Main Steam Flowrate Measurement Model for Steam Turbines Based on KPCA-BiLSTM-GRU

SHENG Wen; XU Shiming; LU Guanfa; GAO Cheng; QI Jing; PENG Xianyong; ZHOU Huaichun

doi:10.19805/j.cnki.jcspe.2025.240453

English Version Journal Login

您当前的位置：

首页 >

文章列表页 >

Main Steam Flowrate Measurement Model for Steam Turbines Based on KPCA-BiLSTM-GRU

更新时间：2026-10-10

- Main Steam Flowrate Measurement Model for Steam Turbines Based on KPCA-BiLSTM-GRU
- Chinese Journal of Power Engineering Vol. 45, Issue 9, Pages: 1483-1491(2025)
- 作者机构：
  
  1. 中国矿业大学低碳能源与动力工程学院,江苏,徐州,221116
  2. 江苏省智慧能源技术及装备工程研究中心,江苏,徐州,221116
  3. 江苏华美热电有限公司,江苏,徐州,221141
  4. 南京师范大学能源与机械工程学院,江苏,南京,210023
- 作者简介：
- 基金信息：
- DOI：10.19805/j.cnki.jcspe.2025.240453
  CLC：
- Online First：16 September 2025，
  
  Published：2025
- 稿件说明：
移动端阅览
盛稳,徐世明,卢官发,高成,祁晶,彭献永,周怀春. 基于KPCA-BiLSTM-GRU的汽轮机主蒸汽流量测量模型动力工程学报, 2025, 45(9): 1483-1491 https://doi.

org/10.19805/j.cnki.jcspe.2025.240453
盛稳,徐世明,卢官发,高成,祁晶,彭献永,周怀春. 基于KPCA-BiLSTM-GRU的汽轮机主蒸汽流量测量模型动力工程学报, 2025, 45(9): 1483-1491 https://doi. DOI： 10.19805/j.cnki.jcspe.2025.240453.

org/10.19805/j.cnki.jcspe.2025.240453 DOI：

摘要

针对难以准确监测机组主蒸汽流量的问题

提出了一种基于核主成分分析-双向长短期记忆-门控循环单元(KPCA-BiLSTM-GRU)的主蒸汽流量测量模型

并以某1 000 MW超超临界一次再热发电机组的历史数据为基础进行了仿真验证。首先

根据实际生产过程中机组运行机理及经验

选取了与主蒸汽流量相关的运行参数作为测量模型输入的候选变量;其次

利用KPCA算法对原始的候选输入特征进行降维

避免因模型输入变量过多对预测结果精度产生影响;最后

使用BiLSTM-GRU神经网络模型进一步学习输入数据特征的变化规律

实现了主蒸汽流量的回归预测。选用反向传播(BP)、LSTM、BiLSTM、GRU等神经网络模型进行了对比实验

以验证所提出模型的预测效果。结果表明:所提出的基于KPCA-BiLSTM-GRU的主蒸汽流量模型能够实现主蒸汽流量的准确测量

其均方根误差(RMSE)为25.76 t/h

平均绝对百分比误差(MAPE)为1.21%;相比于实验中其他模型

KPCA-BiLSTM-GRU主蒸汽流量测量模型的预测效果更好

对深度调峰汽轮发电机组变负荷工况有较好的适应性。

Abstract

Aiming at the problem that it is difficult to accurately measure the main steam flowrate of a unit

a main steam flowrate measurement model based on KPCA-BiLSTM-GRU was proposed

and a simulation verification was proposed based on historical data of a certain 1 000 MW ultra-supercritical primary reheat generating unit. Firstly

based on the operating mechanism and experience of the unit during actual production

operating parameters related to the main steam flowrate were selected as candidate variables for input into the measurement model. Secondly

KPCA algorithm was used to reduce the dimension of the original candidate input features

thereby avoiding the impact on the prediction accuracy caused by an excessive number of input variables in the model. Finally

the BiLSTM-GRU neural network model was used to further learn the change law of the input data features

achieving the regression prediction of the main steam flowrate. At the same time

Neural network models such as BP

LSTM

BiLSTM and GRU were selected for comparative experiments to verify the prediction performance of the proposed model. The results show that the proposed main steam flowrate model based on KPCA-BiLSTM-GRU can accurately measure the main steam flowrate. Its root mean square error (RMSE) is 25.76 t/h

and the mean absolute percentage error (MAPE) is 1.21%. Compared with other models in the experiment

the KPCA-BiLSTM-GRU main steam flowrate measurement model has a better prediction effect and is more adaptable to the variable load operation conditions of the deep load-peak shaving steam turbine power generation unit.

关键词

Keywords

references

柳磊. 汽轮机组调门流量特性对机组安全经济性的影响研究[D]. 南京: 东南大学, 2019.

李勇, 王建君, 曹丽华. 汽轮机主蒸汽流量在线监测方法研究[J]. 热力发电, 2011, 40(4): 33-36, 40. LI Yong, WANG Jianjun, CAO Lihua. Study on the on-line monitoring method of main steam flow rate for steam turbines[J]. Thermal Power Generation, 2011, 40(4): 33-36, 40.

孙剑, 蒙西, 乔俊飞. 基于MIV-RBF神经网络的主蒸汽流量软测量方法[J]. 控制工程, 2022, 29(10): 1829-1834. SUN Jian, MENG Xi, QIAO Junfei. Soft sensor method of main steam flow based on mean impact value and radial basis function neural network[J]. Control Engineering of China, 2022, 29(10): 1829-1834.

冯伟忠. 大机组主蒸汽流量测量刍议[J]. 华东电力, 2000, 28(12): 14-17. FENG Weizhong. Flow rate measurement for main steam of large unit[J]. East China Electric Power, 2000, 28(12): 14-17.

刘吉臻, 闫姝, 曾德良, 等. 主蒸汽流量的测量模型研究[J]. 动力工程学报, 2011, 31(10): 734-738. LIU Jizhen, YAN Shu, ZENG Deliang, et al. A new measurement model for main steam flow in power plants[J]. Journal of Chinese Society of Power Engineering, 2011, 31(10): 734-738.

TIAN Liang, LIU Xinpeng, LUO Huanhuan, et al. Soft sensor of heating extraction steam flow rate based on frequency complementary information fusion for CHP plant[J]. Energies, 2021, 14(12): 3474.

程堃, 万祥, 孙海军, 等. 弗留格尔公式的改进及其在汽轮机湿蒸汽级组中的应用[J]. 汽轮机技术, 2020, 62(2): 104-106, 131. CHENG Kun, WAN Xiang, SUN Haijun, et al. The improvement of flugel formula and its application in wet steam stage groups of steam turbine[J]. Turbine Technology, 2020, 62(2): 104-106, 131.

汪军, 周建新, 司风琪, 等. 汽轮机主蒸汽流量在线计算方法及应用[J]. 热力发电, 2010, 39(10): 42-45. WANG Jun, ZHOU Jianxin, SI Fengqi, et al. On-line calculation method for the main steam flow rate of steam turbine and its application[J]. Thermal Power Generation, 2010, 39(10): 42-45.

梁伟平, 薛文雅, 马靖宁, 等. 基于WOA-Elman神经网络的城市固废焚烧炉主蒸汽流量软测量[J]. 控制工程, 2025, 32(2): 201-207. LIANG Weiping, XUE Wenya, MA Jingning, et al. Soft measurement of main steam flow in municipal solid waste incinerator based on WOA-Elman neural network[J]. Control Engineering of China, 2025, 32(2): 201-207.

齐敏芳, 付忠广, 陈菲, 等. 火电机组主蒸汽流量在线监测计算方法[J]. 华北电力大学学报, 2015, 42(1): 51-57. QI Minfang, FU Zhongguang, CHEN Fei, et al. Research on on-line monitoring calculation method of main steam flow in thermal power units[J]. Journal of North China Electric Power University, 2015, 42(1): 51-57.

朱清智, 董泽. 基于CAWOA-PELM的汽轮机主蒸汽流量预测[J]. 计算机仿真, 2020, 37(9): 93-98. ZHU Qingzhi, DONG Ze. Prediction of main steam flow of steam turbine based on CAWOA-PELM[J]. Computer Simulation, 2020, 37(9): 93-98.

王建星, 付忠广, 靳涛, 等. 基于广义回归神经网络的机组主蒸汽流量测定[J]. 动力工程学报, 2012, 32(2): 130-134, 158. WANG Jianxing, FU Zhongguang, JIN Tao, et al. Main steam flow measurement based on generalized regression neural network[J]. Journal of Chinese Society of Power Engineering, 2012, 32(2): 130-134, 158.

徐红伟, 李美双, 李崇晟, 等. 基于数据驱动的汽轮机主蒸汽流量软测量[J]. 动力工程学报, 2023, 43(6): 742-748. XU Hongwei, LI Meishuang, LI Chongsheng, et al. Soft sensing of main steam flow of steam turbine based on data driven[J]. Journal of Chinese Society of Power Engineering, 2023, 43(6): 742-748.

邓怀勇, 马琴, 陈国彬, 等. 基于AWOA算法与LSSVM的主蒸汽流量软测量模型[J]. 仪表技术与传感器, 2018(12): 78-82. DENG Huaiyong, MA Qin, CHEN Guobin, et al. Soft sensor model of main steam flow based on AWOA algorithm and LSSVM[J]. Instrument Technique and Sensor, 2018(12): 78-82.

章永来, 周耀鉴. 聚类算法综述[J]. 计算机应用, 2019, 39(7): 1869-1882. ZHANG Yonglai, ZHOU Yaojian. Review of clustering algorithms[J]. Journal of Computer Applications, 2019, 39(7): 1869-1882.

汪国新, 郝勇生, 苏志刚. 基于KPCA-GG的火力发电设备状态诊断方法[J]. 东南大学学报(自然科学版), 2019, 49(3): 542-548. WANG Guoxin, HAO Yongsheng, SU Zhigang. Condition diagnosis method for thermal power generation equipment based on KPCA-GG[J]. Journal of Southeast University (Natural Science Edition), 2019, 49(3): 542-548.

GREFF K, SRIVASTAVA R K, KOUTNK J, et al. LSTM: a search space odyssey[J]. IEEE Transactions on Neural Networks and Learning Systems, 2017, 28(10): 2222-2232.

SHERSTINSKY A. Fundamentals of recurrent neural network (RNN) and long short-term memory (LSTM) network[J]. Physica D: Nonlinear Phenomena, 2020, 404: 132306.

CHEN Zhenghua, WU Min, ZHAO Rui, et al. Machine remaining useful life prediction via an attention-based deep learning approach[J]. IEEE Transactions on Industrial Electronics, 2021, 68(3): 2521-2531.

MA Xiaolei, ZHANG Jiyu, DU Bowen, et al. Parallel architecture of convolutional Bi-directional LSTM neural networks for network-wide metro ridership prediction[J]. IEEE Transactions on Intelligent Transportation Systems, 2019, 20(6): 2278-2288.

CHO K, VAN MERRINBOER B, GULCEHRE C, et al. Learning statistical machine translation using RNN encoder-decoder for statistical machine translation[C]//Proceedings of the 2014 Conference on Empirical Methods in Natural Language Processing (EMNLP). Doha, Qatar: Association for Computational Linguistics, 2014: 1724-1734. (下转第1510页)

Views

下载量

CSCD

Alert me when the article has been cited

提交

Tools

Publicity Resources

Research on Key Technologies of Medium and High Temperature Thermochemical Heat Storage

Multi-objective Optimal Maintenance Decision-making of Gas Turbine Blades Based on WPHM and Non-dominated Genetic Algorithm

Effect of Fractal Characteristics on Dynamic Response of Bionic Floating Wind Turbine Platform

Dual-channel Short-term Wind Power Forecasting Fusing Long- and Short-term Dependencies

Research on Multiaixal Creep Behavior and Failure Criteria of TP321 Stainless Steel at 650 ℃

Related Author

No data

Related Institution

No data

AI问答

⁰