A method for controlling the oxygen content of a combustion process

By using a thermal power oxygen control method based on historical data and leveraging machine learning and real-time error back-calculation of the air-coal ratio, the adaptive problem of traditional thermal power unit oxygen control systems has been solved, achieving high-precision and self-learning intelligent oxygen control, and improving combustion efficiency and stability.

CN122170432APending Publication Date: 2026-06-09SHANDONG DAOHE IOT TECH CO LTD
View PDF 0 Cites 0 Cited by

Patent Information

Authority / Receiving Office
CN · China
Patent Type
Applications(China)
Current Assignee / Owner
SHANDONG DAOHE IOT TECH CO LTD
Filing Date
2026-01-22
Publication Date
2026-06-09

AI Technical Summary

Technical Problem

Traditional oxygen control systems for thermal power units cannot dynamically provide the optimal oxygen setpoint based on load and coal quality changes, resulting in energy efficiency loss and incomplete combustion. Existing control methods lack adaptive and optimization capabilities.

Method used

An optimal oxygen model is established based on historical data. The air-coal ratio is calculated in reverse through real-time error. Machine learning and fitting methods are used to construct the relationship between load and oxygen, achieving high-precision self-learning intelligent oxygen control, including data cleaning, model training and real-time correction.

Benefits of technology

It achieves high precision and stability in oxygen control, improves combustion efficiency, reduces exhaust losses and incomplete combustion losses, and has self-learning capabilities.

✦ Generated by Eureka AI based on patent content.

Smart Images

  • Figure CN122170432A_ABST
    Figure CN122170432A_ABST
Patent Text Reader

Abstract

The present application belongs to the field of coal-fired power generation unit boiler combustion optimization control technology, and particularly relates to a thermal power oxygen quantity control method. The present application establishes an optimal oxygen quantity model under different loads based on historical data, and determines real-time oxygen quantity deviation according to the optimal oxygen quantity, reversely calculates and automatically optimizes the air-coal ratio, takes the air-coal ratio correction quantity as the core feedback parameter of closed-loop control, has the ability of continuous learning and updating in the oxygen quantity control program, and realizes the closed-loop intelligent control of "optimal set value calculation + air-coal ratio reverse calculation + self-learning air-coal ratio parameter".
Need to check novelty before this filing date? Find Prior Art