基于特征双重加权支持向量机的放大器性能综合评价研究

摘要

本文针对于现有放大器评价方法的人为因素过大或是成本过高等状况,而提出了基于特征双重加权支持向量机的放大器性能综合评价方法.确定了放大器性能的综合评价系统结构,以高校模拟电子技术实验为依托,采用近一年内由幅频特性测试仪测评所得相关放大器的四项指标构建训练集,然后进行特征双重加权支持向量机的四分类评价.实验表明,该方法优于传统的方法,提高了参数测量的精度,可推广于电子产品的综合性能评价中去.%A novel performance comprehensive evaluation scheme based on feature double weighted support vector machine (FDWSVM) is presented since there exist some problems appeared in the existence evaluation approaches such as artificial factors and higher cost etc. The system structure of the comprehensive evaluation is confirmed firstly. To verify the well property of the proposed method, data acquisition rely on the college analog electronic technology experiments and adopt four indexes of the amplifier performance obtained via amplitude-frequency tester in one year to construct training set. And then the four classifier evaluation actuator based on FDWSVM is generated. Experiment results show that this method is better than the traditional method, such as higher parameters measurement accuracy. And this scheme is applicable to the comprehensive performance evaluation of electronic products.