摘要近年来，人们对无限冲激响应(infinite impulse response，IIR)滤波器有了更多 的关注，因为在许多应用领域，如语音识别、音响和通信，都强烈依赖于自适应 信号处理。对于一些系统辨识问题，自适应 IIR 滤波器试图根据自适应滤波器输 出和未知设备输出之间的误差函数来描述未知系统的特性。为了获得令人满意的 识别结果，有必要找到合适的滤波器系数，这个系数可以使自适应 IIR 滤波器输 出和设备输出之间产生的误差最小。69635

本篇文章对 IIR 系统的识别问题进行研究。首先对数字滤波器进行介绍，并 着重介绍了 IIR 数字滤波器。IIR 系统识别的实质是通过自适应算法来改变自适 应 IIR 滤波器的参数，识别基于 IIR 模型设计而实际未知的 IIR 系统。所以针对 这一问题，提出了用粒子群优化算法(particle swarm optimization，PSO)来进行 IIR 系统识别，同时介绍了几种基于 PSO 算法的改进算法。利用粒子群优化算法， 将系统的辨识问题转化为滤波器参数的优化问题，并利用粒子群优化算法对整个 参数空间进行优化，最终获得最优解。利用 MATLAB 进行了仿真实验，首先通 过仿真观察并分析噪声对于无限冲激响应系统识别造成的影响，接着验证了几种 算法的有效性，并证明了这些算法的全局性，同时获得了这几种算法的比较结果。

该论文有图 13 幅，表 15 个，参考文献 35 篇。

毕业论文关键词：IIR 系统识别 粒子群优化算法 参数 最优化

Research on Identification of Infinite Impulse Response System

Abstract In recent years, people have been more concerned about the IIR filter, because in many applications, such as speech recognition, audio and communication, are strongly dependent on the adaptive signal processing. For some system identification problems, an adaptive IIR filter is used to describe the characteristics of the unknown system according to the error function between the output of the adaptive filter and the output of the unknown device. In order to obtain satisfactory results, it is necessary to find a suitable filter coefficient, which can decrease the error between the output of the adaptive IIR filter and the output of the device.

In this paper, the problem of the identification of infinite impulse  response system is studied. In the first place, the digital filter is introduced, and the IIR digital filter is introduced emphatically. The essence of IIR system identification is to change the parameters of the adaptive IIR filter with the adaptive algorithm, and to identify the IIR system which is based on the IIR model design but is actually unknown. So, in order to solve this problem, scholars put forward a kind  of  particle swarm optimization algorithm to identify the IIR systems, and several improved algorithms based on PSO algorithm are introduced. The identification problem of the system is transformed into the optimization problem of the filter parameters, and Parameter optimization is through the use of particle swarm optimization algorithm to search the entire parameter space efficiently. The validity of the algorithm is verified by experiments, and the results are compared with the results of several algorithms.

Key Words:IIR  system identification Particle  swarm  optimization algorithm Parameter Optimization

目 录

摘 要 I

Abstract II

目 录 III