基于数据驱动的火电机组高压加热系统异常检测研究

doi:10.3969/j.issn.1674-1951.2021.08.010

摘要/Abstract

摘要：

为保证火电机组高压加热（以下简称高加）系统安全经济运行,开展基于数据驱动的高加系统异常检测研究。首先从高加性能和状态2方面综合考虑,选取上端差、下端差、温升、水位、正常疏水调节阀开度5个参数作为异常检测的特征参数建立异常检测模型。然后以稳态工况下的真实历史运行数据驱动,采用主成分分析法解决高维数据分析中的“维度灾难”问题,基于马氏距离和拉依达准则确定参数阈值,实现高加系统的异常检测。最后选取一组真实历史运行数据验证了模型的有效性,证明了该模型能够捕捉到高加系统的早期异常,效果良好,可为该火电机组提供有效的高加系统异常信息,为机组安全经济运行提供保障。

关键词: 火电机组, 高压加热系统, 数据驱动, 异常检测, 主成分分析法

Abstract:

To ensure the safe and economic operation of high-pressure heaters in thermal power units,data-driven research was made on anomaly detection for high-pressure heaters.The research took the performance and state of the high-pressure heater into consideration,and chose five parameters including upper end difference,lower end difference,temperature rise,water level and normal opening of drain valves as the characteristic parameters to establish a model for anomaly detection.Then,driven by the real historical operation data under steady-state condition,Principal Component Analysis was used to solve the "Curse of Dimensionality" in high-dimensional data analysis,and Mahalanobis distance and PauTa criterion were taken to determine the parameters' threshold.This method can realize the anomaly detection for high-pressure heating system.Finally,verified by a group of real historical operation data,the model can capture the early abnormalities of the high-pressure heating system effectively.By providing effective abnormal information for high-pressure heaters in thermal power units,this method can ensure the safe and economic operation of the units.

Key words: thermal power units, high-pressure heating system, data driven, anomaly detection, Principal Component Analysis

中图分类号:

TK267:TM621

韩旭东. 基于数据驱动的火电机组高压加热系统异常检测研究[J]. 华电技术, 2021, 43(8): 67-73.

HAN Xudong. Data-driven based research on anomaly detection for high-pressure heaters in thermal power units[J]. Huadian Technology, 2021, 43(8): 67-73.

图/表 10

图1

图2

图3

图4

图5

图6

图7

图8

图9

图10

参考文献 19

[1]	宋永华, 包铭磊, 丁一, 等. 新电改下我国电力现货市场建设关键要点综述及相关建议[J]. 中国电机工程学报, 2020, 40(10):3172-3187.
	SONG Yonghua, BAO Minglei, DING Yi, et al. Review of Chinese electricity spot market key issues and its suggestions under the new round of Chinese power system reform[J]. Proceedings of the CSEE, 2020, 40(10):3172-3187.
[2]	关鑫源. 非正常运行工况下高压加热器端差特性研究[D]. 北京:华北电力大学, 2012.
[3]	闫哲, 张士明, 顾勇. 超超临界二次再热百万机组高压加热器布置方案[J]. 华电技术, 2016, 38(5):41-42.
	YAN Zhe, ZHANG Shiming, GU Yong. Discuss of ultra-critical secondary reheat megawatts unit high pressure heater layout[J]. Huadian Technology, 2016, 38(5):41-42.
[4]	王建华, 范佩佩, 石峰, 等. 给水旁路调节下高压加热器的瞬态应力分析[J]. 发电技术, 2019, 40(4):329-338.
	WANG Jianhua, FAN Peipei, SHI Feng, et al. Transient stress analysis of high pressure heater during feedwater bypass regulations[J]. Power Generation Technology, 2019, 40(4):329-338.
[5]	ZHAO Y, FAN P, WANG C, et al. Fatigue lifetime assessment on a high-pressure heater in supercritical coal-fired power plants during transient processes of operational flexibility regulation[J]. Applied Thermal Engineering, 2019, 156:196-208. doi: 10.1016/j.applthermaleng.2019.04.066
[6]	LI Y, WANG Y, CAO L, et al. Modeling for the performance evaluation of 600 MW supercritical unit operating No.0 high pressure heater[J]. Energy, 2018, 149:639-661. doi: 10.1016/j.energy.2018.01.103
[7]	黄小军. 600 MW机组高压加热器启动过程中管道振动分析与治理[J]. 华电技术, 2017, 39(4):48-49.
	HUANG Xiaojun. 600 MW unit high pressure reheater start-up pipeline vibration analysis and treatment[J]. Huadian Technology, 2017, 39(4):48-49.
[8]	秦刚华, 雷丽君, 郭鼎, 等. 燃煤电站高压加热器系统故障仿真与诊断[J]. 热力发电, 2019, 48(6):108-114.
	QIN Ganghua, LEI Lijun, GUO Ding, et al. Fault simulation and diagnosis for high pressure heater of coal-fired power plants[J]. Thermal Power Generation, 2019, 48(6):108-114.
[9]	刘书杰, 郭阳, 曲广浩, 等. 基于趋势相似性特征的异常工况监测方法研究[J]. 自动化仪表, 2020, 41(2):37-41.
	LIU Shujie, GUO Yang, QU Guanghao, et al. Study on abnormal conditions monitoring method based on trends similarity features[J]. Process Automation Instrumentation, 2020, 41(2):37-41.
[10]	陈警钰, 陈玉航. 基于INNER-DBSCAN和功率曲线模型的风机异常状态检测[J]. 电力科学与工程, 2017, 33(8):27-34.
	CHEN Jingyu, CHEN Yuhang. Condition monitoring for wind turbines based on INNER-DBSCAN and power curve pattern[J]. Electric Power Science and Engineering, 2017, 33(8):27-34.
[11]	郭明军, 李伟光, 杨期江, 等. 基于SVD原理的PCA特征频率提取算法及其应用[J]. 华南理工大学学报(自然科学版), 2020, 48(1):1-9.
	GUO Mingjun, LI Weiguang, YANG Qijiang, et al. PCA feature frequency extraction algorithm based on SVD principle and its application[J]. Journal of South China University of Technology(Natural Science Edition), 2020, 48(1):1-9.
[12]	KINI K R, MADAKYARU M. Improved anomaly detection based on integrated multi-scale principal component analysis using wavelets:An application to high dimensional processes[J]. IFAC-PapersOnLine, 2020, 53(1):398-403. doi: 10.1016/j.ifacol.2020.06.067
[13]	王仲, 顾煜炯, 韩旭东, 等. 基于历史数据聚类的火电机组工况划分[J]. 仪器仪表学报, 2019, 40(2):90-95.
	WANG Zhong, GU Yujiong, HAN Xudong, et al. Operating condition classification of thermal power unit based on historical data clustering[J]. Chinese Journal of Scientific Instrument, 2019, 40(2):90-95.
[14]	付冲. 基于PCA的多模式辨识及性能评估方法的研究[D]. 沈阳:东北大学, 2012.
[15]	张媛媛. 多尺度自适应PCA及其在过程监测中的应用研究[D]. 北京:北京化工大学, 2012.
[16]	MAESSCHALCK R D, JOUAN-RIMBAUD D, MASSART D L. The Mahalanobis distance[J]. Chemometrics & Intelligent Laboratory Systems, 2000, 50(1):1-18.
[17]	张敏, 袁辉. 拉依达（PauTa）准则与异常值剔除[J]. 郑州工业大学学报(工学版), 1997, 18(1):87-91.
	ZHANG Min, YUAN Hui. The PauTa criterion and rejecting the abnormal value[J]. Journal of Zhengzhou University of Technology(Engineering Science), 1997, 18(1):87-91.
[18]	辛志波. 超超临界直流炉给水控制策略研究与设计[J]. 华电技术, 2019, 41(10):39-43.
	XIN Zhibo. Research and design of feedwater control strategy for an ultra-supercritical once-through boiler[J]. Huadian Technology, 2019, 41(10):39-43.
[19]	徐江, 赵志发, 李军. 1 000 MW二次再热机组给水温度优化实施[J]. 华电技术, 2020, 42(1):78-80.
	XU Jiang, ZHAO Zhifa, LI Jun. Optimization of feedwater temperature of 1 000 MW double reheat units[J]. Huadian Technology, 2020, 42(1):78-80.