热力发电

基于物理引导长短期记忆-物理信息神经网络的磨煤机出口温度预测方法

PDF下载

热力发电 | ,():

收起

热力发电 |

基于物理引导长短期记忆-物理信息神经网络的磨煤机出口温度预测方法

全屏

作者信息

通讯作者:

作者简介:

Coal Mill Outlet Temperature Prediction Method Based on Physics-Guided Long Short-Term Memory-Physics-Informed Neural Network

Affiliations

Corresponding Author:

doi: 10.19666/j.rlfd.202609026

文章导航

摘要

收起

【目的】针对磨煤机出口温度预测中数据驱动模型难以同时兼顾预测精度与能量平衡物理一致性的问题，提出一种融合磨煤机物理先验的出口温度预测方法，以提高预测结果的准确性和物理合理性。

【方法】以某350 MW燃煤机组MPS型中速磨煤机运行数据为基础，构建物理引导长短期记忆-物理信息神经网络（Physics-Guided Long Short-Term Memory-Physics-Informed Neural Network，PG-LSTM-PINN）。模型构造风煤比和热风占比以表征风煤匹配及冷热风混合状态，利用工况差异修正时间注意力，在长短期记忆网络（Long Short-Term Memory，LSTM）遗忘门中引入热惯性衰减因子，并依据能量平衡关系构造物理损失。通过模型对比、物理一致性评价、消融、小样本和物理损失权重敏感性实验评价模型性能。

【结果】PG-LSTM-PINN的R²为0.981 1，均方根误差（Root Mean Square Error，δRMSE）和平均绝对误差（Mean Absolute Error，δMAE）分别为0.078 2 ℃和0.061 1 ℃，相比LSTM分别降低50.69%和52.41%；物理残差均方根误差δRMSE,p和物理残差平均绝对误差δMAE,p分别为21.35 kJ/s和16.23 kJ/s。消融实验中，移除任一物理引导模块后，预测误差和物理残差均增大；小样本实验中，PG-LSTM-PINN在各训练比例下均保持较低预测误差；物理损失权重敏感性实验中，η=1.301 3×10⁻⁹时δRMSE最低。

【结论】所提方法能够提高磨煤机出口温度预测精度，减小能量平衡物理残差，并改善训练数据较少条件下的预测表现。

Abstract

收起

[Objective] Data-driven models for coal mill outlet temperature prediction often have difficulty maintaining high prediction accuracy while also satisfying the physical requirement of energy balance. This study proposes an outlet temperature prediction method that incorporates physical priors of the coal mill, with the aim of improving both the numerical accuracy and the physical consistency of the prediction results.

[Methods] Operating data from an MPS medium-speed coal mill in a 350 MW coal-fired generating unit were used to construct a Physics-Guided Long Short-Term Memory-Physics-Informed Neural Network (PG-LSTM-PINN). The method introduces the air-coal ratio and hot-air ratio to represent the matching relationship between primary air and coal feed and the mixing state of hot and cold air. Differences between operating conditions are then used to correct the temporal attention mechanism so that historical information is weighted according to its relevance to the current condition. A thermal-inertia decay factor is embedded in the forget gate of the Long Short-Term Memory (LSTM) network to represent the dynamic influence of the mill thermal process on state updating. In addition, a physical loss is constructed from the energy-balance relationship and incorporated into model training. Model comparison, physical-consistency evaluation, ablation experiments, reduced-training-data experiments, and physical-loss-weight sensitivity experiments were conducted to evaluate the contribution and effectiveness of the proposed method. Together, these experiments evaluate prediction accuracy, energy-balance physical consistency, and performance with limited training data.

[Results] PG-LSTM-PINN achieved a coefficient of determination (R²) of 0.981 1, a root mean square error (δRMSE) of 0.078 2 °C, and a mean absolute error (δMAE) of 0.061 1 °C. Compared with LSTM, its δRMSE and δMAE were reduced by 50.69% and 52.41%, respectively. The physical-residual root mean square error (δRMSE,p) and physical-residual mean absolute error (δMAE,p) were 21.35 kJ/s and 16.23 kJ/s, respectively. In the ablation experiments, removing any physical-guidance module increased both the prediction error and the physical residual, indicating that each module contributed to the overall performance of the complete model. In the reduced-training-data experiments, PG-LSTM-PINN maintained relatively low prediction errors at all tested training proportions. The sensitivity analysis of the physical-loss weight showed that the lowest δRMSE was obtained when η was 1.301 3×10⁻⁹.

[Conclusion] The proposed PG-LSTM-PINN integrates operating-condition representation, temporal information weighting, thermal-inertia modeling, and energy-balance constraints within a unified prediction framework. The results show that it can improve the accuracy of coal mill outlet temperature prediction, reduce the energy-balance physical residual, and provide better prediction performance when the amount of training data is limited.

引用本文

. 基于物理引导长短期记忆-物理信息神经网络的磨煤机出口温度预测方法. 热力发电, : - . DOI: 10.19666/j.rlfd.202609026

. Coal Mill Outlet Temperature Prediction Method Based on Physics-Guided Long Short-Term Memory-Physics-Informed Neural Network[J]. Thermal Power Generation, : - . DOI: 10.19666/j.rlfd.202609026

参考文献

收起

文献

收起

参考文献引证文献

排序方式：

年第卷第期

PDF下载

引用本文

BibTeX

文章信息

doi: 10.19666/j.rlfd.202609026

首发时间：2026-11-03

补充材料

相关文章

文章信息

作者

出版历史

基金

作者信息

参考文献

分享链接

https://castjournals.cast.org.cn/joweb/rlfd/CN/10.19666/j.rlfd.202609026

分享至

全文二维码

扫描看全文

引用本文

BibTeX

本文的引用情况

2种不同金属材料的力学参数

科 Family	属数 Number of genus	种数 Number of species	占总种数比例 Percentage of total species (%)	属 Genus	种数 Number of species	占总种数比例 Percentage of total species (%)
鹅膏菌科Amanitaceae	2	11	5.26	鹅膏菌属 Amanita	10	4.78
小菇科 Mycenaceae	2	12	5.74	丝盖伞属 Inocybe	5	2.39
多孔菌科 Polyporaceae	8	14	6.70	蜡蘑属 Laccaria	5	2.39
红菇科 Russulaceae	3	23	11.00	小皮伞属 Marasmius	6	2.87
				小菇属 Mycena	11	5.26
				光柄菇属 Pluteus	5	2.39
				红菇属 Russula	17	8.13
				栓菌属 Trametes	5	2.39

关闭全屏

BibTeX
EndNote
RefWorks
TxT