实数编码人工免疫算法概率强收敛速度估计研究

取代传统的状态转移矩阵特征值估计方法,运用随机过程相关理论,对实数编码人工免疫算法的收敛速度估计进行了研究,该方法从满足人工免疫算法概率强收敛的必要条件出发,将其作为一般人工免疫算法符合的充分条件,提出了一种实数编码人工免疫算法指数速度概率强收敛的估计新方法.该方法以种群中最佳抗体的最终收敛为判断依据,避免了传统估计方法过于保守的不足,可用于一类人工免疫算法的收敛性和收敛速度的判断,在人工免疫算法实际应用中如何优化其收敛速度具有一定理论参考意义.

Probability-based Strong Convergence Rate Estimation of Real Coded Artificial Immune Algorithm

Instead of the traditional state transition matrix eigenvalue estimation methods,the convergence rate estimation of real coded artificial immune algorithm(RCAIA) is studied based on the stochastic processes theory.The method begins with analyzing the necessary condition for probability-based strong convergence of artificial immune algorithm and takes it as the sufficient condition of a class of RCAIA,and the probability-based strong convergence exponential rate estimation method of RCAIA is proposed.The final convergence of the best antibody is taken as convergence judgment,which can overcome the conservative defect of traditional estimation methods.The method can be used to analyze the convergence and convergence rate of a class of artificial immune algorithms.The research can be used to optimize the convergence rate in the practical application of artificial immune algorithms.