论文部分内容阅读
针对非线性模拟电路故障的复杂性和非线性,提出一种基于小波领袖多重分形分析和支持向量机的故障诊断方法.首先,采用小波领袖方法对从测试节点采集的信号进行多重分形分析,并将提取的多重分形谱特征构成特征集;然后将特征集输入支持向量机,利用支持向量机的分类功能对电路的模式状态作出决策;最后,视频放大器电路故障诊断实验验证了该方法的有效性.
Aiming at the complexity and nonlinearity of nonlinear analog circuit fault, this paper proposes a fault diagnosis method based on wavelet leader multifractal analysis and support vector machine.Firstly, the wavelet leader method is used to carry out multifractal analysis on the signals collected from the test nodes Then, the feature set is input into support vector machine, and the classification function of SVM is used to make decision on the mode state of the circuit. Finally, the video amplifier circuit fault diagnosis experiment verifies the effectiveness of the method .