论文部分内容阅读
针对含有未知时滞的多输入单输出有限脉冲响应系统，根据系统参数化后具有的稀疏特性，基于压缩感知原理，将匹配追踪方法和梯度搜索原理相结合，在有限采样数据下，提出了可以同时估计系统参数和时滞的梯度追踪算法。该算法同正交匹配追踪算法相比，梯度追踪算法具有较小的计算量。最后通过仿真验证了算法的有效性。“,”For multiple-input single-output finite impulse response (MISO-FIR)systems with unknown time de-lays,we combine the matching pursuit method and the gradient search principle,according to the sparsity of the parameterized model based on the compressed sensing theory,and propose a gradient pursuit algorithm for simultaneously estimating parameters and time delays with limited sampling data.The proposed method re-duces the associated computational burden compared with that of the orthogonal matching pursuit algorithm. The simulation results show the effectiveness of the proposed algorithm.