文章摘要
基于无监督特征学习的水电机组健康状态实时评价方法
Real-time Assessment Method of Hydropower Unit Health Status Based on Unsupervised Feature Learning
投稿时间:2020-06-17  修订日期:2020-10-12
DOI:
中文关键词: 水电机组  振动信号  无监督特征学习  奇异值分解  自编码器  劣化指标
英文关键词: hydropower units  vibration signal  unsupervised feature learning  singular value decomposition  auto-encoder  deterioration index
基金项目:国家自然科学基金项目(面上项目,重点项目,重大项目),
作者单位E-mail
胡 晓 武汉大学 动力与机械学院 electrichuxiao@163.com 
肖志怀 武汉大学 动力与机械学院 xiaozhihuai@126.com 
刘东 武汉大学 水资源与水电工程科学国家重点实验室  
吴道平 国网江西省电力有限公司电力科学研究院  
查海涛 国网江西省电力有限公司柘林水电厂  
廖志芳 天津市输水系统水锤阀门控制技术企业重点实验室  
摘要点击次数: 1012
全文下载次数: 0
中文摘要:
      水电机组健康状态实时评价是状态监测和劣化预警中的重要内容,传统方法采用单一限值比较,不能体现机组个性特色,且适用机组运行工况有限。同时水电机组的复杂性导致设备的故障类型不可能全部被预先掌握,故障样本的缺乏影响了有监督特征学习方法的实用性。本文提出了以无监督特征学习技术构建水电机组健康状态劣化指标的新方法,充分利用水电机组状态监测系统中海量数据,挖掘机组正常状态关键特征,建立基于特征空间重构奇异值分解的时域劣化指标和基于自编码器重构误差的频域劣化指标,实时量化评价机组健康状态。以国内某水电站机组轴向振动波形为例,验证了劣化指标的有效性。结果表明,所提出的劣化指标能够反映机组健康状态劣化程度,且比常用时域统计指标更清晰地表现劣化趋势,有效评价机组健康状态,实用性更强。
英文摘要:
      Real-time assessment of hydropower units’ health status is an important part of condition monitoring and deterioration warning. Traditional method is realized by comparing the monitoring value with the limit value of vibration, which limits the application range of operation conditions and cannot reflect the individuality of the hydropower unit. Meanwhile, the complexity of the hydropower unit makes the fault types of the equipment impossible to be fully acquired in advance. As a result, the lack of fault samples brings about difficulties for supervised methods. In this paper, a new method for constructing vibration degradation indicators using unsupervised feature learning techniques is proposed. The proposed method makes full use of the large amount of samples in the condition monitoring system of hydropower units and establishes two degradation indicators: (1) time domain degradation indicator based on feature space reconstruction and singular value decomposition; (2) frequency domain degradation indicator based on reconstruction error of auto-encoder. Using the propoed degradation indicators can realize real-time and quantitative assessment of hydropower units’ health status. A hydropower unit’s axial vibration waveform dataset has been employed to testify the effectiveness of the proposed degradation indicators. The results show that the proposed deterioration indicators can effectively reflect the deterioration degree of the health status of hydropower unit. Moreover, Comparison experiment results indicate that the proposed deterioration indicators display the deterioration trend and severity more obviously than the commonly used time-domain statistical indicators.
  查看/发表评论  下载PDF阅读器
关闭