電阻層析成像模塊

　　基于生成對(duì)抗網(wǎng)絡(luò)的地鐵盾構(gòu)超前探測(cè)方法研究

　　Research on Advanced Detection Method of Metro Shield Machine Based on Generative Adversarial Networks

　　背景介紹

　　Background

　　盾構(gòu)機(jī)（簡(jiǎn)稱TBM）以其施工安全的gao xiao特點(diǎn)被廣泛應(yīng)用于地鐵隧道建設(shè)中，TBM施工過(guò)程中經(jīng)常會(huì)出現(xiàn)預(yù)料不到的塌方、突涌水等地質(zhì)災(zāi)害，這嚴(yán)重影響工程的進(jìn)展，增加工程的造價(jià)。本文案采用聚焦直流電法超前探測(cè)技術(shù)，以TBM前方不良地質(zhì)體的反演成像作為目標(biāo)，引入生成對(duì)抗網(wǎng)絡(luò)算法 。

　　Shield boring machine (TBM) is widely used in subway tunnel construction with its safe and efficient construction characteristics, and unexpected geological disasters such as landslides and water inrushes often occur during TBM construction, which seriously affects the progress of the project and increases the cost of the project. In this paper, the advanced detection technology of focused direct current method is adopted, and the generative adversarial network algorithm is introduced by taking the inversion imaging of bad geological bodies in front of TBM as the goal

　　關(guān)鍵技術(shù)1：聚焦直流電法盾構(gòu)超前探測(cè)技術(shù)

　　The focused direct current (DC) electrical method for advance detection in shield tunneling

　　關(guān)鍵技術(shù)2：二維有限元正演模擬

　　Two-dimensional finite element forward simulatio

　　關(guān)鍵技術(shù)3：基于相似性原理的物理模型實(shí)驗(yàn)

　　Physical model experiments based on the principle of similarity