引用本文: | 刘庆珍,黄昌硕.基于FCBF特征选择和XGBoost原则的油纸绝缘介电响应特征量优选研究[J].电力系统保护与控制,2022,50(15):50-59.[点击复制] |
LIU Qingzhen,HUANG Changshuo.Optimization of dielectric response characteristics of oil paper insulation based onFCBF feature selection and the XGBoost principle[J].Power System Protection and Control,2022,50(15):50-59[点击复制] |
|
摘要: |
针对高维特征空间中存在的相关特征、冗余特征等导致变压器油纸绝缘综合诊断的特征空间提取存在平均误差大、分类正确率低等问题,提出一种基于快速过滤相关算法和极限梯度上升相结合的特征量优选策略。首先,根据变压器的介电响应实测数据,提取多种类别的时域介电特征量形成初始高维特征空间。其次,提出一种两级式时域特征选择方法,第一级采用快速相关过滤算法剔除低相关、高冗余的特征量,第二级依照极限梯度提升评估特征的重要度,从而确定最优特征空间。最后设置不同对照组对最优特征空间进行对比论证,有效验证了采取所提优选策略得到的最优特征空间的合理性及准确性。 |
关键词: 油纸绝缘 综合诊断 快速相关过滤算法 极限梯度上升 特征选择 |
DOI:DOI: 10.19783/j.cnki.pspc.211401 |
投稿时间:2021-10-18修订日期:2021-12-29 |
基金项目:国家自然科学基金项目资助(61174117) |
|
Optimization of dielectric response characteristics of oil paper insulation based onFCBF feature selection and the XGBoost principle |
LIU Qingzhen,HUANG Changshuo |
(College of Electrical Engineering and Automation, Fujian Key Laboratory of New Energy Generation and
Power Conversion, Fuzhou University, Fuzhou 350108, China) |
Abstract: |
There are problems of large average error and low classification accuracy in feature space extraction of transformer oil-paper insulation comprehensive diagnosis. These problems are due to the existence of correlation and redundant features in high-dimensional feature space. Thus a feature quantity optimization strategy based on a fast filtering correlation algorithm and limit gradient rise is proposed. First, from the measured data of transformer dielectric response, various kinds of time-domain dielectric characteristics are extracted to form the initial high-dimensional feature space. Secondly, a two-stage time-domain feature selection method is proposed. In the first stage, a fast correlation filtering algorithm is used to eliminate the features with low correlation and high redundancy, and in the second stage the importance of features is evaluated according to the limit gradient, so as to determine the optimal feature space. Finally, different control groups are set for comparative demonstration of the optimal feature space. This effectively verifies the rationality and accuracy of the optimal feature space obtained by adopting the optimal strategy proposed above.
This work is supported by the National Natural Science Foundation of China (No. 61174117). |
Key words: oil-paper insulation comprehensive diagnosis fast correlation filtering algorithm limit gradient rise feature selection |