全卷积神经网络在垃圾土勘察中的应用
摘要:垃圾土与原土壤往往存在电阻率差异，常用垃圾土探测方法是高密度电阻率法和时域电磁法，而对反演结果的人工解译效率低，且准确性难以保证。通过全卷积神经网络在垃圾土勘察中的应用，识别某拆后绿地改造工程地下建构筑物垃圾土探测数据，确定垃圾土范围，表明了本方法的有效性、实用性和可靠性，为垃圾土勘察、土方量计算和改善土地性状等提供参考。
Abstract:Due to the difference in resistivity between the garbage and the original soil, the most commonly used garbage soil detection methods are high-density resistivity method and time-domain electromagnetic method. However, the low efficiency of manual interpretation of inversion results and the difficulty in ensuring accuracy still need further study. This research introduces the application of the full convolution neural network in the garbage soil investigation. Through the identification of the garbage soil detection data of the underground buildings of a demolished green space reconstruction project, the garbage soil range was determined, which shows the effectiveness, practicability and reliability of this method. It is the reference basis for waste soil investigation, earthwork calculation and improvement of land properties.
中文标题：
全卷积神经网络在垃圾土勘察中的应用
Application of Full Convolution Neural Network in Garbage Soil Investigation
作者：
徐四一,张旭
Xu Siyi,Zhang Xu
作者简介:徐四一，男，1964年生，汉族，安徽安庆人，大学本科，研究员，主要从事岩土工程等咨询研究工作。E-mail：xsy802@126.com
通讯地址：
上海山南勘测设计有限公司，上海 201206
ShanghaiEaseAsiaGeophysicalProspectingCo.,Ltd.,Shanghai201206,China
中图分类号:P631.3
doi:10.3969/j.issn.1007-2993.2024.01.013
出版物：岩土工程技术
收稿日期:2023-03-15
刊出日期:2024-02-05
关键词:全卷积神经网络,垃圾土,高密度电阻率法,异常识别
Key words:full convolution neural network,garbage soil,high-density resistivity method,abnormal recognition
文档包含图片数量：图片(8)张
文档包含表格数量：表格(0)个
参考文献：
[1]侯军林,毛歆燕. 浅谈垃圾土的工程性质[J]. 甘肃冶金,2010,32(4):98-100, 113.
[2]孟云伟,汪 洋. 垃圾土的工程性质研究现状[J]. 重庆交通学院学报,2006,25(z1):150-154.
[3]陆晓松,王国庆,李勖之,等. 场地环境大数据采集和机器学习方法在污染智能识别中的应用研究进展[J]. 生态与农村环境学报,2022,38(9):1101-1111.
[4]能昌信,孙晓晨,徐 亚,等. 基于深度卷积神经网络的场地污染非线性反演方法[J]. 中国环境科学,2019,39(12):5162-5172.
[5]LONG J,SHELHAMER E,DARRELL T. Fully convolutional networks for semantic segmentation[J]. IEEE Transactions on Pattern Analysis and Machine Intel—ligence,2015,39(4):640-651.
[6]李风生. 基于深度学习的地电高阻污染异常识别技术研究[D]. 上海: 同济大学, 2021.
基金项目：
- 文件大小:
- 2.07 MB
- 下载次数:
- 60
-
高速下载
|
|
