海底观测网小功率DC/DC变换器健康状态判别方法  

Health Condition Identification Method for Low Power DC/DC Converter in Seafloor Observatory Network

作　　者：岳继光[1] 潘杰 夏乾 吕枫[2] YUE Ji-guang;PAN Jie;XIA Qian;LV Feng(College of Electronics and Information Engineering,Tongji University,Shanghai 200092,China;State Key Laboratory of Marine Geology,Tongji University,Shanghai 200092,China)

机构地区：[1]同济大学电子与信息工程学院,上海200092 [2]同济大学、海洋地质国家重点实验室,上海200092

出　　处：《自动化与仪表》2023年第4期1-5,共5页Automation & Instrumentation

基　　金：同济大学学科交叉联合攻关首批示范项目(ZD-22-202103);上海市自然科学基金项目(22ZR1464500)。

摘　　要：在海底观测网DC/DC变换器输出信号特征信息不明显的情况下,该文提出一种根据变换器输出信号过渡过程信息判断变换器健康状态的方法。以正激变换器为实验电路,采集输出信号过渡过程的数据,通过离散小波辅助EM算法构建高斯混合模型,实现对DC/DC变换器软故障的预警;当预警出现时,通过输出信号的过渡过程数据,利用基于所建数据样本库训练的SVM分类器,判断变换器所属状态。仿真实验表明所提方法的有效性。Under the condition that the characteristic information of output signal of DC/DC converter is not obvious,a method to judge the health condition of converter based on the transient process information of output signal is proposed.Taking a forward converter as the experimental circuit,the transient process data of the output signal is collected,and the Gaussian mixture model is constructed by the discrete wavelet aided EM algorithm to realize the early warning of DC/DC converter fault.When the warning occurs,the transient process data of the output signal is used to judge the condition of the converter by using the SVM classifier trained on the self-built database.Simulation results show the effectiveness of the proposed method.

关 键 词：健康状态判别 高斯混合模型 EM算法 小波分析 SVM分类器 

分 类 号：TP274.2[自动化与计算机技术—检测技术与自动化装置] TP319[自动化与计算机技术—控制科学与工程]