Looking for breakthrough ideas for innovation challenges? Try Patsnap Eureka!

Glass furnace temperature control method based on deep learning and reinforcement learning

A temperature control method and reinforcement learning technology, applied in the direction of temperature control using electric methods, auxiliary controllers with auxiliary heating devices, etc., can solve the problems of untimely and inaccurate manual adjustment, achieve good prediction and control, and overcome The effect of concept drift

Active Publication Date: 2019-08-30
WUHAN UNIV OF TECH
View PDF6 Cites 26 Cited by
  • Summary
  • Abstract
  • Description
  • Claims
  • Application Information

AI Technical Summary

Problems solved by technology

At the same time, it can solve the problems of manual adjustment not being timely and inaccurate

Method used

the structure of the environmentally friendly knitted fabric provided by the present invention; figure 2 Flow chart of the yarn wrapping machine for environmentally friendly knitted fabrics and storage devices; image 3 Is the parameter map of the yarn covering machine
View more

Image

Smart Image Click on the blue labels to locate them in the text.
Viewing Examples
Smart Image
  • Glass furnace temperature control method based on deep learning and reinforcement learning
  • Glass furnace temperature control method based on deep learning and reinforcement learning
  • Glass furnace temperature control method based on deep learning and reinforcement learning

Examples

Experimental program
Comparison scheme
Effect test

Embodiment Construction

[0021] The technical solution of the present invention will be described in detail below in conjunction with the drawings and embodiments.

[0022] The invention provides a kiln temperature control method based on deep learning and reinforcement learning, which adjusts the valve openings of oxygen and natural gas in the kiln according to the set values ​​of each key temperature point, so that the temperature environment of the kiln remains stable. This method uses a deep neural network to establish a kiln temperature simulation model based on key characteristic quantities such as kiln historical temperature, pressure, natural gas and oxygen flow, and valve opening, which is used to simulate the kiln temperature change environment. Based on the temperature simulation model, according to the real-time environment of the current kiln temperature, pressure, fuel concentration, etc., combined with deep neural network and reinforcement learning algorithm, the kiln temperature control...

the structure of the environmentally friendly knitted fabric provided by the present invention; figure 2 Flow chart of the yarn wrapping machine for environmentally friendly knitted fabrics and storage devices; image 3 Is the parameter map of the yarn covering machine
Login to View More

PUM

No PUM Login to View More

Abstract

The invention provides a glass furnace temperature control method based on deep learning and reinforcement learning. The method comprises the following steps: establishing a temperature simulation model and a temperature control model through a total-oxygen glass kiln furnace taking natural gas and oxygen as fuel, and maintaining the stabilization of the kiln temperature by regulating a fuel valve; collecting temperature, oxygen flow, natural gas flow, natural gas valve openness, natural gas valve opening and kiln pressure at each key point of the kiln through a sensor; establishing a kiln temperature simulation model by using a deep neural network, thereby simulating the kiln temperature change environment; establishing a kiln temperature control model based on the deep learning and reinforcement learning, and outputting the offset needing to be adopted by the natural gas and oxygen valves in real time according to the current furnace state by using two established models. By utilizing the historic kiln data, the temperature simulation model and the temperature control model are online or periodically updated, thereby reaching precise temperature control.

Description

technical field [0001] The invention relates to the technical field of temperature intelligent control of a glass melting furnace, in particular to a method for controlling the temperature of a glass melting furnace based on deep learning and reinforcement learning. Background technique [0002] The generation process of a glass melting furnace combines a large number of physical reactions and chemical reactions. If it is to be modeled, it will be a complex nonlinear system with many distributed parameters, and the process is very difficult, so it is difficult to control it precisely. At present, the method of controlling various parameters of glass melting furnaces in my country is single-loop PID control, and PID means proportional-integral-derivative controller. Traditional PID controllers are widely used in industry due to their effectiveness for linear systems, ease of design and low cost. Yamamoto and Hashimoto reported in 1991 that, for example, in Japan, more than 9...

Claims

the structure of the environmentally friendly knitted fabric provided by the present invention; figure 2 Flow chart of the yarn wrapping machine for environmentally friendly knitted fabrics and storage devices; image 3 Is the parameter map of the yarn covering machine
Login to View More

Application Information

Patent Timeline
no application Login to View More
Patent Type & Authority Applications(China)
IPC IPC(8): G05D23/32
CPCG05D23/32
Inventor 邹承明杨鹏程姜德生
Owner WUHAN UNIV OF TECH
Who we serve
  • R&D Engineer
  • R&D Manager
  • IP Professional
Why Patsnap Eureka
  • Industry Leading Data Capabilities
  • Powerful AI technology
  • Patent DNA Extraction
Social media
Patsnap Eureka Blog
Learn More
PatSnap group products

Browse by: Latest US Patents, China's latest patents, Technical Efficacy Thesaurus, Application Domain, Technology Topic, Popular Technical Reports.

© 2024 PatSnap. All rights reserved.Legal|Privacy policy|Modern Slavery Act Transparency Statement|Sitemap|About US| Contact US: help@patsnap.com