Study on Performance Prediction Model of Gas Turbine Compressor and Combined Cycle Unit Based on PCA-PSO-LSTM

YIN Jiayang; CHEN Shiyi; TANG Yin; HUANG Qing; XIANG Wenguo

doi:10.19805/j.cnki.jcspe.2026.250094

English Version Journal Login

您当前的位置：

首页 >

文章列表页 >

Study on Performance Prediction Model of Gas Turbine Compressor and Combined Cycle Unit Based on PCA-PSO-LSTM

更新时间：2026-07-16

- Study on Performance Prediction Model of Gas Turbine Compressor and Combined Cycle Unit Based on PCA-PSO-LSTM
- Chinese Journal of Power Engineering Vol. 46, Issue 7, Pages: 1-10,30(2026)
- 作者机构：
  
  1. 东南大学能源与环境学院,江苏,南京,211189
  2. 华能金陵燃机热电有限公司,江苏,南京,210046
- 作者简介：
- 基金信息：
- DOI：10.19805/j.cnki.jcspe.2026.250094
  CLC： TK474.8
- Published：2026
- 稿件说明：
移动端阅览
殷家阳, 陈时熠, 唐寅, 黄庆, 向文国. 基于PCA-PSO-LSTM的燃气轮机压气机及机组性能预测模型研究[J]. 动力工程学报, 2026, 46(7): 1-10,30.
殷家阳, 陈时熠, 唐寅, 黄庆, 向文国. 基于PCA-PSO-LSTM的燃气轮机压气机及机组性能预测模型研究[J]. 动力工程学报, 2026, 46(7): 1-10,30. DOI： 10.19805/j.cnki.jcspe.2026.250094.

DOI： 10.19805/j.cnki.jcspe.2026.250094

摘要

为了预测压气机及联合循环机组的热力性能以保证其高效运行

提出了一种基于主成分分析(PCA)、粒子群优化(PSO)算法和长短期记忆(LSTM)神经网络的压气机及机组性能预测模型。首先

使用PCA将输入参数由13维降至7维

保留关键信息的同时减少了计算量和模型训练时间。然后

采用LSTM对时间序列数据进行建模

捕捉数据的动态趋势与非线性关系。为进一步优化模型性能

引入PSO算法自动调优LSTM超参数

从而提高预测精度与模型稳定性。最后

根据预测误差分布计算报警阈值。结果表明:基于PCA-PSO-LSTM的模型在压气机出口温度、机组修正出力及修正热耗的预测中表现出高准确性

相较于传统方法

均方根误差(RMSE)和平均绝对误差(MAE)显著降低

RMSE降幅在30%以上

MAE低于0.8;计算所得报警阈值为压气机运行状态异常预警提供了理论依据与技术支持。

Abstract

To predict the thermal performance of the compressor and combined cycle unit

and ensure their efficient operation

a compressor and unit performance prediction model based on principal component analysis (PCA)

particle swarm optimization (PSO) algorithm

and long short-term memory (LSTM) neural network was proposed. Firstly

PCA was applied to reduce the input parameters from 13 dimensions to 7 dimensions

preserving key information while reducing computational complexity and model training time. Then

combined with LSTM

the time series data were modeled to capture the dynamic trends and nonlinear relationships of the data. To further optimize model performance

PSO algorithm was introduced to automatically tune LSTM hyperparameters

thereby improving prediction accuracy and model stability. Finally

the alarm threshold was calculated according to predicting error distribution. Results show that the PCA-PSO-LSTM based model exhibits high accuracy in predicting compressor outlet temperature

unit corrected output and corrected heat consumption. Compared with traditional methods

the root mean square error (RMSE) and mean absolute error (MAE) of the proposed model are significantly reduced. RMSE is reduced over 30% and MAE remains below 0.8. In addition

the calculated alarm threshold can provide theoretical basis and technical support for abnormal warning of compressor operating status.

关键词

Keywords

references

SAMARASINGHE T, ABEYKOON C, TURAN A. Modelling of heat transfer and fluid flow in the hot section of gas turbines used in power generation: a comprehensive survey[J]. International Journal of Energy Research, 2018, 43(5): 1647.

JURADO F. Modelling micro-turbines using Hammerstein models[J]. International Journal of Energy Research, 2005, 29(9): 841-855.

刘欢, 张士杰. 基于改进叠加法的变几何轴流压气机性能预测[J]. 清华大学学报(自然科学版), 2024, 64(5): 869-878.LIU Huan, ZHANG Shijie. Performance prediction of axial-flow compressors with variable geometry using a modified stage-stacking method[J]. Journal of Tsinghua University (Science & Technology), 2024, 64(5): 869-878.

刘稼昊, 耿少娟, 金芸, 等. 多级轴流压气机一维性能预测程序开发及应用[J]. 热能动力工程, 2024, 39(1): 12-22.LIU Jiahao, GENG Shaojuan, JIN Yun, et al. Development and application of one-dimensional performance prediction program for multistage axial compressor[J]. Journal of Engineering for Thermal Energy and Power, 2024, 39(1): 12-22.

刘小方, 蒋磊, 司品顺, 等. 燃气轮机压气机特性曲线的拟合方法[J]. 舰船科学技术, 2012, 34(7): 61-63.LIU Xiaofang, JIANG Lei, SI Pinshun, et al. Research on curve fitting method of compressor characteristic curve[J]. Ship Science and Technology, 2012, 34(7): 61-63.

房友龙, 刘东风, 贺星, 等. 压气机特性曲线精确分步拟合方法研究[J]. 燃气涡轮试验与研究, 2019, 32(2): 21-27.FANG Youlong, LIU Dongfeng, HE Xing, et al. Research on the precise step fitting method of compressor characteristic map[J]. Gas Turbine Experiment and Research, 2019, 32(2): 21-27.

涂环, 陈辉. 基于Krging算法的压气机特性建模[J]. 内燃机学报, 2014, 32(4): 377-383.TU Huan, CHEN Hui. Modeling of compressor characteristics using Kriging method[J]. Transactions of CSICE, 2014, 32(4): 377-383.

黄伟, 常俊, 孙智滨. 基于MEA-BP神经网络的压气机特性曲线预测[J]. 重庆理工大学学报(自然科学), 2019, 33(2): 67-74.HUANG Wei, CHANG Jun, SUN Zhibin. Characteristic curve prediction of compressor based on MEA-BP neural network[J]. Journal of Chongqing University of Technology (Natural Science), 2019, 33(2): 67-74.

徐思雨, 应雨龙, 周宏宇, 等. 基于人工蜂群优化支持向量参数的压气机特性线的表达[J]. 燃气轮机技术, 2020, 33(4): 24-33.XU Siyu, YING Yulong, ZHOU Hongyu, et al. Expression of compressor characteristic line based on artificial bee colony optimization support vector machine parameters[J]. Gas Turbine Technology, 2020, 33(4): 24-33.

路绪坤, 张士杰, 迟金玲, 等. 基于遗传算法的压气机性能曲线拟合方法研究[J]. 热能动力工程, 2022, 37(1): 105-109, 123.LU Xukun, ZHANG Shijie, CHI Jinling, et al. Research on the fitting method of compressor performance curve based on genetic algorithm[J]. Journal of Engineering for Thermal Energy and Power, 2022, 37(1): 105-109, 123.

赵子龙, 康英伟, 扶文浩. 基于免疫算法的压气机特性曲线预测方法研究[J]. 汽轮机技术, 2023, 65(4): 289-292.ZHAO Zilong, KANG Yingwei, FU Wenhao. Research on the prediction method of compressor characteristic curve based on immune algorithm[J]. Turbine Technology, 2023, 65(4): 289-292.

MIGENDA N, MLLER R, SCHENCK W. Adaptive dimensionality reduction for neural network-based online principal component analysis[J]. PLoS One, 2021, 16(3): e0248896.

李杨, 蓝茂蔚, 赵国钦, 等. 基于PCA-PSO-LSSVM的电站锅炉效率预测模型研究[J]. 热力发电, 2021, 50(12): 43-50.LI Yang, LAN Maowei, ZHAO Guoqin, et al. Study on prediction model of utility boiler efficiency based on PCA-PSO-LSSVM[J]. Thermal Power Generation, 2021, 50(12): 43-50.

姚钦才, 向文国, 陈时熠, 等. 基于ICEEMDAN-KPCA-ICPA-LSTM的光伏发电功率预测[J]. 动力工程学报, 2025, 45(3): 374-382.YAO Qincai, XIANG Wenguo, CHEN Shiyi, et al. Photovoltaic power forecasting based on ICEEMDAN-KPCA-ICPA-LSTM[J]. Journal of Chinese Society of Power Engineering, 2025, 45(3): 374-382.

李孟萱. 可增量的集成式LSTM时间序列预测研究[D]. 武汉: 中南财经政法大学, 2020.

王文阳. 基于神经网络的燃气轮机燃烧稳定性预测及分析[J]. 动力工程学报, 2023, 43(7): 842-849.WANG Wenyang. Prediction and analysis of combustion stability of gas turbine based on neural network[J]. Journal of Chinese Society of Power Engineering, 2023, 43(7): 842-849.

王晓霞, 马良玉, 祁在山. 基于粒子群和最近邻的热力系统变工况动态过程故障诊断方法[J]. 动力工程学报, 2014, 34(6): 469-476.WANG Xiaoxia, MA Liangyu, QI Zaishan. Thermal system fault diagnosis in load-varying dynamic process based on PSO algorithm and nearest neighbor classifier[J]. Journal of Chinese Society of Power Engineering, 2014, 34(6): 469-476.

喜静波, 马赓, 窦磊, 等. 燃气轮机进气过滤系统性能在线计算方法[J]. 燃气轮机技术, 2023, 36(1): 40-45. XI Jingbo, MA Geng, DOU Lei, et al. On-line performance calculation method for gas turbine air intake filtration system[J]. Gas Turbine Technology, 2023, 36(1): 40-45.

杨宝轩. 燃气轮机进气过滤系统健康状态监测方法[J]. 自动化博览, 2022, 39(5): 76-79.YANG Baoxuan. Health condition monitoring method of gas turbine intake filtration system[J]. Automation Panorama, 2022, 39(5): 76-79.

Views

下载量

CSCD

Alert me when the article has been cited

提交

Tools

Publicity Resources

Numerical Study on the Influence of Small Inlet Distortion on the Aerodynamic Performance of the Compressor

Research of High-temperature Adaptability on Compressor Blade Coatings of Gas Turbines

Data-driven Coordinated Control for a 600 MW Coal-Ammonia Co-firing Unit

A Combined Frequency-Time Domain Modulation Strategy for Optimizing the RMS Value of Inductor Current in Dual Active Bridge Converter

Summary of Research on Pumped Thermal Energy Storage Technology

Related Author

YAN Song

ZHUO Liang

SHI Daolong

LAN Xiaobing

CHU Wuli

YAN Song

CHU Wuli

ZHOU Xia

Related Institution

National Engineering Research Center for Small and Special Precision Motors, Guizhou Aerospace Linquan Motor Co., Ltd.

School of Power and Energy, Northwestern Polytechnical University

Collaborative Innovation Center of Advanced Aero-Engine

Shanghai Electric Gas Turbine Co., Ltd.

AI问答

⁰