改进实数编码量子进化算法及其在参数估计中的应用

Improved real-coded quantum evolutionary algorithms and its application on parameter estimation

借鉴量子计算的相关概念和原理,提出一种改进实数编码量子进化算法(IRCQEA).算法的核心是依据染色体的具体形式和目标函数的梯度信息设计互补变异进化染色体,以实现局部搜索和全局搜索的平衡;根据算法的进化过程动态缩小搜索空间,以加快收敛速度.对标准数值优化问题的求解结果表明,该算法具有寻优能力强、搜索精度高和稳定性好等优点.以非线性系统参数估计问题为例进行的仿真实验表明,所提出的算法能够有效提高估计参数的精度.

Referring to the relational concepts and principles of quantum computing, an improved real-coded quantum evolutionary algorithm is proposed. The core of this algorithm is that, a complementary mutation operator, which is designed based on the specific configuration of real-coded chromosome and the gradient information of objective function, is used to update chromosomes and can treat the balance between exploration and exploitation. And a technique of dynamic reducing the search space is adopted to improve the convergence rate of algorithm, which is implemented on the basis of the evolutionary process of algorithm. Simulation results on benchmark numerical optimization show that the algorithm has the characteristics of more powerful optimizing ability, higher searching precision and better stability. Finally, with the parameter estimation of nonlinear system, simulation experiments are performed and the results show that the algorithm can improve the precision of estimation parameters efficiently.