基于改进果蝇优化算法优化SVM的模拟电路故障诊断

为提高支持向量机(SVM)在模拟电路故障诊断中的精度,对果蝇优化算法(FOA)进行改进,提取了一种基于改进果蝇优化算法优化SVM的模拟电路故障诊断方法。改进果蝇优化算法(SHFOA)在FOA算法中增加了“学习历史”的策略,增强了果蝇种群的多样性和算法跳出局部最优的能力,可以获得更优的SVM参数,有效地提升了SVM的分类性能。Sallen-Key低通滤波器电路故障诊断和工程应用验证了SHFOA算法提升了SVM的识别效果,获得了更高的故障诊断精度,相比于其他一些方法更有优势。

Fault diagnosis of analog circuit based on SVM optimized by improved fruit fly optimization algorithm

In order to improve diagnosis accuracy of support vector machine(SVM) in analog circuit,fruit fly optimization algorithm was improved and an analog circuit fault diagnosis method based on SVM optimized by improved FOA was proposed. Improved FOA(SHFOA) introduced "study history" strategy to FOA,and improved diversity of fruit fly group and the ability of jump out local optimum. Thus better parameters of SVM can be obtained and classification performance of SVM was improved. Sallen-Key low-pass filter circuit fault diagnosis and engineering application validated that SHFOA improved the identification accuracy of SVM and has a certain superiority when compared with some other methods.