基于GMKL-SVM的模拟电路故障诊断方法
发布时间：2019-03-07 08:27
【摘要】：提出了一种新颖的基于广义多核支持向量机(GMKL-SVM)的模拟电路故障诊断方法。首先,应用Haar小波分析提取被测电路时域响应信号的小波系数作为特征参量,并生成样本数据;然后,基于样本数据,应用量子粒子群算法对GMKL-SVM的参数进行优化,并以此建立基于GMKL-SVM的故障诊断模型,用于区分模拟电路的各个故障。实例电路的单故障和双故障诊断实验结果表明,所提出的GMKL-SVM方法能较好地实现模拟电路故障诊断,与传统的GMKL-SVM方法相比,表现出了更好的性能,获得了更高的故障诊断正确率。
[Abstract]:A novel fault diagnosis method for analog circuits based on generalized multi-kernel support vector machine (GMKL-SVM) is proposed. Firstly, the wavelet coefficients of the time-domain response signal of the tested circuit are extracted by Haar wavelet analysis as the characteristic parameter, and the sample data are generated. Then, based on the sample data, quantum particle swarm optimization (QPSO) is applied to optimize the parameters of GMKL-SVM, and then a fault diagnosis model based on GMKL-SVM is established to distinguish the faults of analog circuits. The experimental results of single-fault and double-fault diagnosis show that the proposed GMKL-SVM method can realize analog circuit fault diagnosis better than the traditional GMKL-SVM method, and the performance of the proposed method is better than that of the traditional fault diagnosis method. A higher accuracy rate of fault diagnosis is obtained.
【作者单位】： 合肥工业大学电气与自动化工程学院;安庆师范大学物理与电气工程学院;
【基金】：国家自然科学基金重点项目(51637004);国家自然科学基金(51577046,51607004) 国家重点研发计划“重大科学仪器设备开发”(2016YFF0102200) 安徽省科技计划重点项目(1301022036) 安徽省自然科学基金(1608085QF157) 安徽省高校优秀青年人才支持计划重点项目(gxyq ZD2016207) 安徽省高等学校自然科学研究重点项目(KJ2016A431)资助
【分类号】：TN710
，
本文编号：2435943
[Abstract]:A novel fault diagnosis method for analog circuits based on generalized multi-kernel support vector machine (GMKL-SVM) is proposed. Firstly, the wavelet coefficients of the time-domain response signal of the tested circuit are extracted by Haar wavelet analysis as the characteristic parameter, and the sample data are generated. Then, based on the sample data, quantum particle swarm optimization (QPSO) is applied to optimize the parameters of GMKL-SVM, and then a fault diagnosis model based on GMKL-SVM is established to distinguish the faults of analog circuits. The experimental results of single-fault and double-fault diagnosis show that the proposed GMKL-SVM method can realize analog circuit fault diagnosis better than the traditional GMKL-SVM method, and the performance of the proposed method is better than that of the traditional fault diagnosis method. A higher accuracy rate of fault diagnosis is obtained.
【作者单位】： 合肥工业大学电气与自动化工程学院;安庆师范大学物理与电气工程学院;
【基金】：国家自然科学基金重点项目(51637004);国家自然科学基金(51577046,51607004) 国家重点研发计划“重大科学仪器设备开发”(2016YFF0102200) 安徽省科技计划重点项目(1301022036) 安徽省自然科学基金(1608085QF157) 安徽省高校优秀青年人才支持计划重点项目(gxyq ZD2016207) 安徽省高等学校自然科学研究重点项目(KJ2016A431)资助
【分类号】：TN710
，
本文编号：2435943
本文链接：https://www.wllwen.com/kejilunwen/dianzigongchenglunwen/2435943.html
