the data-driven soft sensor model.

Description

technical field [0001] The invention relates to the field of soft sensor modeling of chemical process, in particular to a method for soft sensor modeling of multi-brand chemical process based on generative confrontation network. Background technique [0002] In the chemical process, the estimation of the key quality variables of the process plays an important role in the continuous and stable operation of the production device, the guarantee of product quality and the full use of the production capacity of the device. However, some important quality variables are difficult to measure directly with online sensors, such as the activity of catalysts, the melt index of polymers, certain quality indicators of petroleum and petrochemical products, and the concentration of bacteria and products in fermentation processes, so soft sensors are required modeling methods to predict it. [0003] In the case of a deep understanding of chemical process technology and known mechanism, mech...

AI Technical Summary

Problems solved by technology

[0005] In order to overcome the shortcomings of high data acquisition cost and low prediction accuracy of the existing multi-brand chemical process soft-sensing method, the present invention provides a multi-brand chemical process soft-sensing modeling method that automatically generates samples, using gradient penalty and Wasserstein The Automatically Generated Adversarial Network (AGAN for short) of the distance generates data to make up for the lack of data volume and improve the prediction accuracy based on the data-driven soft sensor model

Images