Search | Engineering

订阅投稿

首页工程期刊工程焦点工程成就工程前沿关于我们 English

资源类型

期刊论文 702

会议视频 22

年份

2024 1

2023 76

2022 70

2021 72

2020 68

2019 48

2018 37

2017 41

2016 24

2015 30

2014 28

2013 22

2012 20

2011 19

2010 13

2009 16

2008 24

2007 25

2006 11

2005 16

展开︾

关键词

神经网络 23

人工神经网络 5

优化 5

人工智能 4

智能制造 4

能源 4

BP神经网络 3

仿真 3

信息技术 2

增材制造 2

微波遥感 2

控制 2

机器学习 2

模糊神经网络 2

深度神经网络 2

算法 2

系统 2

网络 2

网络安全 2

展开︾

检索范围：

排序：展示方式：

Novel interpretable mechanism of neural networks based on network decoupling method

《工程管理前沿（英文）》 2021年第8卷第4期页码 572-581 doi: 10.1007/s42524-021-0169-x

摘要： The lack of interpretability of the neural network algorithm has become the bottleneck of its wide application. We propose a general mathematical framework, which couples the complex structure of the system with the nonlinear activation function to explore the decoupled dimension reduction method of high-dimensional system and reveal the calculation mechanism of the neural network. We apply our framework to some network models and a real system of the whole neuron map of Caenorhabditis elegans. Result shows that a simple linear mapping relationship exists between network structure and network behavior in the neural network with high-dimensional and nonlinear characteristics. Our simulation and theoretical results fully demonstrate this interesting phenomenon. Our new interpretation mechanism provides not only the potential mathematical calculation principle of neural network but also an effective way to accurately match and predict human brain or animal activities, which can further expand and enrich the interpretable mechanism of artificial neural network in the future.

关键词： neural networks interpretability dynamical behavior network decouple

HTML PDF 收藏

网络系统行为效用计算——概念与原理 Article

胡昌振

《工程（英文）》 2018年第4卷第1期页码 78-84 doi: 10.1016/j.eng.2018.02.010

摘要：

网络的服务与应用是一个面向业务与任务的行为过程，其度量与评估目前尚处于粗略比较状态。本文把网络行为场景刻画为微分流形，根据光滑微分流形的同胚变换，给出了网络行为的数学定义，提出了网络行为路径及行为效用的数学描述。基于微分几何原理，提出了网络行为效用的计算原理与方法，并构建了基于行为效用的网络攻防对抗评估计算框架，从而奠定了网络行为定量度量和评估的数学基础。

关键词：网络度量评估微分流形网络行为效用网络攻防对抗

HTML PDF 收藏

An artificial neural network model on tensile behavior of hybrid steel-PVA fiber reinforced concrete

Fangyu LIU, Wenqi DING, Yafei QIAO, Linbing WANG

《结构与土木工程前沿（英文）》 2020年第14卷第6期页码 1299-1315 doi: 10.1007/s11709-020-0712-6

摘要： The tensile behavior of hybrid fiber reinforced concrete (HFRC) is important to the design of HFRC and HFRC structure. This study used an artificial neural network (ANN) model to describe the tensile behavior of HFRC. This ANN model can describe well the tensile stress-strain curve of HFRC with the consideration of 23 features of HFRC. In the model, three methods to process output features (no-processed, mid-processed, and processed) are discussed and the mid-processed method is recommended to achieve a better reproduction of the experimental data. This means the strain should be normalized while the stress doesn’t need normalization. To prepare the database of the model, both many direct tensile test results and the relevant literature data are collected. Moreover, a traditional equation-based model is also established and compared with the ANN model. The results show that the ANN model has a better prediction than the equation-based model in terms of the tensile stress-strain curve, tensile strength, and strain corresponding to tensile strength of HFRC. Finally, the sensitivity analysis of the ANN model is also performed to analyze the contribution of each input feature to the tensile strength and strain corresponding to tensile strength. The mechanical properties of plain concrete make the main contribution to the tensile strength and strain corresponding to tensile strength, while steel fibers tend to make more contributions to these two items than PVA fibers.

关键词： artificial neural network hybrid fiber reinforced concrete tensile behavior sensitivity analysis stress-strain curve

HTML PDF 收藏

Effects of herding behavior of tradable green certificate market players on market efficiency: Insights

《能源前沿（英文）》 2023年第17卷第2期页码 266-285 doi: 10.1007/s11708-021-0752-1

摘要： Tradable green certificate (TGC) scheme promotes the development of renewable energy industry which currently has a dual effect on economy and environment. TGC market efficiency is reflected in stimulating renewable energy investment, but may be reduced by the herding behavior of market players. This paper proposes and simulates an artificial TGC market model which contains heterogeneous agents, communication structure, and regulatory rules to explore the characteristics of herding behavior and its effects on market efficiency. The results show that the evolution of herding behavior reduces information asymmetry and improves market efficiency, especially when the borrowing is allowed. In addition, the fundamental strategy is diffused by herding evolution, but TGC market efficiency may be remarkably reduced by herding with borrowing mechanism. Moreover, the herding behavior may evolve to an equilibrium where the revenue of market players is comparable, thus the fairness in TGC market is improved.

关键词： tradable green certificate herding behavior evolution heterogeneous agent model complex network

HTML PDF 收藏

Interaction behavior and load sharing pattern of piled raft using nonlinear regression and LM algorithm-basedartificial neural network

《结构与土木工程前沿（英文）》 2021年第15卷第5期页码 1181-1198 doi: 10.1007/s11709-021-0744-6

摘要： In the recent era, piled raft foundation (PRF) has been considered an emergent technology for offshore and onshore structures. In previous studies, there is a lack of illustration regarding the load sharing and interaction behavior which are considered the main intents in the present study. Finite element (FE) models are prepared with various design variables in a double-layer soil system, and the load sharing and interaction factors of piled rafts are estimated. The obtained results are then checked statistically with nonlinear multiple regression (NMR) and artificial neural network (ANN) modeling, and some prediction models are proposed. ANN models are prepared with Levenberg–Marquardt (LM) algorithm for load sharing and interaction factors through backpropagation technique. The factor of safety (FS) of PRF is also estimated using the proposed NMR and ANN models, which can be used for developing the design strategy of PRF.

关键词： interaction load sharing ratio piled raft nonlinear regression artificial neural network

HTML PDF 收藏

面向潜在行为预测的异构行为网络嵌入学习 Article

Yue-yang WANG, Wei-hao JIANG, Shi-liang PU, Yue-ting ZHUANG

《信息与电子工程前沿（英文）》 2020年第21卷第3期页码 422-435 doi: 10.1631/FITEE.1800493

摘要：潜在行为预测即理解特定群体潜在的人类行为，可辅助组织做出战略决策。信息技术的进步使获取人类行为的庞大数据成为可能。本文将真实场景中获取的人类行为数据构建成信息网络；该信息网络由2种对象（人和动作）和3种关系（人—人、人—动作和动作—动作）组成，称作异构行为网络（HBN）。为充分利用异构行为网络的丰富性和异构性，提出一种网络嵌入方法，称作人—行为—属性感知的异构网络嵌入（a4HNE）；该方法综合考虑网络结构邻近性、节点属性相似性和异构性融合。在两个真实数据集上的实验结果表明，该方法在各种异构信息网络挖掘任务中的潜在行为预测性能优于其他同类方法。

关键词：网络嵌入；表示学习；人类行为；社交网络；异构信息网络；属性

HTML PDF 收藏

Design, analysis, and neural control of a bionic parallel mechanism

《机械工程前沿（英文）》 2021年第16卷第3期页码 468-486 doi: 10.1007/s11465-021-0640-8

摘要： Although the torso plays an important role in the movement coordination and versatile locomotion of mammals, the structural design and neuromechanical control of a bionic torso have not been fully addressed. In this paper, a parallel mechanism is designed as a bionic torso to improve the agility, coordination, and diversity of robot locomotion. The mechanism consists of 6-degree of freedom actuated parallel joints and can perfectly simulate the bending and stretching of an animal’s torso during walking and running. The overall spatial motion performance of the parallel mechanism is improved by optimizing the structural parameters. Based on this structure, the rhythmic motion of the parallel mechanism is obtained by supporting state analysis. The neural control of the parallel mechanism is realized by constructing a neuromechanical network, which merges the rhythmic signals of the legs and generates the locomotion of the bionic parallel mechanism for different motion patterns. Experimental results show that the complete integrated system can be controlled in real time to achieve proper limb–torso coordination. This coordination enables several different motions with effectiveness and good performance.

关键词： neural control behavior network rhythm motion pattern

HTML PDF 收藏

A hierarchical system to predict behavior of soil and cantilever sheet wall by data-driven models

Nang Duc BUI; Hieu Chi PHAN; Tiep Duc PHAM; Ashutosh Sutra DHAR

《结构与土木工程前沿（英文）》 2022年第16卷第6期页码 667-684 doi: 10.1007/s11709-022-0822-4

摘要： The study proposes a framework combining machine learning (ML) models into a logical hierarchical system which evaluates the stability of the sheet wall before other predictions. The study uses the hardening soil (HS) model to develop a 200-sample finite element analysis (FEA) database, to develop the ML models. Consequently, a system containing three trained ML models is proposed to first predict the stability status (random forest classification, RFC) followed by 1) the cantilever top horizontal displacement of sheet wall (artificial neural network regression models, RANN1) and 2) vertical settlement of soil (RANN2). The uncertainty of this data-driven system is partially investigated by developing 1000 RFC models, based on the application of random sampling technique in the data splitting process. Investigation on the distribution of the evaluation metrics reveals negative skewed data toward the 1.0000 value. This implies a high performance of RFC on the database with medians of accuracy, precision, and recall, on test set are 1.0000, 1.0000, and 0.92857, respectively. The regression ANN models have coefficient of determinations on test set, as high as 0.9521 for RANN1, and 0.9988 for RANN2, respectively. The parametric study for these regressions is also provided to evaluate the relative insight influence of inputs to output.

关键词： finite element analysis cantilever sheet wall machine learning artificial neural network random forest

HTML PDF 收藏

微小型机器鼠仿鼠行为学习与生成

高子航, 贾广禄, 谢宏钊, 黄强, 福田敏男, 石青

《工程（英文）》 2022年第17卷第10期页码 232-243 doi: 10.1016/j.eng.2022.05.012

摘要：

现有的仿生机器鼠仅可以执行一些基本的仿鼠运动基元（MP），并通过这些基元的刚性组合来形成简单的行为。为了模拟具有高相似性的典型实验鼠行为，本文提出使用概率模型和运动特征对实验鼠的行为进行参数化。首先，对15 个10 min 的实验鼠运动视频片段的分析表明，一只实验鼠在野外通常有6 种典型的行为，且每种行为都包含8 个运动基元的不同组合。本文首先使用softmax 分类器来获得实验鼠的行为-运动分层概率模型。其次，使用静态和动态的运动参数对运动基元组合进行特征化。本文分别使用分层聚类和模糊C均值（FCM）聚类获得静态和动态运动参数的优势值。这些优势值通过二阶傅里叶级数对实验鼠的脊柱关节轨迹进行拟合，并且通过具有两个隐藏层的反向传播（BP）神经网络对关节轨迹进行泛化。最后，将分层概率模型和泛化的关节轨迹分别作为控制策略和指令映射到机器鼠。本文在机器鼠上实现了6 种典型的仿鼠行为，其结果与实验鼠的行为相比显示出高度相似性。

关键词：仿生学微小型机器鼠神经网络学习行为生成

HTML PDF 收藏

基于特征-模式图的SDN下分布式拒绝服务攻击发现方法 Special Feature on Future Network-Research Article

Ya XIAO, Zhi-jie FAN, Amiya NAYAK, Cheng-xiang TAN

《信息与电子工程前沿（英文）》 2019年第20卷第9期页码 1195-1208 doi: 10.1631/FITEE.1800436

摘要：由于软件定义网络（software-defined networks, SDN）的开方式结构，软件定义网络环境下的安全威胁已成为一个重要问题。在所有威胁中，分布式拒绝服务攻击（distributed denial-of-service, DDoS）对网络具有巨大影响。本文提出一种基于特征-模式图模型的方法来发现软件定义网络环境下的DDoS攻击行为。所提出的特征-模式图采用网络模式作为节点，将其相似度作为加权边。该图模型可同时表示网络包的头信息和各网络模式之间的关系信息。节点之间的相似度由度量学习和马氏距离表示。所提方法可以基于图的邻近分类模型发现DDoS攻击，并具有自动发现未知攻击的能力且可通过全局或局部插入新节点的方式扩展已有图结构。两个数据集上的实验证明了所提方法在攻击行为检测和图更新任务上的可行性，并证明了本文基于图的模型在DDoS攻击检测上优于对比模型。

关键词：软件定义网络；分布式拒绝服务攻击；行为检测；距离度量学习；特征-模式图

HTML PDF 收藏

Study on Big Data-based Behavior Modification in Metro Construction

Lie-yun Ding,Sheng-yu Guo

《工程管理前沿（英文）》 2015年第2卷第2期页码 131-136 doi: 10.15302/J-FEM-2015037

摘要： With the rapid development of metro construction in China, construction accidents frequently happen, which are significantly attributable to workers’ unsafe behavior. Behavior-based safety (BBS) is an effective method to modify workers’ unsafe behavior. This paper introduces the study on big data-based metro construction behavior modification, aiming to solve the problem of current research without consideration of workers’ personal characters. First, the behavior modification pushing mechanism based on content-based personalized recommendation is studied. Secondly, the development of behavior modification system of metro construction (BMSMC) is introduced. Thirdly, BMSMC practical applications using the unsafe behavior rate, as a measuring indicator is implemented. Observations at one metro construction site in Wuhan indicate that the unsafe behavior rate of modified scaffolders at this work place decreased by 69.3%. At the same time, as of unmodified scaffolders at another work place for comparison, the unsafe behavior rate decreased by 56.9%, which validates the effectiveness of this system.

关键词： big data unsafe behavior behavior modification behavior-based safety (BBS) unsafe behavior rate

HTML PDF 收藏

The Group Interaction Field for Learning and Explaining Pedestrian Anticipation

Xueyang Wang,Xuecheng Chen,Puhua Jiang,Haozhe Lin,Xiaoyun Yuan,Mengqi Ji,Yuchen Guo,Ruqi Huang,Lu Fang,

《工程（英文）》 doi: 10.1016/j.eng.2023.05.020

摘要： Anticipating others’ actions is innate and essential in order for humans to navigate and interact well with others in dense crowds. This ability is urgently required for unmanned systems such as service robots and self-driving cars. However, existing solutions struggle to predict pedestrian anticipation accurately, because the influence of group-related social behaviors has not been well considered. While group relationships and group interactions are ubiquitous and significantly influence pedestrian anticipation, their influence is diverse and subtle, making it difficult to explicitly quantify. Here, we propose the group interaction field (GIF), a novel group-aware representation that quantifies pedestrian anticipation into a probability field of pedestrians’ future locations and attention orientations. An end-to-end neural network, GIFNet, is tailored to estimate the GIF from explicit multidimensional observations. GIFNet quantifies the influence of group behaviors by formulating a group interaction graph with propagation and graph attention that is adaptive to the group size and dynamic interaction states. The experimental results show that the GIF effectively represents the change in pedestrians’ anticipation under the prominent impact of group behaviors and accurately predicts pedestrians’ future states. Moreover, the GIF contributes to explaining various predictions of pedestrians’ behavior in different social states. The proposed GIF will eventually be able to allow unmanned systems to work in a human-like manner and comply with social norms, thereby promoting harmonious human–machine relationships.

关键词： Human behavior modeling and prediction Implicit representation of pedestrian anticipation Group interaction Graph neural network

HTML PDF 收藏

Flow behavior of non-spherical particle flowing in hopper

He TAO,Wenqi ZHONG,Baosheng JIN

《能源前沿（英文）》 2014年第8卷第3期页码 315-321 doi: 10.1007/s11708-014-0331-9

摘要： Ellipsoidal particles flowing in the hopper were simulated by using the discrete element method (DEM), and described by the multi-element method. The contact detection algorithm and equations for ellipsoidal particle motion in hopper were developed. And the simulation results were confirmed by experiment. Additionally, the mass flow rate, pressure distribution and velocity distribution of two kinds of particles were examined. The results show that the mass flow rate of ellipsoidal particles is smaller than that of spherical particles. There is a maximum value of pressure drop at the top of the junction. Besides, the pressure drop decreases with the discharging time increasing. The velocity of spherical particle is larger than that of ellipsoidal.

关键词： discrete element method ellipsoidal particle flow behavior hopper

HTML PDF 收藏

A simplified method for investigating the bending behavior of piles supporting embankments on soft ground

《结构与土木工程前沿（英文）》页码 1021-1032 doi: 10.1007/s11709-023-0952-3

摘要： In recent years, concrete and reinforced concrete piles have been widely used to stabilize soft ground under embankments. Previous research has shown that bending failure, particularly during rapid filling on soft ground, is the critical failure mode for pile-supported embankments. Here, we propose an efficient two-stage method that combines a test-verified soil deformation mechanism and Poulos’ solution for pile–soil interaction to investigate the bending behavior of piles supporting embankments on soft ground. The results reveal that there are three possible bending failure scenarios for such piles: at the interface between the soft and firm ground layers, at mid-depths of the fan zone, and at the boundary of the soil deformation mechanism. The location of the bending failure depends on the position and relative stiffness of the given pile. Furthermore, the effect of embedding a pile into a firm ground layer on the bending behavior was investigated. When the embedded length of a pile exceeded a critical value, the bending moment at the interface between the soft and firm ground layers reached a limiting value. In addition, floating piles that are not embedded exhibit an overturning pattern of movement in the soft ground layer, and a potential failure is located in the upper part of these piles.

关键词： bending behavior pile embankment soil−structure interaction failure mode

HTML PDF 收藏

Weakening behavior of waterproof performance in joints of shield tunnels under adjacent constructions

《结构与土木工程前沿（英文）》页码 884-900 doi: 10.1007/s11709-022-0912-3

摘要： Groundwater leakage in shield tunnels poses a threat to the safety and durability of tunnel structures. Disturbance of adjacent constructions during the operation of shield tunnels frequently occurs in China, leading to deformation of tunnel lining and leakage in joints. Understanding the impact of adjacent constructions on the waterproofing performance of the lining is critical for the protection of shield tunnels. In this study, the weakening behavior of waterproof performance was investigated in the joints of shield tunnels under transverse deformation induced by adjacent construction. First, the relationship between the joint opening and transverse deformation under three typical adjacent constructions (upper loading, upper excavation, and side excavation) was investigated via elaborate numerical simulations. Subsequently, the evolution of the waterproof performance of a common gasket with a joint opening was examined by establishing a coupled Eulerian–Lagrangian model of joint seepage, and a formula describing the relationship between waterproof performance and joint opening was proposed. Finally, the weakening law of waterproofing performance was investigated based on the results of the aforementioned studies. It was determined that the joints with the greatest decline in waterproof performance were located at the tunnel shoulder in the upper loading case, tunnel crown in the upper excavation case, and tunnel shoulder in the side excavation case. When the waterproof performance of these joints decreased to 50% and 30%, the transverse deformations were 60 and 90 mm under upper loading, 90 and 140 mm under upper excavation, and 45 and 70 mm under side excavation, respectively. The results provide a straightforward reference for setting a controlled deformation standard considering the waterproof performance.

关键词： shield tunnel waterproof performance horizontal transverse deformation joint opening weakening behavior