论文部分内容阅读
针对现有算法的导数依赖性及其局部优化性能 ,为控制工程中的模型参数估计课题提供一种新思路。把具有概率突跳特性模拟退火 (SA)和基于高维 Euclid空间中凸多面体结构的单纯形搜索法 (SM)有机地结合 ,通过对搜索操作和参数的有效设计 ,提出了一种基于 Sim plex- annealing混合算法 (SMSA)的模型参数估计方法。对以传递函数、状态空间和自回归滑动平均 (ARMA)模型形式表达的不同典型对象进行仿真 ,结果表明 :SMSA方法在模型结构已知的情况下可准确地估计参数 ,其性能明显优于单一遗传算法(GA)
Aiming at the derivative dependence of existing algorithms and its local optimization performance, this paper provides a new idea for the control of model parameter estimation in engineering. Combining Simulated Annealing (SA) with probability sudden jump and Simplex Search (SM) based on convex polyhedron structure in high dimensional Euclid space, an effective design of search operation and parameters was proposed based on Sim plex - annealing hybrid algorithm (SMSA) model parameter estimation method. The simulation results of different typical objects expressed in transfer function, state space and autoregressive moving average (ARMA) model show that the SMSA method can accurately estimate the parameters under the condition that the model structure is known, and its performance is obviously better than single Genetic Algorithm (GA)