Unlock instant, AI-driven research and patent intelligence for your innovation.

Heating appliance control system based on reinforcement learning

A technology for enhancing learning and heating appliances, which is applied in temperature control using digital devices, neural learning methods, and temperature control using electric methods. It can solve problems such as large deviation of target temperature and resistance error, and achieve reliable temperature control. Effect

Active Publication Date: 2020-07-28
SICHUAN SANLIAN NEW MATERIAL CO LTD +1
View PDF17 Cites 1 Cited by
  • Summary
  • Abstract
  • Description
  • Claims
  • Application Information

AI Technical Summary

Problems solved by technology

Through this method, it is easily affected by the resistance error of the heating element heating wire, resulting in a large deviation of the target temperature, and the temperature can only be adjusted through later calibration

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
  • Heating appliance control system based on reinforcement learning
  • Heating appliance control system based on reinforcement learning
  • Heating appliance control system based on reinforcement learning

Examples

Experimental program
Comparison scheme
Effect test

Embodiment

[0024] In order to solve the problem that the control system of the heating appliance for heating cigarettes is easily affected by the resistance error of the heating element heating wire, resulting in a large deviation of the target temperature, the embodiment provides a heating appliance control system based on reinforcement learning, such as figure 1 As shown, including voltage module, current module, state generation module and reinforcement learning module, among them:

[0025] The voltage module is used to collect and output the voltage value of the heating element heating wire in real time.

[0026] The current module is used to collect and output the current value of the heating element heating wire in real time.

[0027] The state set generation module is used to extract the resistance feature through the convolutional neural network (CNN) through the voltage value and the current value to generate the state set. The CNN network can be implemented on FPGA or arm chip...

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 relates to the field of electric heaters, and discloses a heating appliance control system based on reinforcement learning, which is used for realizing more accurate temperature controland ensuring the temperature consistency of heating appliances. The system comprises a voltage module used for collecting and outputting a voltage value of a heating wire of a heating element in realtime, a current module used for collecting and outputting a current value of the heating wire of the heating element in real time, a state generation module used for extracting resistance features ofthe voltage value and the current value through a convolutional neural network to generate a state set, and a reinforcement learning module comprising a reinforcement learning network used for learning a state conversion strategy by taking the state set as input to obtain a PWM output instruction, wherein the method for generating the state set comprises the steps of respectively constructing one-dimensional vectors for the collected voltage and current values, carrying out row direction splicing on the one-dimensional vectors according to a fixed rule, encoding the one-dimensional vectors into a sparse matrix, and fusing the sparse matrix with the extracted resistance features to obtain the state set. The system is applicable to heating appliances for cigarettes.

Description

technical field [0001] The invention relates to the field of electric heaters, in particular to a control system for heating appliances based on reinforcement learning. Background technique [0002] With the continuous improvement of consumers' pursuit of quality of life and health, new tobacco products aimed at reducing the release of harmful components and the risk of smoking have received widespread attention in recent years, showing explosive growth. The new tobacco products represented by heated cigarettes have changed the consumption mode of traditional tobacco smoking, and have attracted more consumers’ attention and acceptance due to their low release of harmful components, safety and friendliness, and good smoking experience. [0003] The heating appliance is an indispensable supporting electronic product for smoking heated cigarettes, and the accuracy of its temperature control is the key to affecting the smoking experience of heated cigarettes. Most of the curren...

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
IPC IPC(8): G05D23/19G06N3/04G06N3/08
CPCG05D23/1917G06N3/08G06N3/045
Inventor 包毅黄玉川汤磊韩咚林赵德清郑怡谢力
Owner SICHUAN SANLIAN NEW MATERIAL CO LTD