Enhanced multi-scale convolutional neural network soft measurement method

Abstract

The invention discloses an enhanced multi-scale convolutional neural network soft measurement method, and the method includes performing the data enhancement through reconstructing coarse-grained features, and building a regression model through employing a convolutional neural network; splicing the process variable data in the adjacent time periods to obtain a data matrix which is used as new input of a sample to replace the original fine-grained characteristics, so that the problems of unbalanced process variable sampling and inaccurate input and output correspondence of the sample are solved; using a generative adversarial network for expanding samples, performing data enhancement on an original data set by quantitatively generating the samples, so that the problem of local missing of process data is solved; using a one-dimensional convolution kernel and a two-dimensional convolution kernel to simultaneously carry out feature extraction on coarse-grained features, considering dynamics of variables and time difference between the variables, so the problem of time delay between process variables is solved; reducing data to one dimension through alternate operation of convolution and pooling, building a prediction model through a multi-layer perceptron, and achieving real-time soft measurement of target quality variables.

Description

technical field [0001] The invention belongs to the field of industrial process soft measurement, in particular to an enhanced multi-scale convolutional neural network soft measurement method. Background technique [0002] In the era of industrial big data, data-driven soft sensors have become an important means of guiding industrial production and control. However, in actual industry, different data acquisition methods are different. Most of the process variables in production can be directly measured by the distributed control system (DCS), while some quality variables need to be analyzed by chemical means or professional instruments to obtain value. Meanwhile, the process variable data and the quality variable data are an input value and an output value of one sample, respectively. Due to its high measurement cost, the quantity of quality variable data of industrial products is far less than that of process variable data. Therefore, the unbalanced sampling of different...

AI Technical Summary

Problems solved by technology

[0004] Based on the above three problems, fine-grained features (process variable data at a certain moment) cannot provide effective process information for soft sensor modeling, so good soft sensor results cannot be obtained.

At the same time, when the absolute quantity of quality variable data is considered to be small, and local missing due to some reasons, it will further adversely affect the model

Images