Coal-fired unit boiler thermal efficiency prediction and adjustment method, device and system

By constructing a prediction model using heat loss feature vectors and a multi-scale temporal context encoder, the problems of accuracy and adaptability in boiler thermal efficiency prediction were solved, enabling precise energy saving and flexible operation of coal-fired units.

CN122411080APending Publication Date: 2026-07-17SHANDONG ELECTRIC POWER CONSTR NO 2
View PDF 0 Cites 0 Cited by

Patent Information

Authority / Receiving Office
CN · China
Patent Type
Applications(China)
Current Assignee / Owner
SHANDONG ELECTRIC POWER CONSTR NO 2
Filing Date
2026-06-16
Publication Date
2026-07-17

AI Technical Summary

Technical Problem

Existing technologies struggle to accurately capture the core physical correlations and key parameter mappings of boiler thermal efficiency under complex operating conditions, resulting in insufficient accuracy in thermal efficiency prediction. Furthermore, the models are poorly adaptable to changes in operating conditions, failing to meet the needs of flexible operation and precise energy saving for coal-fired units.

Method used

By acquiring boiler operating parameters, constructing a heat loss feature vector, performing data preprocessing and feature matrix construction, and combining a prediction model with a multi-scale temporal context encoder and a composite loss function, accurate prediction and adjustment of boiler thermal efficiency can be achieved.

Benefits of technology

It significantly improves the accuracy of thermal efficiency prediction and the adaptability of the model, enabling early prediction of thermal efficiency decline trends, providing reliable support for regulation decisions, and reducing the difficulty of managing and controlling the efficient operation of the unit.

✦ Generated by Eureka AI based on patent content.

Smart Images

  • Figure CN122411080A_ABST
    Figure CN122411080A_ABST
Patent Text Reader

Abstract

本发明提供了一种燃煤机组锅炉热效率预测与调节方法、装置及系统,涉及人工智能技术领域,基于锅炉的反平衡法热效率计算原理将锅炉运行参数的分散参数转化为与热效率直接相关的热损失特征向量,并基于此进行数据处理,构建目标特征矩阵,可以聚焦于直接决定热效率水平的核心热损失项进行热效率预测,确保热效率影响因素分析结果的可信性与工程适配性。此外,还基于数据的时序上下文信息确定对应预测结果,能根据运行参数‑热损失‑热效率的动态关联规律实现效率变化的提前预判,打破传统事后核算模式,实现运行参数的靶向调节。综上,本发明不仅能够提升热效率预测的精准度与调节的有效性,还能够降低机组高效运行的管控难度。
Need to check novelty before this filing date? Find Prior Art