CAJ | 학술논문

为提高模拟电路故障诊断效率,将小波包变换和支持向量机结合起来,提出了一种完整的模拟电路故障快算检测和准确定位的方案.利用小波包变换对电路输出电压信号进行多层分解,提取各频带的能量作为故障特征,给出了具体的特征提取方法;利用支持向量机的多分类一对一方法,完成电路的故障定位,同时实现了小波函数的选择.在一模拟电路的故障仿真实验中,通过与BP,RBF和PNN等神经网络对比,结果显示该方法的诊断效率是很高的.
위제고모의전로고장진단효솔,장소파포변환화지지향량궤결합기래,제출료일충완정적모의전로고장쾌산검측화준학정위적방안.이용소파포변환대전로수출전압신호진행다층분해,제취각빈대적능량작위고장특정,급출료구체적특정제취방법;이용지지향량궤적다분류일대일방법,완성전로적고장정위,동시실현료소파함수적선택.재일모의전로적고장방진실험중,통과여BP,RBF화PNN등신경망락대비,결과현시해방법적진단효솔시흔고적.
To improve the efficiency of analog circuit fault diagnosis,a method based on wavelet packet transform and SVM is proposed. Wavelet packet transform is used to extract fault features from the signal of the circuit output voltage The specific feature extraction method is introduced Multi-class one vs one method of SVM carries out the faults classification And it chooses the proper wavelet function This method, BP, RBF, and PNN are used in the faults simulation experiment of some analog circuit The result shows that this method is much better than others.