检索结果-南通市图书馆

Underground Space 2024年第6期19卷 279-300页

作者： weiping luo Dajun Yuan Yannick Choy Hing Ng Dalong Jin Ping Lu Teng Wang Department of Geotechnical Engineering College of Civil EngineeringTongji UniversityShanghai 200092China Key Laboratory of the Ministry of Education for Urban Underground Engineering Beijing Jiaotong UniversityBeijing 100044China Department of Civil and Environmental Engineering National University of SingaporeSingapore 119077Singapore

Many empirical and analytical methods have been proposed to predict fracturing pressure in cohesive *** of them take into account three to four specific influencing factors and rely on the assumption of a failure *** this study,a novel data-mining approach based on the XGBoost algorithm is investigated for predicting fracture initiation in cohesive *** has the advantage of handling multiple influencing factors simultaneously,without pre-determining a failure mode.A dataset of 416 samples consisting of 14 distinct features was herein collected from past studies,and used for developing a regressor and a classifier model for fracturing pressure prediction and failure mode classification *** results show that the intrinsic characteristics of the soil govern the failure mode while the fracturing pressure is more sensitive to the stress *** XGBoost-based model was also tested against conventional approaches,as well as a similar machine learning algorithm namely random forest ***,several large-scale triaxial fracturing tests and an in-situ case study were carried out to further verify the generalization ability and applicability of the proposed data mining approach,and the results indicate a superior performance of the XGBoost model.

关键词： Fracturing pressure Failure mode Cohesive soil Data-mining Large-scale tests

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

基于机器学习的奶牛饲料消耗状态预测模型

农业工程学报 2024年第9期40卷 164-172页

作者：张博罗维平武汉纺织大学机械工程与自动化学院武汉430200 湖北省数字化纺织装备重点实验室武汉430200

饲料作为奶牛重要的营养来源,预测饲料消耗状态对于保障奶牛的健康和提高生产管理效率具有重要意义。然而,由于饲料消耗状态数据呈现出非线性和非平稳的特点,导致预测精度较低。为解决此问题,该研究基于经验模态分解(empirical mode dec... 详细信息

饲料作为奶牛重要的营养来源,预测饲料消耗状态对于保障奶牛的健康和提高生产管理效率具有重要意义。然而,由于饲料消耗状态数据呈现出非线性和非平稳的特点,导致预测精度较低。为解决此问题,该研究基于经验模态分解(empirical mode decomposition,EMD)和长短期记忆网络(long short-term memory,LSTM),提出了组合改进的自适应噪声完全集成经验模态分解(improved complete ensemble empirical mode decomposition with adaptive noise,ICEEMDAN)、随机森林(random forest,RF)与改进的LSTM(improved LSTM,ILSTM)的模型,即ICEEMDANRF-ILSTM,来预测饲料消耗状态。其通过调整遗忘门的输出值范围以增强模型的特征学习能力。首先,使用ICEEMDAN对饲料消耗状态数据进行分解,得到多个相对平稳的分量。其次,考虑到每个分量具有不同的特性,采用不同的方法来建模不同的分量,以进一步提升预测效果。具体而言,为了提升模型的精度以及泛化能力,使用RF建模频率最高的分量;同时,使用ILSTM建模其余分量,以捕获序列数据中的长期依赖性。最后,将所有分量的预测结果相加得到最终的预测结果。基于自建数据集的试验结果表明,ICEEMDAN-RF-ILSTM对于饲料消耗状态预测具有较高的准确度,其决定系数R2、平均绝对百分比误差与均方根误差分别为0.993、2.576%和0.596%,表明其能有效预测饲料消耗状态,同时其性能优于ICEEMDAN-LSTM模型。该研究为评估饲料消耗状态提供了可行的方法,可为制定调度决策提供了科学的技术支持,并为牧业智能化建设提供借鉴。

关键词：机器学习饲料状态预测 ICEEMDAN 长短期记忆网络奶牛

基于Swin-Unet的奶牛饲料消耗状态监测方法

在线全文

学校读者我要写书评

暂无评论

华南农业大学学报 2024年第5期45卷 754-763页

作者：张博罗维平武汉纺织大学机械工程与自动化学院湖北武汉430200

【目的】针对监控图像中饲料区域结构较长、边界模糊,且形状与尺寸复杂多变等特点,本研究旨在更准确地分割饲料残余区域与消耗区域,以达到准确监测饲料消耗状态的目的。【方法】本研究提出了基于Swin-Unet的语义分割模型,其在Swin Trans... 详细信息

【目的】针对监控图像中饲料区域结构较长、边界模糊,且形状与尺寸复杂多变等特点,本研究旨在更准确地分割饲料残余区域与消耗区域,以达到准确监测饲料消耗状态的目的。【方法】本研究提出了基于Swin-Unet的语义分割模型,其在Swin Transformer块的开始阶段应用ConvNeXt块,增强模型对特征信息的编码能力,以提供更好的特征表示,并利用深度卷积替换线性注意力映射,以提供局部空间上下文信息。同时提出了新颖的宽范围感受野模块来代替多层感知机,以丰富多尺度空间上下文信息。此外在编码器的开始阶段,将线性嵌入层替换为卷积嵌入层,通过分阶段压缩特征,在块之间和内部引入更多的空间上下文信息。最后引入多尺度输入策略、深度监督策略,并提出了特征融合模块,以加强特征融合。【结果】所提出方法的平均交并比、准确率、F1分数与运行速度分别为86.46%、98.60%、92.29%和23帧/s,相较于Swin-Unet,分别提高4.36、2.90、0.65个百分点和15%。【结论】基于图像语义分割的方法应用于饲料消耗状态的自动监测是可行的,该方法通过将卷积引入Swin-Unet,有效地提高了分割精度与计算效率,对提升生产管理效率具有重要意义。

关键词：饲料消耗自动监测语义分割 Swin Transformer 奶牛深度卷积

盾构开挖面泥水劈裂离心模型试验相似性分析及验证

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

岩土工程学报 2024年第9期46卷 1919-1927页

作者：罗维平李福豪袁大军朱合华北京交通大学城市地下工程教育部重点试验室北京100044 同济大学地下建筑与工程系上海200092 新加坡国立大学土木与环境工程学院新加坡117576

土工离心试验能够在小比尺模型中还原真实的应力场,为探明盾构开挖面泥水劈裂现象提供了一种有效的研究手段。盾构泥水劈裂涉及土体、泥水、隧道等多方面因素的相互作用,尤其多种流体的存在使得模型试验中量纲分析、试验参数缩放和数据... 详细信息

土工离心试验能够在小比尺模型中还原真实的应力场,为探明盾构开挖面泥水劈裂现象提供了一种有效的研究手段。盾构泥水劈裂涉及土体、泥水、隧道等多方面因素的相互作用,尤其多种流体的存在使得模型试验中量纲分析、试验参数缩放和数据解释更加复杂化,如何确定合理的相似比例是泥水劈裂离心模型试验成功的关键前提。在阐明盾构泥水劈裂基本物理过程的基础上,提出了基于无量纲数的模型试验相似性分析方法,通过Butterfield量纲分析法建立了应用于土工离心机模拟盾构泥水劈裂的“隧道-土-泥水”系统相似性试验设计体系。该体系从尺寸、材料、无量纲数、时间等多方面保障了模型系统与原型系统的相似性,从而可以准确还原真实的盾构泥水劈裂物理过程。最后,通过开展盾构开挖面泥水劈裂离心模型试验,进一步验证本文提出的相似性准则。研究结果对泥水劈裂物理模拟的相似性分析具有一定的参考意义。

关键词：相似性分析泥水劈裂离心模型试验无量纲数盾构开挖面

在线全文

学校读者我要写书评

暂无评论

多通道多尺度的注意力机制单幅图像去雨方法

复旦学报（自然科学版） 2024年第4期63卷 457-467页

作者：吴子凡罗维平樊飞武汉纺织大学机械工程与自动化学院湖北武汉430200 湖北省数字化纺织装备重点实验室湖北武汉430200

为了去除受雨天天气影响而出现在图像中的雨纹和雨线,本文提出了一种基于多通道多尺度的注意力机制单幅图像去除雨纹和雨线的方法,通过多尺度特征提取与网络融合,提取多尺度卷积神经网络不同通道的雨纹和雨线特征。首先利用双边滤波进... 详细信息

为了去除受雨天天气影响而出现在图像中的雨纹和雨线,本文提出了一种基于多通道多尺度的注意力机制单幅图像去除雨纹和雨线的方法,通过多尺度特征提取与网络融合,提取多尺度卷积神经网络不同通道的雨纹和雨线特征。首先利用双边滤波进行图像分解;然后对低频部分进行多尺度的特征提取与融合,并且使用区域注意力进一步提取图像的特征信息,同时对高频部分利用多尺度特征提取的卷积神经网络进行特征学习;最后将2部分相加,得到了去除雨纹和雨线更彻底的清晰图像,在合成数据集和真实数据集上分别与其他去雨方法进行对比分析。分析结果表明:本文去除雨纹和雨线后得到的图像更加清晰,并且图像的部分区域细节丢失更少,本文方法提升了去雨后的图像质量,从而改善了该方法在图像处理、计算机视觉和机器学习等领域的应用效果和性能。

关键词：图像去雨雨纹和雨线多尺度特征提取空洞卷积区域注意力

一种高层外置废弃物升降打包处理一体装置的设计

在线全文

学校读者我要写书评

暂无评论

福建农机 2024年第1期 39-42,54页

作者：张弟罗卫平金陵科技学院江苏南京211169

当前,服装加工企业、产品包装企业、高层建筑工地等生产所产生的布料边角料、泡沫塑料、轻质建筑垃圾等废弃物处理时占用空间,楼层间运送费时费力。设计提供一种高层外置废弃物升降打包处理一体装置,通过在工厂废弃物丢弃侧架设一个废... 详细信息

当前,服装加工企业、产品包装企业、高层建筑工地等生产所产生的布料边角料、泡沫塑料、轻质建筑垃圾等废弃物处理时占用空间,楼层间运送费时费力。设计提供一种高层外置废弃物升降打包处理一体装置,通过在工厂废弃物丢弃侧架设一个废弃物运送框架,框架内运动的废料斗将工厂各层产生的垃圾运送到地面的压缩舱内进行压缩,压缩后的废弃物由自动打包机打包成规则大小的包,便于废料的处理和运输。装置的革新,提高了工作效率,节省了人力和工作成本。

关键词：废弃物处理高层外置打包装置结构设计

Hydraulic fracturing pressure of concentric double-layered cylinder in cohesive soil

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

Frontiers of Structural and Civil Engineering 2021年第4期15卷 937-947页

作者： Dajun YUAN weiping luo Dalong JIN Ping LU Key Laboratory of Urban Underground Engineering of the Education Ministry Beijing Jiaotong UniversityBeijing100044China School of Civil Engineering Beijing Jiaotong UniversityBeijing100044China

This study aims to investigate hydrofracturing in double-layered soil through theoretical and experimental analysis,as multilayered soils where the difference in mechanical properties exists are generally encountered in practical ***,an analytical solution for fracturing pressure in two different concentric regions of soil was presented based on the cavity expansion ***,several triaxial hydraulic fracturing tests were carried out to validate the analytical *** comparison between the experimental and analytical results indicates the remarkable accuracy of the derived formula,and the following conclusions were also ***,there is a linear relationship between the fracturing pressure and confining pressure in concentric double-layered cohesive ***,when the internal-layer soil is softer than the external-layer soil,the presence of internal soil on the fracturing pressure approximately brings the weakening effect,and the greater strength distinction between the two layers,the greater the weakening ***,when the internal-layer soil is harder than the external-layer soil,the existence of the internal-layer soil has a strengthening effect on the fracturing pressure regardless of the proportion of internal-layer ***,the influence of strength distinction between the two layers on the fracturing pressure is significant when the proportion of internal-layer soil is less than half,while it’s limited when the proportion is more than *** proposed solution is potentially useful for geotechnical problems involving aspects of cohesive soil layering in a composite formation.

关键词： hydraulic fracturing pressure layered cavity expansion theory triaxial fracturing test cohesive soil

Robust constrained iterative learning predictive fault-tolerant control of uncertain batch processes

在线全文

学校读者我要写书评

暂无评论

Science China(Information Sciences) 2019年第11期62卷 209-211页

作者： Limin WANG Limei SUN weiping luo School of Mathematics and Statistics Hainan Normal University School of Information and Control Engineering Liaoning Shihua University

Dear editor,Fault-tolerant control is to let a system operate in a steady manner despite the fact that faults exist therein. There have been several results on 1D systems that consider only the time index [1–4].Moreover, research on 2D systems has emerged,especially for batch processes that can be viewed as 2D systems [5–7]. However, current robust design cannot deal with the state deviation, which

关键词： Robust constrained iterative learning predictive fault-tolerant control of uncertain batch processes

Optimal Control of Slurry Pressure during Shield Tunnelling Based on Random Forest and Particle Swarm Optimization

在线全文

同方期刊数据库

学校读者我要写书评

暂无评论

Computer Modeling in Engineering & Sciences 2021年第7期128卷 109-127页

作者： weiping luo Dajun Yuan Dalong Jin Ping Lu Jian Chen Key Laboratory of Urban Underground Engineering of the Education Ministry Beijing Jiaotong UniversityBeijing100044China School of Civil Engineering Beijing Jiaotong UniversityBeijing100044China China Railway 14 Bureau Group Co. Ltd.Jinan250101China

The control of slurry pressure aiming to be consistent with the external water and earth pressure during shield tunnelling has great significance for face stability,especially in urban areas or underwater where the surrounding environment is very sensitive to the fluctuation of slurry *** this study,an optimal control method for slurry pressure during shield tunnelling is developed,which is composed of an identifier and a *** established identifier based on the random forest(RF)can describe the complex non-linear relationship between slurry pressure and its influencing *** proposed controller based on particle swarm optimization(PSO)can optimize the key factor to precisely control the slurry pressure at the normal state of advancement.A data set from Tsinghua Yuan Tunnel in China was used to train the RF model and several performance measures like R2,RMSE,etc.,were employed to ***,the hybrid RF-PSO control method is adopted to optimize the control of slurry *** good agreement between optimized slurry pressure and expected values demonstrates a high identifying and control precision.

关键词： Shield tunnelling slurry pressure optimal control random forest particle swarm optimization

Efficient and Bio-inspired Conversion of Cellulose to Formic Acid Catalyzed by Metalloporphyrins in Alkaline Solution

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

Chinese Journal of Chemistry 2017年第7期35卷 1063-1068页

作者： Qiang Liu Doudou Zhou Zongxiang Li weiping luo Cancheng Guo College of Chemistry and Chemical Engineering Hunan University Changsha Hunan 410082 China

A bio-inspired approach for efficient conversion of cellulose to formic acid （FA） was developed in an aqueous alkaline medium. Metalloporphyrins mimicking cytochrome P450 exhibit efficiently and selectively catalytic per- formance in catalytic conversion of cellulose. High yield of FA about 63.7% was obtained by using sulfonated iron（IlI） porphyrin as the catalyst and O2 as the oxidant. Iron（III）-peroxo species, TSPPFemOO , was involved to cleave the C--C bonds of gluconic acid to FA in this catalytic system. This approach used relatively high concen- tration of cellulose and ppm concentration of catalyst. This work may provide a bio-inspired route to efficient con- version of cellulose to FA.

关键词： metalloporphyrin bio-inspired catalyzed cellulose formic acid