蚁群算法在P-Ⅲ型分布曲线参数估计中的应用

Application of Ant Colony Algorithm to Parameter Estimation of P-Ⅲ Type Distribution Curve

针对蚁群算法具有正反馈、并行计算、较强的鲁棒性,通过对标准蚁群算法的修改,提出一种可用于P-Ⅲ型分布曲线参数估值的连续蚁群算法。以黄河循化站实测资料为例,结果表明,基于离差平方和最小准则的蚁群算法所得的P-Ⅲ型曲线参数精度优于矩法、线性矩法和适线法,收敛速度快。

Ant colony algorithm has characteristics of positive feedback, parallel computation and stronger robustness. A continuous ant colony algorithm is proposed to estimate parameters of P-Ⅲ type distribution curve by modifying the standard ant colony algorithm. Take the observation annual maximum discharge of Xunhua Station in the Yellow River for an example. The result shows that the parameters precision obtained by ant colony algorithm with OLS minimum criterion is better than that of the L-moment and curve-fitting method, and convergence speed of the algorithm is quick.