利用自适应混沌遗传粒子群算法反演瑞雷面波频散曲线

Rayleigh surface-wave dispersion curve inversion based on adaptive chaos genetic particle swarm optimization algorithm

为了提高瑞雷面波频散曲线的反演精度,减少反演过程中的多解性,获取更准确的地下横波速度结构,本文从反演算法入手,对基本的粒子群算法进行改进,提出了一种能同步提高全局和局部搜索能力的自适应混沌遗传粒子群算法(ACGPSO):即先采用自适应惯性权重,并设置粒子的节速度,再引入遗传算法的交叉和变异操作及单维全分量的混沌局部搜索。利用该算法对理论模型的无噪和含噪基阶频散曲线进行反演,且针对含噪数据加入二阶与三阶频散曲线进行联合反演。所得反演结果与常规粒子群算法反演结果的对比表明:ACGPSO算法具有更好的稳定性和抗噪性,且基于该算法的联合反演能有效降低解的多解性,显著提高解的精度。对实际数据所做的两步法反演的效果进一步验证了该算法的适用性。

In order to improve the accuracy of Rayleigh surface wave dispersion curve inversion,reduce multi-solutions in the inversion,and obtain a more accurate subsurface shear wave velocity,we propose an adaptive chaotic genetic particle swarm optimization algorithm(ACGPSO)which can simultaneously improve the global and local search capabilities.ACGPSO adopts adaptive inertia weights,sets knots of particles,and introduces the crossover and mutation operation of genetic algorithm,and the single dimensional full component chaotic local search.With the proposed algorithm,fundamental dispersion curves of a theoretical geological model without noise and with noise are inverted,and the first-order and second-order dispersion curves with noise are jointly inverted.Based on the numerical test,the proposed ACGPSO algorithm has better stability and better noise-resistance than conventional algorithms,and its joint inversion can effectively reduce multi-solutions.Real data tests prove the applicability of the proposed algorithm.