论文部分内容阅读
针对蚁群算法(ACO)在解决高维非线性搜索问题方面的有效性,提出了基于蚁群优化算法的Bayesian最大后验概率方位估计(ACO-Bayesian)快速方法.该方法将Bayesian最大后验概率函数作为蚁群算法的目标函数,选取若干一维高斯函数的加权和作为连续蚁群算法中信息量概率分布函数,经过有限次迭代得到Bayesian方法的非线性全局最优解.仿真结果表明,ACO-Bayesian方法在保持Bayesian方法优良性能的同时,将Bayesian方法的计算量减少到原来的1/14.水池实验结果验证了ACO-Bayesian方法的正确性和有效性,为其工程应用奠定了基础.
Aiming at the effectiveness of ant colony algorithm (ACO) in solving high-dimensional non-linear search problems, this paper proposes an ACO-Bayesian fast method based on ant colony optimization algorithm. The Bayesian Maximum Posteriori Probability Function As the objective function of ant colony algorithm, the weighted sum of some one-dimensional Gaussian functions is selected as the probability distribution function of information quantity in continuous ant colony algorithm, and the nonlinear global optimal solution of Bayesian method is obtained through finite iterations. The simulation results show that ACO- The Bayesian method reduces the computational cost of the Bayesian method to 1/14, while maintaining the excellent performance of the Bayesian method. The experimental results of the water pool verify the correctness and validity of the ACO-Bayesian method, laying a foundation for its engineering application.