基于改进果蝇算法的模拟电路故障诊断

针对模拟电路中非线性元件故障的定位问题，提出一种改进的果蝇算法优化支持向量机的故障诊断方法。首先对被诊断电路的输出信号进行采样，用Volterra级数提取输出信号的特征，然后利用改进的果蝇算法优化SVM的核函数参数和结构参数，建立诊断模型，在对数放大器电路中对故障进行诊断分类。通过实验可以看出，该方法能够有效避免支持向量机参数选择的随机性，有利于提高诊断精度，并且有较快的诊断速度。

Analog Circuit Fault Diagnosis Based on Modified Fruit Fly Optimization Algorithm

Aiming at the problem of the localization of nonlinear components in analog circuits, an improved Drosophila algorithm is proposed to optimize the support vector machine (SVM) fault diagnosis method. Firstly, the output signal of the diagnosed circuit is sampled, the characteristics of the output signal are extracted by the Volterra series, and then the improved fruit fly algorithm is used to optimize the kernel function parameters and structural parameters of the SVM. The diagnosis model is established and the fault is established in the logarithmic amplifier circuit for diagnostic classification. Using MATLAB software to carry out simulation experiments, through experiments we can see that this method can effectively avoid the random selection of support vector machine parameters, help to improve the diagnostic accuracy and diagnostic speed.