基于GA-BP神经网络算法的高密度电法非线性反演

摘要

高密度电法技术在煤矿地质灾害勘探中发挥着重要的作用.近年来,以BP(Backpropagation)神经网络为代表的一类非线性反演方法被广泛运用到高密度电法的反演中.针对BP神经网络方法在高密度电法反演中存在的易陷入局部极小、收敛缓慢、反演精度差等问题,将BP神经网络算法与遗传算法(Genetic Algorithm,简称GA算法)联合演算,实现高密度电法的二维非线性反演.通过典型地电模型对该方法进行验证,结果表明遗传算法能有效优化BP神经网络的权值和阈值,提高了算法的全局寻优性.%High density resistivity method has played an important role in geological disaster exploration in mining industry. In recent years some non-linear inversion methods represented by BP neural network have been widely used in the two-dimensional inversion of high density resistivity method. Aiming at the shortcomings of BP neural network such as being easy to fall into local minimum, slow convergency and poor inversion accuracy, the pro-posed method tried to combine the genetic algorithm and BP neural network method to achieve the two-dimensional inversion of high density resistivity method. The results of the classical electric model indicated that the genetic algorithm method can optimize the weights and bias of the BP neural network effectively and im-prove the performance of global optimization.