基于编码—解码模型的D类功率放大器行为建模

D类功率放大器具有优异的传输效率,属于开关类功放,其输出信号存在较大的非线性失真。对D类功率放大器进行行为建模时要同时考虑其非线性和记忆特性。文中将小波变换引入到编码—解码神经网络模型中,提出了小波编码—解码神经网络模型。使用基于门限循环单元的编码—解码模型和小波编码—解码模型进行D类功率放大器的行为建模。实验结果表明,文中提出的D类功率放大器行为模型相比于传统的Voterra-Laguerre模型而言,在信号的时域和频域都具有更高的精度。

Behavior Modeling of Class-D Power Amplifier Based on Encoder-Decoder Model

Class D power amplifiers have excellent transmission efficiency and are classified as power amplifiers. Their output signals have large nonlinear distortion. The behavior modeling of calss-D power amplifier should take into account both nonlinearity and memory characteristics. This study introduced wavelet transform into the encoder-decoder neural network model, and proposed sequence to sequence wavelet neural network model. In this paper, the encoder-decoder model and sequence to sequence wavelet model based on gated recurrent unit were used in the behavior modeling of class-D power amplifier. Experiments results demonstrated that the proposed behavior model of class-D power amplifier had higher precision in time and frequency domain than the traditional Voterra-Laguerre model.