改进的模拟退火－单纯形综合反演方法

AN IMPROVED SIMULATED ANNEALING-DOWNHILL SIMPLEX HYBRID GLOBAL INVERSE ALGORITHM

实际中的大量地球物理反演是一个多参数、非线性优化问题，所采用的目标函数，即度量由参数化的理论模型得出的预测值与观测值的吻合程度，往往具有多个局部极值．针对这类问题，本文综合全局反演方法具有的全域搜索能力强、局部方法收敛速度快和“均匀设计”布点效率高的特点，提出了模拟退火－单纯性综合反演方法，并通过一维声波非线性反演验证了这种综合方法的搜索能力和效率．

In practical,a geophysical interesting inversion can be identified as a nonlinear multiparameter oPtimization Problem.The objective function,which is the measureof agreement between data and model prediction,has a complex topography with many local minima.For those problem,a hybrid global inverse algorithm algorithm is derived In this PaPer,which combine the simulated annealing with the downhill simplex method,and substitute the'uniform design'test method for the Monte carlo method.The effectiveness of this scheme is evaluated using the 1-D acoustic waveform inversion.