摘要
针对换流器产生谐波的主要特征进行分析,提出一种改进型的小波神经网络,增加了处理层,采用了神经树的网络结构。在Matlab中进行了仿真和数据分析,结果表明:相较于普通的小波神经网络改进的小波神经网络具有较好的检测精度和误差率。
The main characteristics of the harmonic generated from the converter were analyzed and an improved wavelet neural network was proposed,which boasts improved processing layer and neural tree network structure. Simulation with Matalab shows that as compared to the ordinary wavelet neural network,the improved one has better detection speed and smaller error rate.
出处
《化工自动化及仪表》
CAS
2016年第5期491-494,共4页
Control and Instruments in Chemical Industry
基金
黑龙江省教育厅科技攻关项目(12531062)
