检索结果-南通市图书馆

同方期刊数据库博看期刊评论

在线全文

学校读者我要写书评

暂无评论

TBM破岩关键参数跨工程转换关系

地球科学 2024年第5期49卷 1722-1735页

作者：李海波李旭王双敬陈祖煜荆留杰北京交通大学城市地下工程教育部重点实验室北京100044 中国水利水电科学研究院岩土工程研究所北京100048 中铁工程装备集团有限公司河南郑州450016

TBM信息化施工中采集了海量数据,通过数据挖掘建立机器学习模型,是实现TBM智能化的前提.然而在TBM新建工程初期,由于数据量稀少导致机器学习模型预测效果不佳;同时由于TBM设备结构和刀盘直径存在差异,基于历史工程训练得到的机器学习模... 详细信息

TBM信息化施工中采集了海量数据,通过数据挖掘建立机器学习模型,是实现TBM智能化的前提.然而在TBM新建工程初期,由于数据量稀少导致机器学习模型预测效果不佳;同时由于TBM设备结构和刀盘直径存在差异,基于历史工程训练得到的机器学习模型也并不适用于新建工程.为了解决这一瓶颈问题,基于单刀受力分析、经验方法和扭剪实验模型等多种换算关系推导得到了仅与刀具数量和刀盘直径有关的物理不变量,利用由不变量组成的转换方案,可以对新建工程数据进行转换;之后针对围岩分类和机器学习模型上的应用效果,比选出最佳的破岩关键参数转换方案;进而采用遗传算法,以比选得到的转换方案不变量作为初值,迭代搜索出适合当前工程的最优转换方案不变量.研究结果表明,引绰工程(新建工程)数据经过不变量的转换后输入到引松工程(历史工程)机器学习模型,其刀盘扭矩T和刀盘推力F预测结果的拟合优度R2分别达到了0.84和0.70.本研究采用该转换方案不变量,可将不同工程的TBM施工数据归一化,将其统一到同一个框架下进行分析,实现了基于历史工程数据训练得到的机器学习模型指导新建工程施工.研究结果可为TBM机器学习模型跨工程应用提供参考.

关键词： TBM 机器学习破岩关键参数不变量遗传算法岩土工程工程地质

知识驱动和数据驱动在TBM智能施工机器学习中的应用

在线全文

学校读者我要写书评

暂无评论

土木工程学报 2024年第6期57卷 1-12页

作者：陈祖煜范立涛张云旆肖浩汉王琳西安理工大学省部共建西北旱区生态水利国家重点实验室陕西西安710048 中国水利水电科学研究院流域水循环模拟与调控国家重点实验室北京100048

依托引绰济辽工程(YC)和引松供水工程(YS),从理论分析、统计检验等方面系统回顾并总结基于知识驱动方法提取的现场贯入指标FPI和扭矩贯入指标TPI在TBM智能施工机器学习中的应用。从智能预测围岩分类和掘进参数两方面出发,将基于特征参... 详细信息

依托引绰济辽工程(YC)和引松供水工程(YS),从理论分析、统计检验等方面系统回顾并总结基于知识驱动方法提取的现场贯入指标FPI和扭矩贯入指标TPI在TBM智能施工机器学习中的应用。从智能预测围岩分类和掘进参数两方面出发,将基于特征参数的预测结果与通过数据驱动获得的结果进行比较。研究结果表明:通过知识驱动获取的参数FPI和TPI可以降低数据维度和噪音,提高预测效率。在围岩分类智能预测方面,知识驱动和数据驱动方法均表现出较好的精度水平;在掘进参数预测方面,知识驱动的预测精度远高于数据驱动。作者认为单独使用FPI和TPI或者将其与数据驱动参数结合,可以丰富TBM领域机器学习的输入参数,获得较好的预测成果。

关键词： TPI FPI 知识驱动数据驱动围岩分类掘进参数预测

Probabilistic model of disc-cutter wear in TBM construction:A case study of Chaoer to Xiliao water conveyance tunnel in China

在线全文

学校读者我要写书评

暂无评论

Science China(Technological Sciences) 2023年第12期66卷 3534-3548页

作者： YANG WenKun chen zuyu WU GenSheng XING Hai School of Civil Engineering Institute of Future Underground SpaceSoutheast UniversityNanjing 211189China Department of Geotechnical Engineering China Institute of Water Resources and Hydropower ResearchBeijing 100038China Sinohydro Bureau 6 Co. Ltd.Shenyang 110179China

Disc-cutters play a crucial role in the penetration process during construction using a tunnel boring machine(TBM).Their wear status has a significant impact on working efficiency and costs that accounts for a large part of the *** the wear pattern and characteristics of disc-cutters could provide a valuable guide for field maintenance and cutter replacement *** also provides insight into the wear mechanism of cutters at different positions for optimizing the disc-cutter arrangement *** this study,the cutter wears data of 34 disc-cutters over 643 days in the Chaoer River to Xiliao River water diversion tunnel was *** dataset contains 21862 manual readings measured from 1079 disc-cutters replaced in this *** raw data from the hard copy version was transformed into a digital twin database by eliminating abnormal data,filling in empty values,and performing linear *** has been found that the cutters can pass statistical testing for an exponential probability distribution function with respect to the wear rate(w).The regression ratios of R2are essentially greater than *** findings would help estimate the future service life of a currently working cutter,which means significant savings for the costly *** application of exponential distribution has the advantage of only one shape parameter,λ,whose reciprocal represents both the statistical mean and standard deviation of the wear *** is simple and practically amenable.A preliminary study was carried out to simulate the wear process between two neighboring cutters for drafting a replacement plan for disc-cutters by the Monte Carlo *** prediction results agreed reasonably well with the measured information.

关键词： tunnel boring machine disc-cutter wear wear rate probability model

An approach to quick and easy evaluation of the dam breach flood

在线全文

学校读者我要写书评

暂无评论

Science China(Technological Sciences) 2019年第10期62卷 1773-1782页

作者： chen zuyu PING ZiYi WANG NaiXin YU Shu chen ShuJing Institute of Geotechnical Engineering Zhejiang UniversityHangzhou310027China Key Laboratory of Soft Soils and Geoenvironmental Engineering of Ministry of Education Zhejiang UniversityHangzhou310058China State Key Laboratory of Simulation and Regulation of Water Cycle in River Basin China Institute of Water Resources and Hydropower ResearchBeijing100038China Department of Engineering Training National Academy for Mayors of ChinaBeijing100029China

In the context of an impending dam failure, quick evaluation of dam breach flood is necessary. Previous studies provided an approach to calculate the dam breach hydrograph using an Excel spreadsheet based on the improved soil erosion model and numerical algorithm. However, calculation of the breach lateral enlargement requires the modeling of the successive collapse of the breach banks. It is time-consuming with special training, which is difficult to provide during an emergency. This study proposes that the lateral enlargement process can be modeled using a hyperbolic relationship with sufficient accuracy. Consequently, field engineers can perform the dam breach analysis along with the sensitive study for a target case within 1 h in an Excel spreadsheet which is self-tutorial. This paper presents this easy and quick approach based on only fifteen input parameters that can be determined based on the experience. This approach can also be used for the preliminary study when a dam safety planning work is undertaken.

关键词： dam breach flood breach lateral enlargement hyperbolic relationship

在线全文

学校读者我要写书评

暂无评论

离心模拟水下爆炸试验技术

岩土工程学报 2024年第S1期46卷 32-36页

作者：胡晶陈祖煜雷雨萌王云超张紫涛张雪东中国水利水电科学研究院北京100048

随着国际形式日趋紧张,重要基础设施的抗爆安全愈发受到关注。对于水下爆炸研究,超重力场可以实现水下爆炸冲击波和气泡脉动的同时相似,离心模型试验是爆炸毁伤效应的重要研究手段。结合中国水科院十余年来离心模拟水下爆炸的实践经验,... 详细信息

随着国际形式日趋紧张,重要基础设施的抗爆安全愈发受到关注。对于水下爆炸研究,超重力场可以实现水下爆炸冲击波和气泡脉动的同时相似,离心模型试验是爆炸毁伤效应的重要研究手段。结合中国水科院十余年来离心模拟水下爆炸的实践经验,系统介绍了相关设备的系统组成,给出了设备满足的技术指标。通过2组离心模型试验,测试了离心机主轴、吊耳部位及模型箱的振动响应,结果表明:①离心机主轴所受的爆炸冲击响应较小,与正常运转条件下的振动速度基本一致,可以忽略爆炸冲击对离心机整体稳定的影响;②吊耳部位所受的冲击加速度及振动速度较大,可以通过在模型箱布置高弹橡胶减轻吊篮的冲击响应;③试验模型箱的变形基本处于弹性范围,模型箱长边可在跨中布置支撑减小跨中的变形,模型箱壁支座可采用螺栓增加支座的稳定。

关键词：水下爆炸离心机超重力抗冲击气泡脉动

Centrifuge experiment and numerical analysis of an air-backed plate subjected to underwater shock loading

在线全文

学校读者我要写书评

暂无评论

Frontiers of Structural and Civil Engineering 2019年第6期13卷 1350-1362页

作者： Zhijie HUANG Xiaodan REN zuyu chen Daosheng LING MOE Key L aboratory of Soft Soils and Geoenvironmental Engineering Zhejiang UniversityHangzhou 310058China Institute of Geotechnical Engineering Zhejiang UniversityHangzhou 310058China China Institute of Water Resources and Hydropower Research Beijing 100048China School of Civil Engineering Tongji UniversityShanghai 200092China

In this study,systematic centrifuge experiments and numerical studies are conducted to investigate the effect of shock loads due to an underwater explosion on the dynamic responses of an air-backed steel *** simulations with three different models of pressure time history generated by underwater explosion were carried *** first model of pressure time history was measured in *** second model to predict the time history of shock wave pressure from an underwater explosion was created by Cole in *** of Cole's formulas are determined *** third model was developed by Zamyshlyaev and Yakovlev in *** of them are implemented into the numerical model to calculate the shock responses of the *** peak strains obtained from the three models are compared with the experimental results,yielding average relative differences of 21.39%,45.73%,and 13.92%,*** Russell error technique is used to quantitatively analyze the correlation between the numerical and experimental *** analysis shows that the simulated strains for most measurement points on the steel plate are *** changing the scaled distances,different shock impulses were obtained and exerted on the steel *** numerical studies are performed to investigate the effect of the accumulated shock impulse on the peak *** numerical and experimental results suggest that the peak strains are strongly dependent on the accumulated shock impulse.

关键词： underwater explosion centrifuge experiment shock load dynamic response accumulated shock impulse

Cross-project prediction for rock mass using shuffled TBM big dataset and knowledge-based machine learning methods

维普期刊数据库评论

在线全文

维普期刊数据库

学校读者我要写书评

暂无评论

Science China(Technological Sciences) 2023年第3期66卷 751-770页

作者： ZHANG YunPei chen zuyu JIN Feng JING LiuJie XING Hai LI PengYu Department of Hydraulic Engineering Tsinghua UniversityBeijing 100084China Key Laboratory of Simulation and Regulation of Water Cycle in River Basin China Institute of Water Resources and Hydropower ResearchBeijing 100038China China Railway Engineering Equipment Group Co. Ltd.Zhengzhou 450016China Sinohydro Bureau 6 Co. Ltd.Shenyang 110179China

Extensive research has confirmed the successful prediction of rock mass quality in tunnel boring machine(TBM)construction using machine learning methods based on big data collected during the boring ***,the developed model cannot be applied to a new project owing to the different mechanical and environmental features involved in different *** study tries to combine the datasets of three TBM projects whose cutterhead diameters are 5.2,7.9 and 9.8 m,*** this study,machine learning focused on predictions of a binary rock mass quality system was implemented using this unified dataset by adding the diameter and disc cutter number as new attributes into the *** process consists of:(1)individual learning for the three respective datasets,(2)shuffled learning for the unified dataset containing randomly distributed information from the three projects,and(3)crossed learning aimed at validating that the algorithm developed on the unified dataset can produce predictions with equally acceptable accuracies as those obtained in the individual *** is anticipated that with more datasets joining this cross-project learning,we will be able to develop a machine learning algorithm that is suitable for new projects with a wide range of cutterhead diameters and disc cutter numbers at the beginning of the tunnel excavation.

关键词： TPI FPI rock mass quality machine learning cross project

Quantitative deterministic versus probability analyses based on a safety margin criterion

在线全文

学校读者我要写书评

暂无评论

Science China(Technological Sciences) 2014年第10期57卷 1988-2000页

作者： chen zuyu chen LiHong XU Jiacheng SUN Ping WU Chao WANG YuJie State Key Laboratory of Simulation and Regulation of Water Cycle in River Basin Department of Geotechnical Engineering China Institute of Water Resources and Hydropower Research School of Civil Engineering Beijing Jiaotong University China International Engineering Consulting Corporation

This paper proposes a new criterion called the ratio of safety margin(RSM)for use in the areas of the global factor of safety,reliability and limit states analyses with reference to their respective allowable *** equation for calculating RSM based on the reliability index is *** for proving the applicability of this criterion include a theoretical demonstration in a simple one-variable case;an investigation on a test problem involving two random variables,followed by a slope stability study on a 156 m high embankment dam and an illustrative example presented in a EuroCode 7 *** of the ratios of safety margin in the three areas provides a quantitative way to accommodate the analytical results within the same theoretical framework and makes the outcomes mutually comparable and supportive,which is much more enlightening than that would be the case by considering only one of *** RSMs for reliability and limit states methods has also helped solve the key issue concerning the uniqueness of the partial factors calibrated from a particular‘target case’.

关键词： factor of safety reliability index partial factor ratio of safety margin embankment dam reliability analysis

Advanced prediction of tunnel boring machine performance based on big data

在线全文

学校读者我要写书评

暂无评论

Geoscience Frontiers 2021年第1期12卷 331-338页

作者： Jinhui Li Pengxi Li Dong Guo Xu Li zuyu chen Department of Civil and Environmental Engineering Harbin Institute of Technology(Shenzhen)ShenzhenChina School of Civil Engineering Beijing Jiaotong UniversityBeijingChina China Institute of Water Resources and Hydropower Research BeijingChina

Predicting the performance of a tunneling boring machine is vitally important to avoid any possible accidents during tunneling *** prediction is not straightforward due to the uncertain geological conditions and the complex rock-machine *** on the big data obtained from the 72.1 km long tunnel in the Yin-Song Diversion Project in China,this study developed a machine learning model to predict the TBM performance in a real-time *** total thrust and the cutterhead torque during a stable period in a boring cycle was predicted in advance by using the machine-returned parameters in the rising period.A long short-term memory model was developed and its accuracy was *** results show that the variation in the total thrust and cutterhead torque with various geological conditions can be well reflected by the proposed *** real-time predication shows superior performance than the classical theoretical model in which only a single value can be obtained based on the single measurement of the rock *** improve the accuracy of the model a filtering process was *** indicate that filtering the unnecessary parameters can enhance both the accuracy and the computational ***,the data deficiency was discussed by assuming a parameter was *** is found that the missing of a key parameter can significantly reduce the accuracy of the model,while the supplement of a parameter that highly-correlated with the missing one can improve the prediction.

关键词： TBM Big data Machine learning LSTM neural network Data efficiency Data deficiency