A method and system for environmental control of glass melting furnace based on causal reasoning

Abstract

The invention provides a method and a system for controlling the environment of a glass melting furnace based on causal reasoning, which is used for an all-oxygen glass furnace melting furnace using natural gas and oxygen as fuel, and the time series data of glass melting furnace related parameters and glass quality time series data collected by sensors The sparse causal model is obtained through the conditional selection algorithm; the sparse causal model is used as the input, and the sparse causal model with the false positive causal association removed is obtained through the instantaneous conditional independence test; based on information theory, the concept of source entropy is used to measure the causal strength , and give corresponding control decisions according to the causal strength. For the glass melting furnace environment with high-dimensional, nonlinear time series and time lag characteristics, the invention can reason about the time-lag causal relationship; and can quantify the strength of the causal relationship, and provide decision support suggestions for the environmental control of the glass melting furnace.

Description

technical field [0001] The invention relates to the technical field of glass melting furnace environment control, in particular to a method and system for glass melting furnace environment control based on causal reasoning. Background technique [0002] Glass melting furnace is a complex system accompanied by various physical and chemical reactions. During the clarification and homogenization process in the melting pool or forehearth, the glass liquid needs to be kept in a specific temperature range stably for a long time. In order to obtain good glass in industry Quality requires some control of the environment inside the furnace. At present, the traditional PID control technology is mainly used in related fields in my country. This technology is relatively inexpensive and easy to design, but for a system with high dimensions, nonlinearity and time lag, such as a furnace, the control effect is not ideal, making it difficult to produce high-quality glass. In addition, many...

AI Technical Summary

Problems solved by technology

[0004] Although these improved algorithms perform well under experimental simulation conditions, they cannot achieve good performance in practical applications.

One is that the complex furnace environment cannot be perfectly simulated; the other is that the neural network-based machine learning algorithm cannot explain causality and is not convincing for actual production decisions

Images