中文摘要：

虽然VolterraLMS（VLMS）算法简单，计算量小，但是由于Volterra滤波器系统是非线性的，使得输入向量自相关矩阵包含了输入信号的高阶统计量，导致矩阵特征值扩展很大，因此其收敛速度一般很慢。为加快收敛速度，利用格型滤波器后向预测误差的正交特性，提出采用两个格型滤波器正交顸处理的自适应Volterra滤波算法。仿真结果表明，该算法具有比VLMS算法和GPV算法更为优越的收敛性能。

英文摘要：

LMS adaptive algorithm of second order Volterra filter has the simple structure and little computational complexity. For Volterra system is nonlinear, the impact of nonlinear operations on the input signal results in that the date correlation matrix consists of higher order statistics and eigen values spread, so its convergence speed is very slow. In order to solve this problem,an adaptive algorithm of second order Volterra filter using two lattice filters as pre- processing is proposed. This algorithm uses the orthogonalization property of backward prediction error which can weaken the nonuniform convergence be- havior. Finally,computer simulation results illustrate that the performance of the proposed algorithm is superior to VLMS algorithm and GPV algorithm.