为有效抑制电力线通信(power line communication,PLC)系统中的脉冲噪声,从信号被脉冲噪声影响后正态性被破坏的角度出发,文章提出一种基于广义幂变换的脉冲噪声抑制方法。该方法首先引入Box-Cox变换,通过对接收信号进行幂变换处理,使...为有效抑制电力线通信(power line communication,PLC)系统中的脉冲噪声,从信号被脉冲噪声影响后正态性被破坏的角度出发,文章提出一种基于广义幂变换的脉冲噪声抑制方法。该方法首先引入Box-Cox变换,通过对接收信号进行幂变换处理,使其分布更接近正态分布,又通过推导引入新的零记忆非线性(zero memory non-linearity,ZMNL)函数,以便进一步优化处理效果。此种结合ZMNL函数的Box-Cox变换可改善接收信号的正态性,实现对脉冲噪声的抑制。仿真结果验证所提广义幂变换方法对接收信号的正态性改善效果明显,对脉冲噪声有良好的抑制效果,并且与传统消隐法相比效果更好。展开更多
A new type of ANN (Artificial Neural Network) structure is introduced, and a nonlinear transformation of the original features is proposed so as to improve the learning covergence of the neural network. This kind of i...A new type of ANN (Artificial Neural Network) structure is introduced, and a nonlinear transformation of the original features is proposed so as to improve the learning covergence of the neural network. This kind of improved ANN is then used to analyse the transient stability of two real power systems. The results show that this method possesses better effectiveness and high convergence speed.展开更多
文摘为有效抑制电力线通信(power line communication,PLC)系统中的脉冲噪声,从信号被脉冲噪声影响后正态性被破坏的角度出发,文章提出一种基于广义幂变换的脉冲噪声抑制方法。该方法首先引入Box-Cox变换,通过对接收信号进行幂变换处理,使其分布更接近正态分布,又通过推导引入新的零记忆非线性(zero memory non-linearity,ZMNL)函数,以便进一步优化处理效果。此种结合ZMNL函数的Box-Cox变换可改善接收信号的正态性,实现对脉冲噪声的抑制。仿真结果验证所提广义幂变换方法对接收信号的正态性改善效果明显,对脉冲噪声有良好的抑制效果,并且与传统消隐法相比效果更好。
文摘A new type of ANN (Artificial Neural Network) structure is introduced, and a nonlinear transformation of the original features is proposed so as to improve the learning covergence of the neural network. This kind of improved ANN is then used to analyse the transient stability of two real power systems. The results show that this method possesses better effectiveness and high convergence speed.