面向多模态过程的凝汽器故障特征提取研究

朱继涛; 曾水平; 贺宇清; 郑佳佳; 代雨辰; 司风琪

doi:10.19805/j.cnki.jcspe.2025.230679

欢迎来到能源电力期刊网！

English Version 读者登录期刊登录

您当前的位置：

首页 >

文章列表页 >

面向多模态过程的凝汽器故障特征提取研究

数字化与智能化 | 更新时间：2026-02-05

- 面向多模态过程的凝汽器故障特征提取研究
- Research on Fault Condenser Feature Extraction for Multi-modal Processes
- 动力工程学报 2025年45卷第1期页码：124-130
- 作者机构：
  
  1. 国家电投集团江西电力有限公司,江西,南昌,330000
  2. 国家电投集团江西电力有限公司景德镇发电厂,江西,景德镇,333036
  3. 东南大学能源与环境学院,江苏,南京,210096
- 作者简介：
  
  [ "朱继涛(1972—),男,江西玉山人,高级工程师,本科,研究方向为智慧电厂,E-mail:392187926@qq.com" ]
- 基金信息：
  
  国家重点研发计划资助项目(2022YFB4100700)
- DOI：10.19805/j.cnki.jcspe.2025.230679
  中图分类号： TM621
- 网络首发：2025-01-15，
  
  纸质出版：2025
- 稿件说明：
移动端阅览
朱继涛,曾水平,贺宇清,郑佳佳,代雨辰,司风琪. 面向多模态过程的凝汽器故障特征提取研究动力工程学报, 2025, 45(1): 124-130 https://doi.

org/10.19805/j.cnki.jcspe.2025.230679
朱继涛,曾水平,贺宇清,郑佳佳,代雨辰,司风琪. 面向多模态过程的凝汽器故障特征提取研究动力工程学报, 2025, 45(1): 124-130 https://doi. DOI： 10.19805/j.cnki.jcspe.2025.230679.

org/10.19805/j.cnki.jcspe.2025.230679 DOI：

摘要

针对凝汽器设备多模态运行过程的在线监测与故障特征提取问题

提出了一种融合

-means聚类与重构主成分分析的故障特征提取方法。首先

采用

-means聚类进行模态识别

聚类结果表明不同模态之间平方预测误差(SPE)统计量存在显著差异

需要对子模态分别建立监测模型。为有效获取故障特征

抑制故障分离过程中的残差污染现象

采用重构主成分分析法获取故障特征向量

实现了面向多模态过程的故障特征提取。结果表明:使用重构贡献图法能够分离检测出故障变量及其特征向量

且能有效避免残差污染问题

具有良好的故障定位精度。

Abstract

To address the issue of online monitoring and fault feature extraction in multi-modal operation process of condenser equipment

a fault feature extraction method integrating

-means clustering and reconstructed principal component analysis was proposed. First

-means clustering was used to identify modes. The clustering results show significant differences in squared prediction error (SPE) statistics among different modes

and it is necessary to establish monitoring models for sub-modes. In order to obtain fault features effectively and suppress residual pollution in fault separation process

fault feature vectors were obtained by reconstructing principal component analysis method

and the fault feature extraction for multi-modal

process was realized. Results show that fault variables and their feature vectors can be separated and detected by using the reconstructed contribution graph method

and the residual pollution problem can be avoided effectively

and the fault location accuracy is good.

关键词

Keywords

references

任少君. 热工过程海量数据流模型分析及诊断方法研究[D]. 南京: 东南大学, 2018.

VERMA V, GORDON G, SIMMONS R, et al. Real-time fault diagnosis[J]. IEEE Robotics & Automation Magazine, 2004, 11(2): 56-66.

MICHELI-TZANAKOU E. Supervised and unsupervised pattern recognition: feature extraction and computational intelligence[M]. Boca Raton, USA: CRC Press, 2000: 133-194.

刘畅. 电站设备辅机状态监测与故障诊断[D]. 北京: 华北电力大学, 2017.

ZHOU Zhe, WEN Chenglin, YANG Chunjie. Fault isolation based on k -nearest neighbor rule for industrial processes[J ] . IEEE Transac tions on Industrial Electronics, 2016, 63(4): 2578-2586.

DAI Yuchen, REN Shaojun, SI Fengqi. A novel fault diagnosis method integrating reconstruction-based principal component analysis with probabilistic neural network on condenser[C]//2022 5th International Conference on Energy, Electrical and Power Engineering (CEEPE). Chongqing, China: IEEE, 2022: 496-501.

ALTMAN N, KRZYWINSKI M. The curse(s) of dimensionality[J]. Nature Methods, 2018, 15(6): 399-400.

GUYON I. Feature extraction: foundations and applications[M]. Berlin, Germany: Springer, 2014: 73-121.

XU Wenqiang, WU Xiaogang, LI Yalun, et al. A comprehensive review of DC arc faults and their mechanisms, detection, early warning strategies, and protection in battery systems[J]. Renewable and Sustainable Energy Reviews, 2023, 186: 113674.

HUANG Congzhi, SHENG Xinxin. Data-driven model identification of boiler-turbine coupled process in 1 000 MW ultra-supercritical unit by improved bird swarm algorithm[J]. Energy, 2020, 205: 118009.

SONG Y J. Experimental and theoretical study of horizontal tube bundle for passive condensation heat transfer[D]. West Lafayette, USA: Purdue University, 2007.

BOTSCH T W, STEPHAN K, ALCOCK J L, et al. Modelling and simulation of the dynamic behaviour of a shell-and-tube condenser[J]. International Journal of Heat and Mass Transfer, 1997, 40(17): 4137-4149.

王思平. 污垢对凝汽器及汽轮机组性能影响的数值分析[D]. 上海: 上海电力学院, 2013.

徐卫峰. 600 MW火电机组汽轮机系统建模与仿真[D]. 南京: 东南大学, 2005.

ZAMZAM A S, FU Xiao, SIDIROPOULOS N D. Data-driven learning-based optimization for distribution system state estimation[J]. IEEE Transactions on Power Systems, 2019, 34(6): 4796-4805.

MUOZ A, SANZ-BOBI M A. An incipient fault detection system based on the probabilistic radial basis function network: application to the diagnosis of the condenser of a coal power plant[J]. Neurocomputing, 1998, 23(1/3): 177-194.

MA Zhenjun, WANG Shengwei. Online fault detection and robust control of condenser cooling water systems in building central chiller plants[J]. Energy and Buildings, 2011, 43(1): 153-165.

张凯旋. 基于粗糙集和集成SVM的凝汽器故障诊断应用研究[D]. 北京: 华北电力大学, 2018.

周卫庆, 黄葆华, 仇晓智, 等. 基于MSET和模糊识别的凝汽器故障诊断[J]. 热能动力工程, 2018, 33(10): 107-112, 146. ZHOU Weiqing, HUANG Baohua, QIU Xiaozhi, et al. Condenser fault diagnosis based on MSET and fuzzy recognition[J]. Journal of Engineering for Thermal Energy and Power, 2018, 33(10): 107-112, 146.

蒋国栋. 基于K-means聚类算法的负荷模型研究[D]. 哈尔滨: 哈尔滨工业大学, 2009.

殷瑞刚, 魏帅, 李晗, 等. 深度学习中的无监督学习方法综述[J]. 计算机系统应用, 2016, 25(8): 1-7. YIN Ruigang, WEI Shuai, LI Han, et al. Introduction of unsupervised learning methods in deep learning[J]. Computer Systems & Applications, 2016, 25(8): 1-7.

RAO Y N, PRINCIPE J C. A fast, on-line algorithm for PCA and its convergence characteristics[C]//Neural Networks for Signal Processing X. Proceedings of the 2000 IEEE Signal Processing Society Workshop (Cat. No.00TH8501). Sydney, NSW, Australia: IEEE, 2000: 299-307.

HENRY YUE H, JOE QIN S. Reconstruction-based fault identification using a combined index[J]. Industrial & Engineering Chemistry Research, 2001, 40(20): 4403-4414.

MATHEWS I, MATHEWS E H, VAN LAAR J H, et al. A simulation-based prediction model for coal-fired power plant condenser maintenance[J]. Applied Thermal Engineering, 2020, 174: 115294.

WESTERHUIS J A, GURDEN S P, SMILDE A K. Generalized contribution plots in multivariate statistical process monitoring[J]. Chemometrics and Intelligent Laboratory Systems, 2000, 51(1): 95-114.

DUNIA R, JOE QIN S. Subspace approach to multidimensional fault identification and reconstruction[J]. AICHE Journal, 1998, 44(8): 1813-1831.

浏览量

下载量

CSCD

文章被引用时，请邮件提醒。

提交

工具集

关联资源

暂无数据