资源类型

期刊论文 71

会议视频 2

年份

2023 12

2022 12

2021 13

2020 6

2019 4

2018 2

2017 2

2016 1

2015 1

2014 1

2013 3

2012 1

2011 3

2010 1

2009 2

2008 2

2007 2

2005 1

展开 ︾

关键词

强化学习 3

深度强化学习 2

H∞控制；零和动态博弈；强化学习；自适应动态规划；极小极大Q-学习；策略迭代 1

三峡电站 1

交互式分割 1

交通信号控制；交通预测；交通世界模型；强化学习 1

人—多机器人协同系统；基于零空间行为控制；任务管理器；强化学习；知识库 1

人在回路AI 1

人工智能 1

人类指导 1

体外预应力 1

全方位 1

决策优化 1

冻结加固 1

凸块锚固区 1

化学吸收 1

化学逆合成预测 1

区块链 1

医疗图像分割 1

展开 ︾

检索范围：

排序： 展示方式：

A new automatic convolutional neural network based on deep reinforcement learning for fault diagnosis

《机械工程前沿（英文）》 2022年 第17卷 第2期 doi: 10.1007/s11465-022-0673-7

摘要： Convolutional neural network (CNN) has achieved remarkable applications in fault diagnosis. However, the tuning aiming at obtaining the well-trained CNN model is mainly manual search. Tuning requires considerable experiences on the knowledge on CNN training and fault diagnosis, and is always time consuming and labor intensive, making the automatic hyper parameter optimization (HPO) of CNN models essential. To solve this problem, this paper proposes a novel automatic CNN (ACNN) for fault diagnosis, which can automatically tune its three key hyper parameters, namely, learning rate, batch size, and L2-regulation. First, a new deep reinforcement learning (DRL) is developed, and it constructs an agent aiming at controlling these three hyper parameters along with the training of CNN models online. Second, a new structure of DRL is designed by combining deep deterministic policy gradient and long short-term memory, which takes the training loss of CNN models as its input and can output the adjustment on these three hyper parameters. Third, a new training method for ACNN is designed to enhance its stability. Two famous bearing datasets are selected to evaluate the performance of ACNN. It is compared with four commonly used HPO methods, namely, random search, Bayesian optimization, tree Parzen estimator, and sequential model-based algorithm configuration. ACNN is also compared with other published machine learning (ML) and deep learning (DL) methods. The results show that ACNN outperforms these HPO and ML/DL methods, validating its potential in fault diagnosis.

关键词： deep reinforcement learning     hyper parameter optimization     convolutional neural network     fault diagnosis    

HTML PDF 收藏

Punching of reinforced concrete slab without shear reinforcement: Standard models and new proposal

Luisa PANI, Flavio STOCHINO

《结构与土木工程前沿（英文）》 2020年 第14卷 第5期   页码 1196-1214 doi: 10.1007/s11709-020-0662-z

摘要： Reinforced concrete (RC) slabs are characterized by reduced construction time, versatility, and easier space partitioning. Their structural behavior is not straightforward and, specifically, punching shear strength is a current research topic. In this study an experimental database of 113 RC slabs without shear reinforcement under punching loads was compiled using data available in the literature. A sensitivity analysis of the parameters involved in the punching shear strength assessment was conducted, which highlighted the importance of the flexural reinforcement that are not typically considered for punching shear strength. After a discussion of the current international standards, a new proposed model for punching shear strength and rotation of RC slabs without shear reinforcement was discussed. It was based on a simplified load-rotation curve and new failure criteria that takes into account the flexural reinforcement effects. This experimental database was used to validate the approaches of the current international standards as well as the new proposed model. The latter proved to be a potentially useful design tool.

关键词： punching shear strength     reinforced concrete     slabs     reinforcement ratio    

HTML PDF 收藏

Spatial embedded reinforcement of 20-node block element for analysis PC bridges

LONG Peiheng, DU Xianting, CHEN Weizhen

《结构与土木工程前沿（英文）》 2008年 第2卷 第3期   页码 274-280 doi: 10.1007/s11709-008-0039-1

摘要： The formula for the contribution of prestressed reinforcement on embedded reinforcement element is derived according to the mechanical behavior of PC bridges and the foundational principle of finite element method. Mechanical concept is definite and examples validate the calculation results. Reinforcement element model allows generating a finite element mesh without taking into consideration the layout of reinforcements. Furthermore, the prestressing tendon may pass through the concrete elements in an arbitrary manner. It is an effective approach that the no-node loads are diverted from the tendons to the adjacent concrete elements. A useful arithmetic analysis of the spatial curved tendon PC Bridges is provided.

关键词： arithmetic analysis     calculation     prestressed reinforcement     mechanical     arbitrary    

HTML PDF 收藏

Anthropomorphic Obstacle Avoidance Trajectory Planning for Adaptive Driving Scenarios Based on Inverse Reinforcement

Jian Wu,Yang Yan,Yulong Liu,Yahui Liu,

《工程（英文）》 doi: 10.1016/j.eng.2023.07.018

摘要： The forward design of trajectory planning strategies requires preset trajectory optimization functions, resulting in poor adaptability of the strategy and an inability to accurately generate obstacle avoidance trajectories that conform to real driver behavior habits. In addition, owing to the strong time-varying dynamic characteristics of obstacle avoidance scenarios, it is necessary to design numerous trajectory optimization functions and adjust the corresponding parameters. Therefore, an anthropomorphic obstacle-avoidance trajectory planning strategy for adaptive driving scenarios is proposed. First, numerous expert-demonstrated trajectories are extracted from the HighD natural driving dataset. Subsequently, a trajectory expectation feature-matching algorithm is proposed that uses maximum entropy inverse reinforcement learning theory to learn the extracted expert-demonstrated trajectories and achieve automatic acquisition of the optimization function of the expert-demonstrated trajectory. Furthermore, a mapping model is constructed by combining the key driving scenario information that affects vehicle obstacle avoidance with the weight of the optimization function, and an anthropomorphic obstacle avoidance trajectory planning strategy for adaptive driving scenarios is proposed. Finally, the proposed strategy is verified based on real driving scenarios. The results show that the strategy can adjust the weight distribution of the trajectory optimization function in real time according to the “emergency degree” of obstacle avoidance and the state of the vehicle. Moreover, this strategy can generate anthropomorphic trajectories that are similar to expert-demonstrated trajectories, effectively improving the adaptability and acceptability of trajectories in driving scenarios.

关键词： Obstacle avoidance trajectory planning     Inverse reinforcement theory     Anthropomorphic     Adaptive driving scenarios    

HTML PDF 收藏

Automated synthesis of steady-state continuous processes using reinforcement learning

《化学科学与工程前沿（英文）》 2022年 第16卷 第2期   页码 288-302 doi: 10.1007/s11705-021-2055-9

摘要： Automated flowsheet synthesis is an important field in computer-aided process engineering. The present work demonstrates how reinforcement learning can be used for automated flowsheet synthesis without any heuristics or prior knowledge of conceptual design. The environment consists of a steady-state flowsheet simulator that contains all physical knowledge. An agent is trained to take discrete actions and sequentially build up flowsheets that solve a given process problem. A novel method named SynGameZero is developed to ensure good exploration schemes in the complex problem. Therein, flowsheet synthesis is modelled as a game of two competing players. The agent plays this game against itself during training and consists of an artificial neural network and a tree search for forward planning. The method is applied successfully to a reaction-distillation process in a quaternary system.

关键词： automated process synthesis     flowsheet synthesis     artificial intelligence     machine learning     reinforcement learning    

HTML PDF 收藏

Deep reinforcement learning-based critical element identification and demolition planning of frame structures

Shaojun ZHU; Makoto OHSAKI; Kazuki HAYASHI; Shaohan ZONG; Xiaonong GUO

《结构与土木工程前沿（英文）》 2022年 第16卷 第11期   页码 1397-1414 doi: 10.1007/s11709-022-0860-y

摘要： This paper proposes a framework for critical element identification and demolition planning of frame structures. Innovative quantitative indices considering the severity of the ultimate collapse scenario are proposed using reinforcement learning and graph embedding. The action is defined as removing an element, and the state is described by integrating the joint and element features into a comprehensive feature vector for each element. By establishing the policy network, the agent outputs the Q value for each action after observing the state. Through numerical examples, it is confirmed that the trained agent can provide an accurate estimation of the Q values, and handle problems with different action spaces owing to utilization of graph embedding. Besides, different behaviors can be learned by varying hyperparameters in the reward function. By comparing the proposed method and the conventional sensitivity index-based methods, it is demonstrated that the computational cost is considerably reduced because the reinforcement learning model is trained offline. Besides, it is proved that the Q values produced by the reinforcement learning agent can make up for the deficiencies of existing indices, and can be directly used as the quantitative index for the decision-making for determining the most expected collapse scenario, i.e., the sequence of element removals.

关键词： progressive collapse     alternate load path     demolition planning     reinforcement learning     graph embedding    

HTML PDF 收藏

Effect of earth reinforcement, soil properties and wall properties on bridge MSE walls

《结构与土木工程前沿（英文）》 2021年 第15卷 第5期   页码 1209-1221 doi: 10.1007/s11709-021-0764-2

摘要： Mechanically stabilized earth (MSE) retaining walls are popular for highway bridge structures. They have precast concrete panels attached to earth reinforcement. The panels are designed to have some lateral movement. However, in some cases, excessive movement and even complete dislocation of the panels have been observed. In this study, 3-D numerical modeling involving an existing MSE wall was undertaken to investigate various wall parameters. The effects of pore pressure, soil cohesion, earth reinforcement type and length, breakage/slippage of reinforcement and concrete strength, were examined. Results showed that the wall movement is affected by soil pore pressure and reinforcement integrity and length, and unaffected by concrete strength. Soil cohesion has a minor effect, while the movement increased by 13–20 mm for flexible geogrid reinforced walls compared with the steel grid walls. The steel grid stresses were below yielding, while the geogrid experienced significant stresses without rupture. Geogrid reinforcement may be used taking account of slippage resistance and wall movement. If steel grid is used, non-cohesive soil is recommended to minimize corrosion. Proper soil drainage is important for control of pore pressure.

关键词： mechanically stabilized earth walls     precast concrete panels     backfill soil     finite element modeling     earth reinforcement    

HTML PDF 收藏

Layout optimization of steel reinforcement in concrete structure using a truss-continuum model

《结构与土木工程前沿（英文）》 2023年 第17卷 第5期   页码 669-685 doi: 10.1007/s11709-023-0963-0

摘要： Owing to advancement in advanced manufacturing technology, the reinforcement design of concrete structures has become an important topic in structural engineering. Based on bi-directional evolutionary structural optimization (BESO), a new approach is developed in this study to optimize the reinforcement layout in steel-reinforced concrete (SRC) structures. This approach combines a minimum compliance objective function with a hybrid truss-continuum model. Furthermore, a modified bi-directional evolutionary structural optimization (M-BESO) method is proposed to control the level of tensile stress in concrete. To fully utilize the tensile strength of steel and the compressive strength of concrete, the optimization sensitivity of steel in a concrete–steel composite is integrated with the average normal stress of a neighboring concrete. To demonstrate the effectiveness of the proposed procedures, reinforcement layout optimizations of a simply supported beam, a corbel, and a wall with a window are conducted. Clear steel trajectories of SRC structures can be obtained using both methods. The area of ​​critical tensile stress in concrete yielded by the M-BESO is more than 40% lower than that yielded by the uniform design and BESO. Hence, the M-BESO facilitates a fully digital workflow that can be extremely effective for improving the design of steel reinforcements in concrete structures.

关键词： bi-directional evolutionary structural optimization     steel-reinforced concrete     concrete stress     reinforcement method     hybrid model    

HTML PDF 收藏

Toward Trustworthy Decision-Making for Autonomous Vehicles: A Robust Reinforcement Learning Approach

Xiangkun He,Wenhui Huang,Chen Lv,

《工程（英文）》 doi: 10.1016/j.eng.2023.10.005

摘要： While autonomous vehicles are vital components of intelligent transportation systems, ensuring the trustworthiness of decision-making remains a substantial challenge in realizing autonomous driving. Therefore, we present a novel robust reinforcement learning approach with safety guarantees to attain trustworthy decision-making for autonomous vehicles. The proposed technique ensures decision trustworthiness in terms of policy robustness and collision safety. Specifically, an adversary model is learned online to simulate the worst-case uncertainty by approximating the optimal adversarial perturbations on the observed states and environmental dynamics. In addition, an adversarial robust actor-critic algorithm is developed to enable the agent to learn robust policies against perturbations in observations and dynamics. Moreover, we devise a safety mask to guarantee the collision safety of the autonomous driving agent during both the training and testing processes using an interpretable knowledge model known as the Responsibility-Sensitive Safety model. Finally, the proposed approach is evaluated through both simulations and experiments. These results indicate that the autonomous driving agent can make trustworthy decisions and drastically reduce the number of collisions through robust safety policies.

关键词： Autonomous vehicle     Decision-making     Reinforcement learning     Adversarial attack     Safety guarantee    

HTML PDF 收藏

概念加固思想及工程应用

段敬民,钱永久,张方,曾宪桃

《中国工程科学》 2005年 第7卷 第8期   页码 22-25

摘要：

提出了工程结构加固中新的思路——概念加固。概念加固是运用人的思维和判断，从宏观上决定工程加固中的基本问题、基本概念及基本原则，并阐述了基于“概念加固”思想指导下的整体预应力加固技术，介绍了在工程加固中的应用实例。

关键词： 工程结构     概念加固     整体预应力加固技术    

HTML PDF 收藏

Monitoring corrosion of reinforcement in concrete structures via fiber Bragg grating sensors

Zhupeng ZHENG, Xiaoning SUN, Ying LEI

《机械工程前沿（英文）》 2009年 第4卷 第3期   页码 316-319 doi: 10.1007/s11465-009-0040-y

摘要： Corrosion of steel and rebar in concrete structures is one of the most frequent reasons for civil infrastructure failures. Thus, improving the effective corrosion sensor technology can greatly reduce cost and provide safe structures with long service lives. However, assessing the corrosion condition of rebars is not simple because they are buried in concrete. In this paper, using fiber Bragg grating (FBG), a corrosion sensor for monitoring steel rebars embedded in a concrete structure is developed and validated by experiments. Based on the fact that the volume and diameter of a rebar embedded in concrete will enlarge due to corrosion, an FBG packaged with fiber-reinforced plastics (FRP) is wrapped on the steel bar. During corrosion, the increase in the bar diameter leads to the increase in fiber strain, which can be measured by the shift of the wavelength of FBG. Performances of the corrosion sensor are validated by accelerating corrosion in lab experiments. The corrosion sensor is embedded in a concrete specimen put in a 5% sodium chloride solution with a constant current. Experimental results show that the corrosion sensor can monitor the concurrence of corrosion of rebars in concrete. The corrosion extent can be quantitatively evaluated through the change in the wavelength of FBG. Therefore, the corrosion sensor developed in this paper is feasible for monitoring the early corrosion of rebars in concrete.

关键词： fiber Bragg grating (FBG)     corrosion     concrete structures     accelerated corrosion test    

HTML PDF 收藏

Seismic effects on reinforcement load and lateral deformation of geosynthetic-reinforced soil walls

《结构与土木工程前沿（英文）》 2021年 第15卷 第4期   页码 1001-1015 doi: 10.1007/s11709-021-0734-8

摘要： Current design methods for the internal stability of geosynthetic-reinforced soil (GRS) walls postulate seismic forces as inertial forces, leading to pseudo-static analyses based on active earth pressure theory, which yields unconservative reinforcement loads required for seismic stability. Most seismic analyses are limited to the determination of maximum reinforcement strength. This study aimed to calculate the distribution of the reinforcement load and connection strength required for each layer of the seismic GRS wall. Using the top-down procedure involves all of the possible failure surfaces for the seismic analyses of the GRS wall and then obtains the reinforcement load distribution for the limit state. The distributions are used to determine the required connection strength and to approximately assess the facing lateral deformation. For sufficient pullout resistance to be provided by each reinforcement, the maximum required tensile resistance is identical to the results based on the Mononobe–Okabe method. However, short reinforcement results in greater tensile resistances in the mid and lower layers as evinced by compound failure frequently occurring in GRS walls during an earthquake. Parametric studies involving backfill friction angle, reinforcement length, vertical seismic acceleration, and secondary reinforcement are conducted to investigate seismic impacts on the stability and lateral deformation of GRS walls.

关键词： geosynthetics     reinforced soil     retaining walls     seismic performance    

HTML PDF 收藏

Distributed fiber optic monitoring of a CFA pile with a central reinforcement bar bundle

Yi RUI, Nicholas de BATTISTA, Cedric KECHAVARZI, Xiaomin XU, Mei YIN

《结构与土木工程前沿（英文）》 2021年 第15卷 第1期   页码 167-176 doi: 10.1007/s11709-020-0581-z

摘要： In this paper, we present an application of distributed fiber optic sensor (DFOS) technology to measure the strain of a continuous flight auger (CFA) test pile with a central reinforcement bar bundle, during a static load test carried out in London. Being distributed in nature, DFOS gives much more information about the pile performance as compared to traditional point sensors, such as identifying cross-sectional irregularities or other anomalies. The strain profiles recorded along the depth of the piles from the DFOS were used to calculate pile deformation (contraction), shaft friction, and tip resistance under various loads. Based on this pile load test, a finite element (FE) analysis was performed using a one-dimensional nonlinear load-transfer model. Calibrated by the shaft friction and tip resistance derived from the monitored data, the FE model was able to simulate the pile and soil performance during the load testing with good accuracy. The effect of the reinforcement cage and central reinforcement bar bundle were investigated, and it was found that the addition of a reinforcement cage would reduce the pile settlement by up to 20%.

关键词： continuous flight auger pile     static load test     central reinforcement bar bundle     distributed fiber optic sensor     finite element     load transfer    

HTML PDF 收藏

Innovative hybrid reinforcement constituting conventional longitudinal steel and FRP stirrups for improved

Mostafa FAKHARIFAR,Ahmad DALVAND,Mohammad K. SHARBATDAR,Genda CHEN,Lesley SNEED

《结构与土木工程前沿（英文）》 2016年 第10卷 第1期   页码 44-62 doi: 10.1007/s11709-015-0295-9

摘要： The use of fiber reinforced polymer (FRP) reinforcement is becoming increasingly attractive in construction of new structures. However, the inherent linear elastic behavior of FRP materials up to rupture is considered as a major drawback under seismic attacks when significant material inelasticity is required to dissipate the input energy through hysteretic cycles. Besides, cost considerations, including FRP material and construction of pre-fabricated FRP configurations, especially for stirrups, and probable damage to epoxy coated fibers when transported to the field are noticeable issues. The current research has proposed a novel economical hybrid reinforcement scheme for the next generation of infrastructures implementing on-site fabricated FRP stirrups comprised of FRP sheets. The hybrid reinforcement consists of conventional longitudinal steel reinforcement and FRP stirrups. The key feature of the proposed hybrid reinforcement is the enhanced strength and ductility owing to the considerable confining pressure provided by the FRP stirrups to the longitudinal steel reinforcement and core concrete. Reinforced concrete beam specimens and beam-column joint specimens were tested implementing the proposed hybrid reinforcement. The proposed hybrid reinforcement, when compared with conventional steel stirrups, is found to have higher strength, stiffness, and energy dissipation. Design methods, structural behavior, and applicability of the proposed hybrid reinforcement are discussed in detail in this paper.

关键词： FRP     ductility     confinement     seismic     shear    

HTML PDF 收藏

Hybrid flexural components: Testing pre-stressed steel and GFRP bars together as reinforcement for flexural

Mohammed FARUQI, Oved I. MATA, Francisco AGUINIGA

《结构与土木工程前沿（英文）》 2018年 第12卷 第3期   页码 352-360 doi: 10.1007/s11709-017-0453-3

摘要：

Concrete members historically have used either pre-stressed steel or steel bars. In recent years there has been an increased interest in the use of fiber reinforced polymer (FRP) materials. However, the flexure behavior of a hybrid system reinforced by the combination of pre-stressed steel and glass fiber reinforced (GFRP) is still relatively unknown. The purpose of this work is to study this. Two slabs of 100 and 150-millimeter thickness, with a span of 2.1 m reinforced with both pre-stressing steel and GFRP were constructed and tested to failure using ACI 318-11 and ACI 440.1R-15. The concrete had strength of 31 MPa and the slabs were respectively reinforced with 5#4 bars and 3#5 bars. Each slab had 37.41 mm2 prestressing wire with a failure stress of 1722.5 MPa. The experimental flexural strength and deflection of slabs were compared with their respective sizes theoretical slabs. The theoretical slabs were either reinforced with pre-stressed steel or GFRP rebars, or a hybrid system. It was found that the hybrid system produces better results.

关键词： Partial pre-stressing     composite structures     GFRP bars    

HTML PDF 收藏

标题 作者 时间 类型 操作

A new automatic convolutional neural network based on deep reinforcement learning for fault diagnosis

期刊论文

Punching of reinforced concrete slab without shear reinforcement: Standard models and new proposal

Luisa PANI, Flavio STOCHINO

期刊论文

Spatial embedded reinforcement of 20-node block element for analysis PC bridges

LONG Peiheng, DU Xianting, CHEN Weizhen

期刊论文

Anthropomorphic Obstacle Avoidance Trajectory Planning for Adaptive Driving Scenarios Based on Inverse Reinforcement

Jian Wu,Yang Yan,Yulong Liu,Yahui Liu,

期刊论文

Automated synthesis of steady-state continuous processes using reinforcement learning

期刊论文

Deep reinforcement learning-based critical element identification and demolition planning of frame structures

Shaojun ZHU; Makoto OHSAKI; Kazuki HAYASHI; Shaohan ZONG; Xiaonong GUO

期刊论文

Effect of earth reinforcement, soil properties and wall properties on bridge MSE walls

期刊论文

Layout optimization of steel reinforcement in concrete structure using a truss-continuum model

期刊论文

Toward Trustworthy Decision-Making for Autonomous Vehicles: A Robust Reinforcement Learning Approach

Xiangkun He,Wenhui Huang,Chen Lv,

期刊论文

概念加固思想及工程应用

段敬民,钱永久,张方,曾宪桃

期刊论文

Monitoring corrosion of reinforcement in concrete structures via fiber Bragg grating sensors

Zhupeng ZHENG, Xiaoning SUN, Ying LEI

期刊论文

Seismic effects on reinforcement load and lateral deformation of geosynthetic-reinforced soil walls

期刊论文

Distributed fiber optic monitoring of a CFA pile with a central reinforcement bar bundle

Yi RUI, Nicholas de BATTISTA, Cedric KECHAVARZI, Xiaomin XU, Mei YIN

期刊论文

Innovative hybrid reinforcement constituting conventional longitudinal steel and FRP stirrups for improved

Mostafa FAKHARIFAR,Ahmad DALVAND,Mohammad K. SHARBATDAR,Genda CHEN,Lesley SNEED

期刊论文

Hybrid flexural components: Testing pre-stressed steel and GFRP bars together as reinforcement for flexural

Mohammed FARUQI, Oved I. MATA, Francisco AGUINIGA

期刊论文