CAJ | 학술논문

为使瞬变电磁勘探的反演法简单和通用，提出了一种瞬变电磁勘探中的人工神经网络反演法，基于人工神经网络的BP算法，设计和开发了一个自适应的人工神经网络反演系统．该系统避免了复杂的电磁场计算，只需经过学习训练就能够解决复杂的实际问题，而且具有记忆功能，从而使瞬变电磁法的反演工作具有延续性和可继承性．通过对实际的地质数据进行反演，结果表明，该方法是切实可行的．
위사순변전자감탐적반연법간단화통용，제출료일충순변전자감탐중적인공신경망락반연법，기우인공신경망락적BP산법，설계화개발료일개자괄응적인공신경망락반연계통．해계통피면료복잡적전자장계산，지수경과학습훈련취능구해결복잡적실제문제，이차구유기억공능，종이사순변전자법적반연공작구유연속성화가계승성．통과대실제적지질수거진행반연，결과표명，해방법시절실가행적．
A new inversion method of artficial neural network is presented for the purpose of simplification and more general application for the inversion method in transient electromagnetic exploration. On the basis of back propagation(BP) algorithm, an adaptive inversion system of artificial neural network had been designed and developed． The system avoids complicated calculations of electromagnetic field and can be used to solve some practical problems through learning and training．It can also memorize and make the inversion a continuous process which depends not only on current event but also the previous event.The inversion results are in good agreement with geological data.