基于振动特性曲线的抽水蓄能机组状态监测优化方法  

Optimization Method for State Monitoring of Pumped Storage Units Based on Vibration Characteristic Curve

作　　者：赵卫强 严单单 许贝贝 王正伟 ZHAO Weiqiang;YAN Dandan;XU Beibei;WANG Zhengwei(State Key Laboratory of Hydroscience and engineering,Beijing 100084,China;College of Water Resources and Civil Engineering,China Agricultural University,Beijing 100083,China;Institute of Water Resources and Hydropower Research,Northwest A&F University,Yangling 712100,China)

机构地区：[1]水沙科学水利水电工程国家重点实验室,北京市100084 [2]中国农业大学水利与土木工程学院,北京市100083 [3]西北农林科技大学水利与建筑工程学院,陕西省咸阳市712100

出　　处：《水电与抽水蓄能》2023年第5期47-52,60,共7页Hydropower and Pumped Storage

基　　金：中国博士后科学基金面上资助,资助编号2022M711768;清华大学水沙科学水利水电工程国家重点实验室及宁夏银川水联网数字治水联合研究院联合开放研究基金资助课题,项目编号sklhse-2022-Iow13。

摘　　要：为早日实现“双碳”目标,以风能和太阳能为代表的新型可再生能源近年来成为能源增长的主力军。为应对新型可再生能源带来的间歇性供电和用电端的需求波动,抽水蓄能正在发挥越来越重要的作用,同时水泵水轮机需要更多地在远离设计点的扩展运行范围内运行,这带来了更多的转轮疲劳破坏等故障现象。针对这种运行方式,建立有效的状态参数趋势分析非常重要。本文针对水泵水轮机的振动特点进行详细分析,提出了一系列表征机组振动特征的性能指标,进而提出类似混流式水轮机综合特性曲线的水泵水轮机机组振动特性曲线。通过对水泵水轮机机组振动特性曲线的趋势分析,可以更准确地评估指标及其趋势以及异常值的识别。本方法被用于某大型水泵水轮机的两年运行的监测。首先,针对机组振动特征,从振动监测数据提取相关特征参数,使用人工神经网络(ANN)对特征参数进行拟合,获得水泵水轮机机组振动特性等值线图。将水泵水轮机机组振动特性曲线同国际标准建议的警报和停机值进行对比,量化评估不同方法对机组状态监测的准确性。最后,针对不同状态监测指标的趋势分析,提出了水泵水轮机状态监测雷达图。结果表明使用动态状态监测指标代替常数值设置动作水平,受试者工作特征(ROC曲线)将得到改善,证明动态状态监测指标可以对水泵水轮机实现更好的诊断能力。In order to achieve the"dual carbon"goal as soon as possible,new renewable energy represented by wind and solar energy have become the main force of energy growth in recent years.Pumped storage energy is playing an increasingly important role in responding to the intermittent power supply and demand fluctuations brought about by new renewable energy sources.At the same time,pump turbines need to operate more within an extended operating range far from the design point,which has led to more failure phenomena such as runner fatigue damage.It is very important to establish effective trend analysis of state parameters for this operating mode.This article provides a detailed analysis of the vibration characteristics of water pump turbines,proposes a series of performance indicators that characterize the vibration characteristics of the unit,and then proposes a vibration characteristic curve of water pump turbine units similar to the comprehensive characteristic curve of mixed flow turbines.By analyzing the trend of the vibration characteristic curve of pump turbine units,it is possible to more accurately evaluate indicators and their trends,as well as identify outliers.This method is used for monitoring the two-year operation of a large water pump turbine.Firstly,based on the vibration characteristics of the unit,relevant feature parameters are extracted from vibration monitoring data,and artificial neural network(ANN)is used to fit the feature parameters to obtain the contour map of the vibration characteristics of the pump turbine unit.Compare the vibration characteristic curve of the pump turbine unit with the alarm and shutdown values recommended by international standards,and quantitatively evaluate the accuracy of different methods for monitoring the unit status.Finally,based on the trend analysis of different status monitoring indicators,a radar chart for pump turbine status monitoring was proposed.The results indicate that using dynamic state monitoring indicators instead of constant values to set action level

关 键 词：水泵水轮机 状态监测 振动特性曲线 故障诊断 

分 类 号：TV743[水利工程—水利水电工程]