【摘要】 针对现有有载分接开关振动特性测试手段单一、采集到的振动切换波形数据信息少，难以形成更准确的故障诊断方法的问题，以有载分接开关内部切换芯子中性点处产生的机械振动信号作为研究对象，构建了以小波包变换、能量特征向量和支持向量机为基础的故障诊断模型。利用小波包变换方法将所采集到的振动信号进行频段分解，通过能量计算，将所获取小波包能量特征向量输入所建立的支持向量机分类器中，并利用支持向量机分类器输出结果实现有载分接开关状态识别和故障诊断。在所搭建的传感测试系统和实验平台上，开展了触头磨损、传动轴卡滞和弹簧削短缺陷状态故障模拟实验。测试时将振动加速度传感器吸附于有载分接开关切换芯子中性点处，并在实验中用油箱中注满变压器油以模拟实际运行状况。实验结果表明，所提出的诊断模型能够利用信号对故障进行分类识别，且具有较高的故障诊断准确率。更多还原

【Abstract】 In view of the problems that the existing on-load tap-changer vibration characteristic test method is single, the vibration switching waveform data information is few, and it is difficult to form a more accurate fault diagnosis method, a fault diagnosis model based on wavelet packet transform, energy eigenvector and support vector machine is proposed for the mechanical vibration signals generated at the neutral points of switching cores in on-load tap-changers. The vibration signal is decomposed into frequency bands by using the wavelet packet transform method. The energy eigenvector of the wavelet packet is input into the established support vector machine classifier through energy calculation, on-load tap-changer state recognition and fault diagnosis are realized by using the output of the support vector machine classifier. The simulation experiments of contact wear, transmission shaft stuck and spring cutting defects were carried out on the sensor test system and experimental platform. During the test, the vibrating accelerometer were adsorbed on the neutral point of the switching core of the on-load tap changer, and the oil tank was filled with transformer oil to simulate the actual operation. The experimental results show that the proposed diagnosis model can classify and identify the faults by using the signals,and has a high accuracy rate of fault diagnosis.更多还原