细胞神经网络在重力异常分异中的研究及应用

Study and application of gravity anomaly separation by cellular neural networks

介绍采用细胞神经网络CNN(cellular neural network)方法,对铬铁矿区内的矿体和围岩的重力异常进行分异。首先阐述了CNN方法的原理和算法,采用拟BP学习算法训练网络的权值,用全局误差函数求导方法推导权值的修正公式,讨论了如何根据目标异常训练适合该地质条件的网络的连接权值;其次将重力异常数据预处理,以达到适合CNN方法处理的数据格式和要求;最后由于该矿区内没有已知的重力数据作为网络训练的目标输出,根据相关地质图设置相应的地下构造模型。利用"点元"法分别正演出叠加异常和矿体异常,进而训练出适合全区的网络连接权值,实现了对全区重力异常的分异。应用结果表明,细胞神经网络方法较好地突出该矿区高异常和矿体的边界,只要选择了合适的网络连接权值,就能将横向叠加异常区分开,故CNN方法可以实现矿体和围岩的重力异常分异。

This article describes the separation of the mining of ore bodies and rock gravity anomalies by the cellular neural network method.First the principle and algorithm of CNN method were elaborated,a pseudo-BP algorithm was used to train the weights of neural network,using the global error function derivative method to derive corrected formula of weights,and how to train the network connection weight based on target gravity anomalies in the particular geological conditions were dis-cussed.Secondly,in order to achieve data format and requirements of the CNN processing,do some pretreatment about the gravity anomaly data.Furthermore,since there is no known gravity data in the region as target output in the network training, so set the corresponding subsurface structure model according to the relevant geological map.The superimposed anomaly and the ore anomaly was forward modeled by the “point element”method,and obtained the targeted connection weights by training the network,to fractionate the region gravity anomaly.The results of application show that the neural network well highlight the high anomaly of the mining area and ore body boundary.As long as the appropriate network connection weights are chosen, lateral stacking anomalies can be separated.So the CNN method can serve to separate out the mining of ore bodies and rock gravity anomalies.