基于多层感知器神经网络的锅炉再热蒸汽温度预测

doi:10.3969/j.issn.1008-0198.2022.01.014

湖南电力 ›› 2022, Vol. 42 ›› Issue (1): 71-75.doi: 10.3969/j.issn.1008-0198.2022.01.014

基于多层感知器神经网络的锅炉再热蒸汽温度预测

陈刚¹, 蒲靖凡², 梅海龙¹, 虞兵¹, 张林¹, 石川¹, 谭鹏²

1.国电汉川发电有限公司,湖北孝感 431616;
2.华中科技大学能源与动力工程学院煤燃烧国家重点实验室,湖北武汉 430074

收稿日期:2021-09-13 修回日期:2021-11-05 发布日期:2025-08-05
作者简介:陈刚(1974),男,湖北武汉人,本科,工程师,主要从事电力系统及其自动化、火电厂生产运营及管理、新能源生产运营、管理及研究工作。

Prediction of Boiler Reheat Steam Temperature Based on Multi-Layer Perceptron Neural Network

CHEN Gang¹, PU Jingfan², MEI Hailong¹, YU Bing¹, ZHANG Lin¹, SHI Chuan¹, TAN Peng²

1. Guodian Hanchuan Power Generation Co., Ltd., Xiaogan 431616, China;
2. State Key Laboratory of Coal Combustion, Huazhong University of Science and Technology, Wuhan 430074, China

Received:2021-09-13 Revised:2021-11-05 Published:2025-08-05

摘要/Abstract

摘要： 为大规模消纳新能源,燃煤电站需要频繁调整负荷,这给再热蒸汽温度控制带来了一些困难。以某1 000 MW超超临界燃煤锅炉为研究对象,利用其历史运行数据,建立基于多层感知器神经网络(MLP)的锅炉再热蒸汽温度预测模型。结果表明,所建立的再热蒸汽温度预测模型均方误差仅0.71℃,在平均相对误差、相关系数、训练用时以及泛化效果都要优于长短时记忆神经网络(LSTM)以及支持向量机(SVM)。将该模型预测结果引入控制器有助于提高再热蒸汽温度控制品质。

关键词: 燃煤锅炉, MLP神经网络, 再热蒸汽温度, 预测模型

Abstract: In order to absorb large-scale new energy into the power network, coal-fired power stations require frequent load adjustments, which brings some difficulties to reheat steam temperature control. Based on the historical operation data of a certain 1 000 MW ultra-supercritical coal-fired boiler, a prediction model of boiler reheat steam temperature based on multi-layer perceptron (MLP) neural network is established. The results show that the mean square error of the reheat steam temperature prediction model is only 0.71℃, which is superior to long and short term(LSTM)neural network and short vector machine (SVM)in mean relative error, correlation coefficient, training time and generalization effect. Introducing the prediction results of the model into the controller is helpful to improve the reheat steam temperature control quality.

Key words: coal-fired boiler, MLP neural network, reheated steam temperature, prediction model

中图分类号:

TK323

陈刚, 蒲靖凡, 梅海龙, 虞兵, 张林, 石川, 谭鹏. 基于多层感知器神经网络的锅炉再热蒸汽温度预测[J]. 湖南电力, 2022, 42(1): 71-75.

CHEN Gang, PU Jingfan, MEI Hailong, YU Bing, ZHANG Lin, SHI Chuan, TAN Peng. Prediction of Boiler Reheat Steam Temperature Based on Multi-Layer Perceptron Neural Network[J]. Hunan Electric Power, 2022, 42(1): 71-75.

参考文献

[1] 路澍柘. 浅谈在碳中和环境下的燃煤电厂的未来趋势[J]. 科技经济市场, 2021(5): 139-140.
[2] 推动能源结构转型构建清洁低碳安全高效能源体系——两会代表、委员为能源行业转型发展建言献策[J]. 中国煤炭工业, 2021(4): 30-31.
[3] 赵兵,景杰. “碳达峰、碳中和”目标下火力发电行业的转型与发展[J]. 节能与环保, 2021(5): 32-33.
[4] 李琳, 张芬芬, 闫东海,等. 330 MW燃煤锅炉蒸汽超温分析研究[J]. 山东电力高等专科学校学报, 2020, 23(6): 59-62.
[5] 李胜男. 灵活性运行下燃煤发电机组热力系统建模研究[D].武汉: 华中科技大学, 2020.
[6] 金志远, 李胜男, 谭鹏,等. 基于长短时记忆神经网络的锅炉多参数协同预测模型[J]. 热力发电, 2021, 50(5): 120-126.
[7] 赵佳鹏, 韩月皎, 翟永杰. 基于LS-SVM的再热汽温趋势预测与控制优化[J]. 计算机仿真, 2016, 33(5): 145-147,170.
[8] LiuZ, Jiang S, Yang H, et al. The prediction research of steam reheating temperature in power plants based on LS-SVM[J]. Proc SPIE, 2013: 8919.
[9] 华菁云. 高维时序数据下考虑时延的火电再热汽温预测[C]//用电与能效专题讲座暨智能用电及能效管理技术研讨会, 2019, 南京, 中国. 中国电力科学研究院:北京市海淀区太极计算机培训中心, 2019: 6.
[10] Gui N, Lou J, Qiu Z, at el. Temporal Feature Selection for Multi-Step Ahead Reheater Temperature Prediction[J]. Processes, 2019, 7(7): 473.
[11] Rosenblatt F. The perceptron: a probabilistic model for information storage and organization inthe brain[J]. Psychological Review, 1958, 65: 386-408.
[12] Atkinson P M,Tatnall A. Introduction neural networks in remote sensing[J]. International Journal of Remote Sensing, 1997, 18(4): 699-709.
[13] Ammar H E,Swellam W, Mohamed A E, et al. Modeling of solar energy systems using artificial neural network: A comprehensive review[J]. Solar Energy, 2019, 180: 622-639.
[14] Ma S,Sigal L, Sclaroff S. Learning Activity Progression in LSTMs for Activity Detection and Early Detection[C]//2016 IEEE Conference on Computer Vision and Pattern Recognition (CVPR), 2016, Beijing, China. IEEE, 2016: 1942-1950.
[15] Kingma D, Ba J. Adam. A Method for Stochastic Optimization[C]//3rd International Conference on Learning Representations, 2015, San Diego, Chile. Cornell University, 2015: 1-15.

基于多层感知器神经网络的锅炉再热蒸汽温度预测

Prediction of Boiler Reheat Steam Temperature Based on Multi-Layer Perceptron Neural Network

PDF (PC)

可视化

摘要/Abstract

引用本文

使用本文

参考文献

相关文章 3

编辑推荐

Metrics

本文评价

[1]	文思伦, 张楚岩, 刁明光, 周振安, 徐惠勇, 刘慧芳. 基于LSTM和ArcGIS的区域输电网污秽状态智能评估方法[J]. 湖南电力, 2024, 44(3): 55-63.
[2]	杜伟春, 罗宏波, 杨楠. 改进灰色预测模型在电力负荷预测中的应用[J]. 湖南电力, 2023, 43(3): 88-93.
[3]	邓怡卿, 孙斌, 李晓兵, 李丹, 王嵘婧. 基于大数据的输变电工程造价趋势预测[J]. 湖南电力, 2023, 43(2): 108-111.