首页> 外国专利> TBM Apparatus for predicting advance rate of shield tunnel boring machine and method thereof

TBM Apparatus for predicting advance rate of shield tunnel boring machine and method thereof

机译:盾构隧道掘进机掘进速度预测的TBM装置及其方法

摘要

The present invention relates to an apparatus and method for predicting the actual drilling speed of shield TBM. According to the present invention, for each of the plurality of sites previously constructed, a plurality of ground factors measured corresponding to the site, and the DB, which stores the field penetration index calculated based on the actual excavation speed of the site, which is one of the ground factors A clustering unit for correcting the rock class and updating and reflecting the data in the DB, projecting coordinate points corresponding to a plurality of ground factors after the update to the input vector space, and fuzzy clustering each coordinate point into a plurality of clusters; Neural network learning unit for learning neural networks by applying a plurality of ground factors and field penetration indexes to the input and output nodes of the adaptive neuro fuzzy neural network (ANFIS) constructed based on the membership function by fuzzy clustering. Input the plurality of ground factors acquired for the predetermined construction target site into the learned neural network in the same manner as the established construction site, It includes prediction unit configured to predict the Penetration Index. According to the present invention, it is possible to train the ground factors and field penetration index acquired in the past construction site in the neural network, to predict the site penetration index only with the ground data of the construction site, and based on this, it is possible to reliably predict the actual drilling speed. Prediction errors in construction costs and construction time can be greatly reduced.
机译:本发明涉及一种用于预测盾构TBM的实际钻速的装置和方法。根据本发明,对于先前构造的多个场所中的每一个,测量与该场所相对应的多个地面因素,以及DB,其存储基于该场所的实际开挖速度而计算出的场穿透指数,即地面要素之一聚类单元,用于校正岩石等级并更新和反映数据库中的数据,在更新到输入向量空间后投影与多个地面要素相对应的坐标点,并将每个坐标点模糊聚类为多个集群;神经网络学习单元,用于通过基于模糊聚类的隶属函数构造的自适应神经模糊神经网络(ANFIS)的输入和输出节点应用多个地面因素和场穿透指标来学习神经网络。以与所建立的施工现场相同的方式将针对预定施工目标现场获取的多个地面因素输入到学习的神经网络中。其包括被构造为预测渗透指数的预测单元。根据本发明,可以在神经网络中训练在过去的建筑工地中获取的地面因素和场穿透指数,以仅利用建筑地的地面数据来预测场穿透指数,并基于此,可以可靠地预测实际钻孔速度。可以大大减少建造成本和建造时间的预测误差。

著录项

  • 公开/公告号KR102003612B1

    专利类型

  • 公开/公告日2019-10-01

    原文格式PDF

  • 申请/专利权人 인하대학교 산학협력단;

    申请/专利号KR20170159530

  • 发明设计人 송기일;이항로;

    申请日2017-11-27

  • 分类号G06F17/50;E21D9/06;G06N3/08;

  • 国家 KR

  • 入库时间 2022-08-21 11:48:08

相似文献

  • 专利
  • 外文文献
  • 中文文献
获取专利

客服邮箱:kefu@zhangqiaokeyan.com

京公网安备:11010802029741号 ICP备案号:京ICP备15016152号-6 六维联合信息科技 (北京) 有限公司©版权所有
  • 客服微信

  • 服务号