基于注意力机制与神经网络的热电联产锅炉负荷预测

doi:10.16183/j.cnki.jsjtu.2021.346

上海交通大学学报 ›› 2023, Vol. 57 ›› Issue (3): 316-325.doi: 10.16183/j.cnki.jsjtu.2021.346

所属专题：《上海交通大学学报》2023年“机械与动力工程”专题

基于注意力机制与神经网络的热电联产锅炉负荷预测

万安平¹, 杨洁¹^,², 缪徐¹, 陈挺¹(), 左强¹, 李客²^,³

1.浙大城市学院机电系,杭州 310015
2.浙江大学机械工程学院,杭州 310027
3.中信重工机械股份有限公司,河南洛阳 471039

收稿日期:2021-09-08 接受日期:2021-11-10 出版日期:2023-03-28 发布日期:2023-03-30
通讯作者: 陈挺(1989-),博士研究生,博士后;E-mail:chenting@zucc.edu.cn.
作者简介:万安平(1983-),博士后,副教授,主要从事热电联产机组负荷预测与运行优化研究.
基金资助:
国家自然科学基金项目(51705455);浙江省教育厅教师专业发展项目(FX2021111);广东省海洋经济发展(海洋六大产业)专项资金项目(GDNRC[2022]28);杭州市农业与社会发展科研计划重点项目(20212013B04);浙江省基础公益研究计划项目(LGG20E050007)

Boiler Load Forecasting of CHP Plant Based on Attention Mechanism and Deep Neural Network

WAN Anping¹, YANG Jie¹^,², MIAO Xu¹, CHEN Ting¹(), ZUO Qiang¹, LI Ke²^,³

1. Department of Mechanical Engineering, Zhejiang University City College, Hangzhou 310015, China
2. School of Mechanical Engineering, Zhejiang University, Hangzhou 310027, China
3. CITIC Heavy Industries Co., Ltd., Luoyang 471039, Henan, China

Received:2021-09-08 Accepted:2021-11-10 Online:2023-03-28 Published:2023-03-30

摘要/Abstract

摘要：

热电联产机组的锅炉负荷准确预测对电厂生产管理及调度有直接作用.基于注意力机制和深度卷积-长短期记忆网络原理,提出一种新的热电联产长期负荷预测模型,该模型以锅炉出口蒸汽流量(负荷)历史数据和多维负荷影响因素为输入,对负荷进行长期预测.利用Pearson相关系数判定对原始数据进行筛选;将处理后的数据经卷积层进行特征提取和进一步降维,通过长短期记忆层进行拟合,并采取注意力机制对权值进行优化,实现对负荷的精准预测.以浙江桐乡电厂实测数据为例进行验证,结果表明所提方法的平均绝对百分比误差小于1%,能够实现锅炉负荷的精准预测,智能算法在热电联产领域的应用具有一定的借鉴意义.

关键词: 热电联产, 注意力机制, 卷积神经网络, 长短期记忆, 负荷预测

Abstract:

Accurate boiler load forecasting of cogeneration units plays a direct role in production management and dispatching of power plants. A long-term load forecasting model of combined heat and power (CHP) based on attention mechanism and the deep convolution long-short-term memory network (CNN-LSTM-AM) is proposed, which takes the historical data of boiler outlet steam flow (load) and multi-dimensional load influence factors as input to make long-term load forecasting. First, the original data is screened by Pearson correlation coefficient judgment. Then the processed data is processed by convolution layer for feature extraction and further dimensionality reduction, fitted through long-term and short-term memory layer, and optimized the weight by adopting attention mechanism, so as to achieve accurate load forecasting. The proposed model is verified by the measured data of Tongxiang Power Plant in Zhejiang Province. The results show that the MAPE of the proposed method is less than 1%. It can realize the accurate prediction of boiler load, which has a certain reference significance for the application of intelligent algorithm in the field of combined heat and power.

Key words: combined heat and power (CHP), attention mechanism (AM), convolution neural network (CNN), long-short term memory (LSTM), load forecasting

中图分类号:

TK14

万安平, 杨洁, 缪徐, 陈挺, 左强, 李客. 基于注意力机制与神经网络的热电联产锅炉负荷预测[J]. 上海交通大学学报, 2023, 57(3): 316-325.

WAN Anping, YANG Jie, MIAO Xu, CHEN Ting, ZUO Qiang, LI Ke. Boiler Load Forecasting of CHP Plant Based on Attention Mechanism and Deep Neural Network[J]. Journal of Shanghai Jiao Tong University, 2023, 57(3): 316-325.

图/表 12

图1

图2

图3

图4

图5

表1

图6

图7

图8

图9

图10

图11

参考文献 21

[1]	陈向国. 智慧供热引领供热行业发展新方向[J]. 节能与环保, 2021(3): 22-25.
	CHEN Xiangguo. Smart heating leads the new development direction of heating industry[J]. Energy Conservation & Environmental Protection, 2021 (3): 22-25.
[2]	陈新和, 裴玮, 邓卫, 等. 数据驱动的虚拟电厂调度特性封装方法[J]. 中国电机工程学报, 2021, 41(14): 4816-4828.
	CHEN Xinhe, PEI Wei, DENG Wei, et al. Data-driven virtual power plant dispatching characteristic packing method[J]. Proceedings of the CSEE, 2021, 41(14): 4816-4828.
[3]	许可. 母管制热电机组热力系统建模与负荷优化分配[D]. 杭州: 浙江大学, 2020.
	XU Ke. Thermal system modeling of main-pipeline cogeneration unit and combined heat and power optimized distribution[D]. Hangzhou: Zhejiang University, 2020.
[4]	DUDZIK W, NALEPA J, KAWULOK M. Evolving data-adaptive support vector machines for binary classification[J]. Knowledge-Based Systems, 2021, 227: 107221.
[5]	YANG J, ZHANG T Z, HONG J C, et al. Research on driving control strategy and Fuzzy logic optimization of a novel mechatronics-electro-hydraulic power coupling electric vehicle[J]. Energy, 2021, 233: 121221.
[6]	IMANI M. Electrical load-temperature CNN for residential load forecasting[J]. Energy, 2021, 227: 120480.
[7]	KUMAR D, MATHUR H D, BHANOT S, et al. Forecasting of solar and wind power using LSTM RNN for load frequency control in isolated microgrid[J]. International Journal of Modelling and Simulation, 2021, 41(4): 311-323. doi: 10.1080/02286203.2020.1767840 URL
[8]	REZAEE M J, DADKHAH M, FALAHINIA M. Integrating neuro-fuzzy system and evolutionary optimization algorithms for short-term power generation forecasting[J]. International Journal of Energy Sector Management, 2019, 13(4): 828-845. doi: 10.1108/IJESM-09-2018-0015 URL
[9]	KARABIBER A, ALÇIN Ö F. Short term PV power estimation by means of extreme learning machine and support vector machine[C]// 2019 7th International Istanbul Smart Grids and Cities Congress and Fair. Istanbul, Turkey: IEEE, 2019: 41-44.
[10]	TAN Z F, DE G, LI M L, et al. Combined electricity-heat-cooling-gas load forecasting model for integrated energy system based on multi-task learning and least square support vector machine[J]. Journal of Cleaner Production, 2020, 248: 119252.
[11]	ZYMEŁKA P, SZEGA M. Short-term scheduling of gas-fired CHP plant with thermal storage using optimization algorithm and forecasting models[J]. Energy Conversion and Management, 2021, 231: 113860.
[12]	刘亚珲, 赵倩. 基于聚类经验模态分解的CNN-LSTM超短期电力负荷预测[J]. 电网技术, 2021, 45(11): 4444-4451.
	LIU Yahui, ZHAO Qian. Ultra-short-term power load forecasting based on cluster empirical mode decomposition of CNN-LSTM[J]. Power System Technology, 2021, 45(11): 4444-4451.
[13]	陆继翔, 张琪培, 杨志宏, 等. 基于CNN-LSTM混合神经网络模型的短期负荷预测方法[J]. 电力系统自动化, 2019, 43(8): 131-137.
	LU Jixiang, ZHANG Qipei, YANG Zhihong, et al. Short-term load forecasting method based on CNN-LSTM hybrid neural network model[J]. Automation of Electric Power Systems, 2019, 43(8): 131-137.
[14]	OKAMURA H, OSADA Y, NISHIJIMA S, et al. Novel robust time series analysis for long-term and short-term prediction[J]. Scientific Reports, 2021, 11: 11938. doi: 10.1038/s41598-021-91327-8 pmid: 34099758
[15]	FENG G L, ZHANG L Y, YANG J H, et al. Long-term prediction of time series using fuzzy cognitive maps[J]. Engineering Applications of Artificial Intelligence, 2021, 102: 104274.
[16]	ZHANG G, BAI X Q, WANG Y X. Short-time multi-energy load forecasting method based on CNN-Seq2Seq model with attention mechanism[J]. Machine Learning With Applications, 2021, 5: 100064.
[17]	JIN Y L, TAN E L, LI L, et al. Hybrid traffic forecasting model with fusion of multiple spatial toll collection data and remote microwave sensor data[J]. IEEE Access, 2018(6): 79211-79221.
[18]	YANG Y R, XIONG Q Y, WU C, et al. A study on water quality prediction by a hybrid CNN-LSTM model with attention mechanism[J]. Environmental Science and Pollution Research International, 2021, 28(39): 55129-55139. doi: 10.1007/s11356-021-14687-8 pmid: 34129164
[19]	BOMMISETTY R M, PRAKASH O, KHARE A. Keyframe extraction using Pearson correlation coefficient and color moments[J]. Multimedia Systems, 2020, 26(3): 267-299. doi: 10.1007/s00530-019-00642-8
[20]	CHEN Q, ZHANG W Y, ZHU K, et al. A novel trilinear deep residual network with self-adaptive Dropout method for short-term load forecasting[J]. Expert Systems With Applications, 2021, 182: 115272.
[21]	张珂, 杨歆豪, 张嘉慧, 等. 基于高次指数平滑动态边界限制的深度学习优化算法[J]. 信息与控制, 2021, 50(6): 685-693. doi: 10.13976/j.cnki.xk.2021.0522
	ZHANG Ke, YANG Xinhao, ZHANG Jiahui, et al. Deep learning optimization algorithm based on high order exponential smoothing dynamic boundary constraint[J]. Information and Control, 2021, 50(6): 685-693. doi: 10.13976/j.cnki.xk.2021.0522

层号	层类别	神经元数量
1	输入层	24×6
2	卷积层	24×64
3	池化层	24×64
4	Dropout层	24×64
5	LSTM层	24×50
6	全连接层	24×50
7	Attention层	24×50
8	Flatten层	1×1 200
9	输出层	1×24

基于注意力机制与神经网络的热电联产锅炉负荷预测

Boiler Load Forecasting of CHP Plant Based on Attention Mechanism and Deep Neural Network

RichHTML

PDF (PC)

可视化

摘要/Abstract

引用本文

使用本文

图/表 12

参考文献 21

相关文章 15

编辑推荐

Metrics

本文评价

[1]	. 基于知识-数据融合模型的综合能源系统多元负荷短期预测[J]. J Shanghai Jiaotong Univ Sci, 2026, 31(2): 499-514.
[2]	. 用于水下图像增强的全局密集双分支级联网络[J]. J Shanghai Jiaotong Univ Sci, 2026, 31(2): 458-474.
[3]	. 改进DeepLabv3+的高分辨率遥感图像分割方法[J]. J Shanghai Jiaotong Univ Sci, 2026, 31(2): 348-358.
[4]	刘轩, 兰晓宸, 徐大鹏, 何良, 刘茂珅. 基于深度学习时序特征增强的海杂波抑制方法[J]. 空天防御, 2026, 9(1): 36-45.
[5]	李湘, 陈思远, 张俊, 柯德平, 高杰迈, 杨欢欢. 基于物理信息嵌入的非固定长度电力系统暂态稳定快速评估[J]. 上海交通大学学报, 2025, 59(7): 962-970.
[6]	曾金灿, 何耿生, 李姚旺, 杜尔顺, 张宁, 朱浩骏. 基于卷积神经网络与轻量级梯度提升树组合模型的电力行业短期以电折碳方法[J]. 上海交通大学学报, 2025, 59(6): 746-757.
[7]	. 基于深度学习序列方法的多人姿态估计用来检测人体与关键点位置[J]. J Shanghai Jiaotong Univ Sci, 2025, 30(6): 1103-1113.
[8]	. 基于多种影响因素的电动汽车充电负荷建模方法[J]. J Shanghai Jiaotong Univ Sci, 2025, 30(6): 1232-1241.
[9]	. 基于ALBERT的中国诗酒文化命名实体识别[J]. J Shanghai Jiaotong Univ Sci, 2025, 30(5): 1065-1072.
[10]	. CenterLineFormer：基于单车载相机的车道中心线生成方法[J]. J Shanghai Jiaotong Univ Sci, 2025, 30(5): 1009-1017.
[11]	潘美琪, 贺兴. 基于零样本学习的风力机故障诊断方法[J]. 上海交通大学学报, 2025, 59(5): 561-568.
[12]	. 基于多注意力机制的轻量化人体姿态估计[J]. J Shanghai Jiaotong Univ Sci, 2025, 30(5): 899-910.
[13]	. 基于多特征提取方法的多场景烟雾检测[J]. J Shanghai Jiaotong Univ Sci, 2025, 30(5): 866-879.
[14]	梁煜婉, 肖朝昀, 李明广, 孟江山, 周建烽, 黄山景, 朱浩杰. 基于长短时记忆的真空预压地基沉降预测[J]. 上海交通大学学报, 2025, 59(4): 525-532.
[15]	. 迁移学习和注意机制融合用于CT图像COVID-19病灶分割的计算机辅助诊断[J]. J Shanghai Jiaotong Univ Sci, 2025, 30(3): 566-581.