检索结果-内蒙古大学图书馆

Drive-By Detection of Scour in a Railway Bridge

JOURNAL OF BRIDGE ENGINEERING 2025年第7期30卷

作者： Tola, Sinem O'Brien, Eugene Cantero, Daniel Tinoco, Joaquim Matos, Jose C. Bose, Tulika Berkers, Jos Univ Minho Dept Civil Engn ISISE ARISE P-4800058 Guimaraes Portugal Univ Coll Dublin Sch Civil Engn Dublin D04 V1W8 Ireland Norwegian Univ Sci & Technol NTNU Dept Struct Engn Richard Birkelands Vei 1A N-7491 Trondheim Norway Univ Minho Dept Civil Engn ISISE ARISE P-4800058 Guimaraes Portugal Fugro BV Railway Consultancy Blaeulaan 60A NL-3528 AD Utrecht Netherlands

This paper proposes an innovative indirect monitoring system for bridge foundation scour damage detection. The Rail Infrastructure Alignment Acquisition system, a mobile mapping system that can be attached to the front or rear of an operating train, is used for data acquisition. The difference between healthy and damaged pier stiffness responses is utilized as the scour indicator. A cross-entropy optimization algorithm finds the pier stiffness values that minimize the difference between the displacements computed with a numerical model and the measurements. The numerical model adopts the unit load theorem to determine the Moving Reference Influence Lines for a six-axle vehicle crossing the bridge, simulating Rail Infrastructure Alignment Acquisition system displacement measurements on a railway bridge in the UK. The measurements provided belong to the after-repair, i.e., the healthy stage, of the bridge. Due to the absence of scoured-stage measurements, the displacement response of the damaged bridge is synthetically generated using a vehicle-bridge interaction model. Foundation scour is modeled by reducing the vertical pier stiffness. With healthy-bridge field data and synthetically generated damaged-bridge responses superposed with rail irregularities, it is possible to detect the presence of the scour. This approach not only facilitates the early detection of foundation scour but also enhances infrastructure maintenance strategies by enabling the implementation of timely and targeted repairs, thereby improving the safety and resilience of railway operations.

关键词： Bridge scour Scour detection Indirect monitoring optimization algorithms Rail infrastructure alignment acquisition system

来源：评论

学校读者我要写书评

暂无评论

Estimation of rapid chloride permeability of SCC using hyperparameters optimized random forest models

引用

JOURNAL OF SUSTAINABLE CEMENT-BASED MATERIALS 2023年第5期12卷 542-560页

作者： Ge, Da-Ming Zhao, Li-Cai Esmaeili-Falak, Mahzad Nanjing Forestry Univ Coll Civil Engn Nanjing 210037 Jiangsu Peoples R China China Railway 19th Bur Grp Third Engn Co Ltd Shenyang 110136 Peoples R China Natl Taiwan Univ Sci & Technol Dept Civil & Construct Engn 43 Keelung Rd Sec 4 Keelung 106 Taiwan Islamic Azad Univ North Tehran Branch Dept Civil Engn Tehran Iran

Discovering concrete properties takes time, money, laboratory design, material preparation, and testing with adequate equipment at the right ages. As a consequence, in the concrete sector, solutions that minimize or reduce cost, time, and other downsides are essential. So, utilizing forecasting systems to compute concrete characteristics based on historical data is quite advantageous. Employing the rapid chloride penetration test (RCPT), this study proposed novel classification models for predicting chloride penetration into self-compacting concrete (SCC). Designs for predicting the quantity of RCPT are constructed utilizing optimized random forest (RF) classifications, which have not yet been outlined in the literature. The fundamental objective of this research is to build innovative combined classification models that combine RF with optimization techniques such as particle swarm optimization (PSO), whale optimization algorithm (WOA), and Harris hawks optimization (HHO) for better approximation of RCPT. Using PSO, WOA, and HHO, five critical RF model hyperparameters were fine-tuned to provide the most powerful and dependable RF models ever. Considered combined classifications were trained by seven variables, namely cement content, fly ash, silica fume, a ratio of coarse and fine aggregates, water to cement ratio, and temperature. The findings reveal that in the training/testing phases, all three approaches had appropriate efficiency in estimating the RCPT, reflecting the allowable correlation among actual and anticipated values. HHO - RF outperforms the other versions in both stages, with R-2 and RMSE of 0.9854 and 28.6 for the learning phase and 0.9645 and 41.44 for the assessment phase, respectively. Although the performance evaluator indices for PSO - RF are lower than HHO - RF and WOA - RF models, it has acceptable results with R-2 larger than 0.9243. Overall, the findings show that the HHO method is more capable than PSO and WOA at calculating the ideal valu

关键词： rapid chloride permeability of concrete fly ash silica fume random forest optimization algorithms

来源：评论

学校读者我要写书评

暂无评论

On the Convergence of Decentralized Federated Learning Under Imperfect Information Sharing

引用

IEEE CONTROL SYSTEMS LETTERS 2023年 7卷 2982-2987页

作者： Chellapandi, Vishnu Pandi Upadhyay, Antesh Hashemi, Abolfazl Zak, Stanislaw H. Purdue Univ Coll Engn W Lafayette IN 47907 USA

Most of the current literature focused on centralized learning is centered around the celebrated average-consensus paradigm and less attention is devoted to scenarios where the communication between the agents may be imperfect. This letter presents three different algorithms of Decentralized Federated Learning (DFL) in the presence of imperfect information sharing modeled as noisy communication channels. The first algorithm, Federated Noisy Decentralized Learning (FedNDL1) comes from the literature, where the noise is added to the algorithm parameters to simulate the scenario of the presence of noisy communication channels. This algorithm shares parameters to form a consensus with the clients based on a communication graph topology through a noisy communication channel. The proposed second algorithm (FedNDL2) is similar to the first algorithm but with added noise to the parameters and it performs the gossip averaging before the gradient optimization. The proposed third algorithm (FedNDL3), on the other hand, shares the gradients through noisy communication channels instead of the parameters. Theoretical and experimental results show that under imperfect information sharing, the third scheme that mixes gradients is more robust in the presence of a noisy channel compared with the algorithms from the literature that mix the parameters.

关键词： optimization algorithms distributed control stochastic systems numerical algorithms

来源：评论

学校读者我要写书评

暂无评论

Tracking Point Vortices and Circulations via Advected Passive Particles: An Estimation Approach

引用

IEEE CONTROL SYSTEMS LETTERS 2023年 7卷 1760-1765页

作者： Marques, Gil Afonso, Marco Martins Gama, Silvio Univ Porto Fac Ciencias Ctr Matemat Univ Porto Dept Matemat P-4169007 Porto Portugal

We present a novel method for estimating the circulations and positions of point vortices in a two-dimensional (2D) environment using trajectory data of passive particles in the presence of Gaussian noise. The method comprises two algorithms: the first one calculates the vortex circulations, while the second one reconstructs the vortex trajectories. This reconstruction is done thanks to a hierarchy of optimization problems, involving the integration of systems of differential equations, over time sub-intervals all with the same amplitude defined by the autocorrelation function for the advected passive particles' trajectories. Our findings indicate that accurately tracking the position of vortices and determining their circulations is achievable, even when passive particle trajectories are affected by noise.

关键词： Trajectory Particle measurements Atmospheric measurements Autocorrelation optimization Mathematical models Differential equations Fluid flow systems numerical algorithms optimization algorithms

来源：评论

学校读者我要写书评

暂无评论

An Online Newton's Method for Time-Varying Linear Equality Constraints

引用

IEEE CONTROL SYSTEMS LETTERS 2023年 7卷 1423-1428页

作者： Lupien, Jean-Luc Lesage-Landry, Antoine Polytech Montreal GERAD & Mila Dept Elect Engn Montreal PQ H3T 1J4 Canada

We consider online optimization problems with time-varying linear equality constraints. In this framework, an agent makes sequential decisions using only prior information. At every round, the agent suffers an environment-determined loss and must satisfy time-varying constraints. Both the loss functions and the constraints can be chosen adversarially. We propose the Online Projected Equality-constrained Newton Method (OPEN-M) to tackle this family of problems. We obtain sublinear dynamic regret and constraint violation bounds for OPEN-M under mild conditions. Namely, smoothness of the loss function and boundedness of the inverse Hessian at the optimum are required, but not convexity. Finally, we show OPEN-M outperforms state-of-the-art online constrained optimization algorithms in a numerical network flow application.

关键词： Heuristic algorithms optimization Machine learning algorithms Power system dynamics Upper bound Newton method Measurement optimization algorithms time-varying systems machine learning

来源：评论

学校读者我要写书评

暂无评论

On Distributed Nonconvex Optimisation via Modified ADMM

引用

IEEE CONTROL SYSTEMS LETTERS 2023年 7卷 3699-3704页

作者： Mafakheri, Behnam Manton, Jonathan H. Shames, Iman Univ Melbourne Dept Elect & Elect Engn Melbourne Vic 3010 Australia Australian Natl Univ Sch Engn CIICADA Lab Canberra ACT 2601 Australia

This letter addresses the problem of nonconvex nonsmooth decentralised optimisation in multi-agent networks with undirected connected communication graphs. Our contribution lies in introducing an algorithmic framework designed for the distributed minimisation of the sum of a smooth (possibly nonconvex and non-separable) function and a convex (possibly nonsmooth and non-separable) regulariser. The proposed algorithm can be seen as a modified version of the ADMM algorithm where, at each step, an "inner loop" needs to be iterated for a number of iterations. The role of the inner loop is to aggregate and disseminate information across the network. We observe that a naive decentralised approach (one iteration of the inner loop) may not converge. We establish the asymptotic convergence of the proposed algorithm to the set of stationary points of the nonconvex problem where the number of iterations of the inner loop increases logarithmically with the step count of the ADMM algorithm. We present numerical results demonstrating the proposed method's correctness and performance.

关键词： optimization Convex functions Convergence Approximation algorithms Machine learning algorithms Distributed algorithms Australia optimization algorithms networked control systems

来源：评论

学校读者我要写书评

暂无评论

Social-Aware Long-Distance Trip Planner for Electric Vehicles Using Genetic Algorithm1

引用

ASME Letters in Dynamic Systems and Control 2023年第2期3卷 021011页

作者： Su, Zifei Lamantia, Maxavier Chen, Pingen Department of Mechanical Engineering Tennessee Technological University CookevilleTN38505 United States

In the past decade, the number of battery electric vehicles (BEVs) on the road has been growing rapidly in response to global climate change and cyclic gasoline shortages. Due to the limited driving range of most commercial BEVs, individuals who use BEVs for long-distance travel tend to spend much more time on the road than owners of traditional internal combustion engine vehicles. To reduce travel time in long-distance trips, a social-aware trip planner is necessary to coordinate driving speed, vehicle charging, and social activities (e.g., dining, visit of places of interest). This paper formulates this travel time minimization problem into a mixed-integer programming model and utilizes genetic algorithm (GA) to solve for the optimal driving speed, vehicle charging, and the schedule of dining. The proposed planner is first tested numerically based on two real-world routes. Then, Monte Carlo simulations are performed to give a thorough analysis on the performance of the proposed planner. The simulation results show that the proposed method outperforms the baseline on both routes. Additionally, real-world tests are conducted to further validate the accuracy of the mixed-integer programming model. Copyright © 2023 by ASME.

关键词： Vehicles social activities genetic algorithm Roads Genetic algorithms Batteries trip planner automotive systems control applications Electric vehicles Simulation results optimization algorithms Simulation battery electric vehicle

来源：评论

学校读者我要写书评

暂无评论

Learning in Stochastic Stackelberg Games

Learning in Stochastic Stackelberg Games

引用

American Control Conference (ACC)

作者： Das, Pranoy Nortmann, Benita Ratliff, Lillian J. Gupta, Vijay Mylvaganam, Thulasi Purdue Univ Elmore Family Sch Elect & Comp Engn W Lafayette IN 47907 USA Imperial Coll Dept Aeronaut London England Univ Washington Dept Elect & Comp Engn Seattle WA USA

ISBN: (纸本)9798350382662;9798350382655

We present a learning algorithm for players to converge to their stationary policies in a general sum stochastic sequential Stackelberg game. The algorithm is a two time scale implicit policy gradient algorithm that provably converges to stationary points of the optimization problems of the two players. Our analysis allows us to move beyond the assumptions of zero-sum or static Stackelberg games made in the existing literature for learning algorithms to converge.

关键词： optimization algorithms

来源：评论

学校读者我要写书评

暂无评论

Energy-aware resource management in Internet of vehicles using machine learning algorithms

引用

JOURNAL OF HIGH SPEED NETWORKS 2023年第1期29卷 27-39页

作者： Chen, Sichao Hu, Yuanchao Huang, Liejiang Shen, Dilong Pan, Yuanjun Pan, Ligang Hangzhou Xinmei Complete Elect Appliance Mfg Co L Hangzhou Peoples R China Shandong Univ Technol Zibo Shandong Peoples R China

Internet of Vehicles (IoV) presents a new generation of vehicular communications with limited computation offloading, energy and memory resources with 5G/6G technologies that have grown enormously and are being used in wide variety of Intelligent Transportation Systems (ITS). Due to the limited battery power in smart vehicles, the concept of energy consumption is one of the main and critical challenges of the IoV environments. Optimizing resource management strategies for improving the energy consumption using AI-based methods is one of important solutions in the IoV environments. There are various machine learning algorithms for selecting optimal solutions for energy-efficient resource management strategies. This paper presents the existing energy-aware resource management strategies for the IoV case studies, and performs a comparative analysis among their applied AI-based methods and machine learning algorithms. This analysis presents a technical and deeper understanding of the technical aspects of existing machine learning and AI-based algorithms that will be helpful in design of new hybrid AI approaches for optimizing resource management strategies with reducing their energy consumption.

关键词： Internet of Vehicles (IoV) energy consumption vehicular communications resource management machine learning optimization algorithms

来源：评论

学校读者我要写书评

暂无评论

Welfare Maximization Algorithm for Solving Budget-Constrained Multi-Component POMDPs

引用

IEEE CONTROL SYSTEMS LETTERS 2023年 7卷 1736-1741页

作者： Vora, Manav Thangeda, Pranay Grussing, Michael N. Ornik, Melkior Univ Illinois Dept Aerosp Engn Urbana IL 61801 USA Univ Illinois Coordinated Sci Lab Urbana IL 61801 USA US Army Corps Engineers Engineer Res & Dev Ctr Champaign IL 61822 USA

Partially Observable Markov Decision Processes (POMDPs) provide an efficient way to model real-world sequential decision making processes. Motivated by the problem of maintenance and inspection of a group of infrastructure components with independent dynamics, this letter presents an algorithm to find the optimal policy for a multi-component budget-constrained POMDP. We first introduce a budgeted-POMDP model (b-POMDP) which enables us to find the optimal policy for a POMDP while adhering to budget constraints. Next, we prove that the value function or maximal collected reward for a special class of b-POMDPs is a concave function of the budget for the finite horizon case. Our second contribution is an algorithm to calculate the optimal policy for a multi-component budget-constrained POMDP by finding the optimal budget split among the individual component POMDPs. The optimal budget split is posed as a welfare maximization problem and the solution is computed by exploiting the concavity of the value function. We illustrate the effectiveness of the proposed algorithm by proposing a maintenance and inspection policy for a group of real-world infrastructure components with different deterioration dynamics, inspection and maintenance costs. We show that the proposed algorithm vastly outperforms the policies currently used in practice.

关键词： Heuristic algorithms Costs Maintenance engineering Planning Inspection Markov processes Computational modeling optimization algorithms distributed control

来源：评论

学校读者我要写书评

暂无评论

建议与咨询留下您的常用邮箱和电话号码，以便我们向您反馈解决方案和替代方法

时间限定

文献类型

馆藏选择

核心期刊

语言

文献类型

帮助

文字说明：

检索规则说明：

检索范例：

分类表

所选分类

限定检索结果

文献类型

馆藏范围

日期分布

学科分类号

主题

机构

作者

语言

请选择保存的检索档案：

请选择收藏分类：

通借通还

建议与咨询 留下您的常用邮箱和电话号码，以便我们向您反馈解决方案和替代方法

时间限定

文献类型

馆藏选择

核心期刊

语言

文献类型

帮助

文字说明：

检索规则说明：

检索范例：

分类表

所选分类

限定检索结果

文献类型

馆藏范围

日期分布

学科分类号

主题

机构

作者

语言

请选择保存的检索档案： 新增检索档案 确定 取消

请选择收藏分类： 新增自定义分类 确定 取消

通借通还

建议与咨询留下您的常用邮箱和电话号码，以便我们向您反馈解决方案和替代方法

请选择保存的检索档案：

请选择收藏分类：