基于Relief-FP算法的电力变压器运行状态检测方法  

Power transformer operation state detection method based on relief FP algorithm

作　　者：高博 朱超 茆超 叶承晋[3] 王蕾 GAO Bo;ZHU Chao;MAO Chao;YE Chengjin;WANG Lei(Jiashan Power Supply Company,Jiashan,Zhejiang 314100,China;Economic and Technological Research Institute of State Grid Zhejiang Electric Power Co.,LTD.,Hangzhou,310000,China;College of Electrical Engineering,Zhejiang University,Hangzhou 310058,China)

机构地区：[1]国网浙江省电力有限公司嘉善供电公司,浙江嘉善314100 [2]国网浙江省电力有限公司经济技术研究院,杭州310000 [3]浙江大学电气工程学院,杭州310058

出　　处：《自动化与仪器仪表》2023年第2期70-75,共6页Automation & Instrumentation

基　　金：国网浙江省电力公司科技项目(No.2021ZK11)。

摘　　要：为了确保变压器正常工作,降低故障发生带来的重大损失,提出一种基于Relief-FP算法的电力变压器运行状态检测方法。由于压电加速度传感器内部晶体电压量与作用力成正比,为极化电容器,将收集到的变压器振动信号实施数字转换,方便保存和分析。选取样本中的待选参数赋予权数,通过程序训练得到特征参数和样本类型相关性,利用Relief算法获得参数类型。根据关联规则支持度,得出变压器故障和状态量超标间关联,算出综合状态量内单项的置信度,若置信值权重系数大则判断为故障。通过仿真模拟实验,证明所提算法能够明确当前变压器运行状态,准确检测到故障问题。In order to ensure the normal operation of transformer and reduce the heavy loss caused by fault, a power transformer operation state detection method based on relief FP algorithm is proposed. The internal crystal voltage of the piezoelectric acceleration sensor is directly proportional to the force. It is a polarized capacitor, which converts the collected transformer vibration signal, so as to save the data for analysis. Select the parameters to be selected in the sample, give the weight, obtain the correlation between the characteristic parameters and the sample type through program training, and obtain the parameter type by using the relief algorithm. According to the support degree of association rules, transformer faults are associated with excessive state quantities;Calculate the confidence degree of single item in the comprehensive state quantity, compare the size of all confidence coefficients, and determine the weight coefficient. Through simulation experiments, it is proved that the proposed algorithm can clearly understand the operation state of the transformer and accurately detect the fault problem.

关 键 词：Relief-FP算法 电力变压器 故障状态检测 振动信号采集 特征参数提取 

分 类 号：TP274[自动化与计算机技术—检测技术与自动化装置] TM406[自动化与计算机技术—控制科学与工程]