陈啸轩,邹阳,翁祖辰,林锦茄,林昕亮,张云霄.基于IKNN和LOF的变压器回复电压数据清洗方法研究[J].电子测量与仪器学报,2024,38(2):92-100 |
基于IKNN和LOF的变压器回复电压数据清洗方法研究 |
Recovery voltage data cleaning method for transformerbased on IKNN and LOF |
|
DOI: |
中文关键词: 油纸绝缘 特征数据清洗 局部离群因子算法 回复电压极化谱 改进K最近邻算法 |
英文关键词:oil-paper insulation feature data cleaning local outlier factor algorithm recovery voltage polarization spectrum improved K-nearest neighbor algorithm |
基金项目:国家自然科学基金重大研究计划培育项目(92266110)、福建省自然科学基金项目(2019J01248)资助 |
|
Author | Institution |
Chen Xiaoxuan | School of Electrical Engineering and Automation of Fuzhou University, Fuzhou 350108, China |
Zou Yang | School of Electrical Engineering and Automation of Fuzhou University, Fuzhou 350108, China |
Weng Zuchen | School of Electrical Engineering and Automation of Fuzhou University, Fuzhou 350108, China |
Lin Jinjia | School of Electrical Engineering and Automation of Fuzhou University, Fuzhou 350108, China |
Lin Xinliang | School of Electrical Engineering and Automation of Fuzhou University, Fuzhou 350108, China |
Zhang Yunxiao | School of Electrical Engineering and Automation of Fuzhou University, Fuzhou 350108, China |
|
摘要点击次数: 178 |
全文下载次数: 349 |
中文摘要: |
基于回复电压极化谱提取特征参量是目前广泛应用的变压器油纸绝缘状态评估方法,但极化谱易受工况干扰、人工失误等因素影响而出现特征数据异常的情况,严重降低评估准确性。针对上述问题,该文提出了一种基于局部离群因子(LOF)和改进K最近邻(IKNN)的回复电压数据清洗方法。首先,选取回复电压极化谱的回复电压极大值Urmax、初始斜率Sr与主时间常数tcdom作为老化特征参量,并基于LOF算法对非标准极化谱中的异常特征量数据进行识别与筛除。其次,利用模糊C均值(FCM)聚类算法减小噪声点对KNN算法的干扰,并通过加权欧氏距离标度突出各特征量间的关联性,进而构建出基于IKNN的数据填补模型架构以实现特征缺失数据的填补。最后,代入多组实测数据验证所提数据清洗方法的实效性。结果表明,数据清洗后的状态评估准确率相较于原有数据上升了50%左右,有效提高了变压器回复电压数据质量,为准确感知变压器运行状况奠定坚实的基础。 |
英文摘要: |
Extracting feature parameters from the recovery voltage polarization spectrum is currently a widely adopted method for evaluating the status of transformer oil-paper insulation. However, the polarization spectrum is prone to anomalous feature data due to factors such as working condition interference and artificial errors, which seriously reduces the accuracy of the evaluation. In response to the above issues, this paper proposed a recovery voltage data cleaning method based on local outlier factor (LOF) and improved K-nearest neighbor (IKNN). Firstly, Maximum recovery voltage Urmax, the initial slope Sr and dominant time constant tcdom of the recovery voltage polarization spectrum were selected as aging feature parameters, and anomalous feature data in the non-standard polarization spectrum were identified and filtered out based on the LOF algorithm. Secondly, the Fuzzy C-means (FCM) clustering algorithm was used to reduce the interference of noise points on the KNN algorithm, and the correlations between various features were highlighted by weighted Euclidean distance scale. Then, a data filling model architecture based on IKNN was constructed to fill in missing feature data. Finally, multiple sets of measured data were incorporated to validate the effectiveness of the proposed data cleaning method. The results indicate that the accuracy of status evaluation after data cleaning has increased by about 50% compared to the original data, which effectively improves the quality of transformer recovery voltage data and lays a solid foundation for accurate perception of transformer operation status. |
查看全文 查看/发表评论 下载PDF阅读器 |
|
|
|