检索结果-内蒙古大学图书馆

SSRN 2023年

作者： Kwon, Yeong-Man Moon, Jun Ho Cho, Gye-Chun Kim, Young Uk Chang, Ilhan Daejeon34141 Korea Republic of Department of Civil and Environmental Engineering Myongji University Yongin17058 Korea Republic of Department of Civil Systems Engineering Ajou University Suwon16499 Korea Republic of

Owing to their hydraulic and mechanical properties and low environmental impact, biopolymers, naturally-produced polymers, can be employed as an alternative to conventional civil engineering materials for internal erosion prevention. However, the internal erosion behavior of biopolymer-treated soils, particularly in a full-scale embankment, has not yet been thoroughly investigated. Therefore, this study investigated the application of xanthan gum biopolymer for internal erosion control in earthen embankments. Notably, xanthan gum biopolymer-based soil treatment (BPST) significantly increased the embankment’s resilience to internal erosion by enhancing the soils’ plasticity and mechanical strength. Furthermore, the thermal observations revealed a significant reduction in thermal anomalies with biopolymer treatments. © 2023, The Authors. All rights reserved.

关键词： Embankments

Ampilot: An Open Benchmark for Autonomous Transportation with Large Language Models in Open-Pit Mines

学校读者我要写书评

暂无评论

SSRN 2025年

作者： Teng, Siyu Wang, Jing Yan, Ran Peng, Mingxing Zhu, Meixin Chen, Long Zhu, Jiasong College of Civil and Transportation Engineering Shenzhen University Shenzhen China Department of Civil and Environmental Engineering The Hong Kong University of Science and Technology Clear Water Bay Hong Kong School of Civil and Environmental Engineering Nanyang Technological University Singapore Guangzhou China School of Transportation Southeast University China The State Key Laboratory of Multimodal Artificial Intelligence Systems Institute of Automation Chinese Academy of Sciences Beijing China

Significant advancements have been made in autonomous transportation in recent years. However, the deployment of autonomous technologies in open-pit mines—characterized by unstructured environments—remains formidable challenges due to inherent difficulties such as complex working conditions, blurred environmental textures, and hard mechanical control. Large language models (LLMs), renowned for their impressive learning and reasoning capabilities, offer promising solutions to these challenges. In this research, we introduce AMPolit, a benchmark specifically developed to train and evaluate the efficacy of language model programs for autonomous transportation in open-pit mines. AMPolit consists of two core components: (a) AMPolit-Dataset: A collection of 180,000 single-modality frames selected from 26 hours of human-machine hybrid driving data, spanning multiple mining areas across various periods. Each frame is paired with detailed natural language instruction prompts designed for mining scenarios;(b) AMPolit-Metrix: An open-loop evaluation metric designed for the distinctive transportation scenarios and stringent safety requirements of open-pit mines, aimed at assessing the suitability of autonomous transportation models and guiding their optimization. We conduct extensive experiments to evaluate the performance of state-of-the-art LLM-based transportation models on AMPolit. The results demonstrate that LLMs exhibit significantly greater potential in managing mining transportation scenarios compared to traditional learning-based approaches. To support further research and development in unmanned mining, we will open-source our data at https://***/tengsiyu/***. © 2025, The Authors. All rights reserved.

关键词： Open pit mining

Transferring self-supervised pre-trained models for SHM data anomaly detection with scarce labeled data

学校读者我要写书评

暂无评论

arXiv

arXiv 2024年

作者： Zhou, Mingyuan Jian, Xudong Xia, Ye Lai, Zhilu Guangzhou China Future Resilient Systems Singapore-ETH Centre Singapore Singapore Department of Civil Environmental and Geomatic Engineering ETH Zurich Zurich Switzerland Department of Bridge Engineering Tongji University Shanghai China Shanghai Qi Zhi Institute Shanghai China The Department of Civil and Environmental Engineering The Hong Kong University of Science and Technology Hong Kong

Structural health monitoring (SHM) has experienced significant advancements in recent decades, accumulating massive monitoring data. Data anomalies inevitably exist in monitoring data, posing significant challenges to their effective utilization. Recently, deep learning has emerged as an efficient and effective approach for anomaly detection in bridge SHM. Despite its progress, many deep learning models require large amounts of labeled data for training. The process of labeling data, however, is labor-intensive, time-consuming, and often impractical for large-scale SHM datasets. To address these challenges, this work explores the use of self-supervised learning (SSL), an emerging paradigm that combines unsupervised pre-training and supervised fine-tuning. The SSL-based framework aims to learn from only a very small quantity of labeled data by fine-tuning, while making the best use of the vast amount of unlabeled SHM data by pre-training. Mainstream SSL methods are compared and validated on the SHM data of two in-service bridges. Comparative analysis demonstrates that SSL techniques boost data anomaly detection performance, achieving increased F1 scores compared to conventional supervised training, especially given a very limited amount of labeled data. This work manifests the effectiveness and superiority of SSL techniques on large-scale SHM data, providing an efficient tool for preliminary anomaly detection with scarce label information. © 2024, CC BY.

关键词： Self-supervised learning

Lumped Drag Model Identification and Real-Time External Force Detection for Rotary-Wing Micro Aerial Vehicles

学校读者我要写书评

暂无评论

Lumped Drag Model Identification and Real-Time External Forc...

IEEE International Conference on Robotics and Automation (ICRA)

作者： Lucas Wälti Alcherio Martinoli Distributed Intelligent Systems and Algorithms Laboratory (DISAL) School of Architecture Civil and Environmental Engineering (ENAC) Swiss Federal Institute of Technology (EPFL) Lausanne Switzerland

ISBN: (数字)9798350384574

ISBN: (纸本)9798350384581

This work focuses on understanding and identifying the drag forces applied to a rotary-wing Micro Aerial Vehicle (MAV). We propose a lumped drag model that concisely describes the aerodynamical forces the MAV is subject to, with a minimal set of parameters. We only rely on commonly available sensor information onboard a MAV, such as accelerometer data, pose estimate, and throttle commands, which makes our method generally applicable. The identification uses an offline gradient-based method on flight data collected over specially designed trajectories. The identified model allows us to predict the aerodynamical forces experienced by the aircraft due to its own motion in real-time and, therefore, will be useful to distinguish them from external perturbations, such as wind or physical contact with the environment. The results show that we are able to identify the drag coefficients of a rotary-wing MAV through onboard flight data and observe the close correlation between the motion of the MAV, the measured external forces, and the predicted drag forces.

关键词： Accelerometers Force measurement Drag Perturbation methods Atmospheric modeling Wind tunnels Real-time systems

State of health estimation of retired battery for echelon utilization based on charging curve 29

学校读者我要写书评

暂无评论

State of health estimation of retired battery for echelon ut...

29th CIRP Conference on Life Cycle engineering, LCE 2022

作者： Ma, Huazheng Deng, Yelin Liu, Wei-Wei Li, Tao Zhang, Hongchao School of Mechanical Engineering Dalian University of Technology Liaoning Province Dalian116024 China Department of Civil and Environmental Engineering Soochow University Jiangsu Province Suzhou215131 China Department of Industrial Manufacturing and Systems Engineering Texas Tech University LubbockTX79409-3061 United States

Recently, the number of retired batteries for electric vehicles is gradually increasing with the improvement of the market share of electric vehicles. The demand for echelon utilization of retired batteries has become increasingly prominent. For the echelon utilization of retired batteries, compared with fresh batteries, more accurate state of health (SOH) estimation methods are needed to ensure the safe operation of the energy storage system. Taking the retired battery as the research object, this paper further carries on the accelerated aging test on the retired battery under the condition of variable environment temperature. Based on the voltage change in the constant current charging stage and the current change in the constant voltage charging stage, feature parameters that can reflect the dynamic change of the battery charging curve are extracted to estimate the battery discharge capacity. This paper also extracts feature parameters that can reflect the change of environment temperature and battery aging condition through correlation analysis. Finally, the SVR model is used to estimate the capacity of the retired battery. The selected feature parameters are used as input, and the battery discharge capacity is used as output. The accuracy of the model is verified with experimental data. © 2022 Elsevier B.V.. All rights reserved.

关键词： Life cycle

Artificial Intelligence in Water Resource Management: The Past, Present and Opportunities Thereof

学校读者我要写书评

暂无评论

SSRN 2024年

作者： Patil, Nishanth Anilkumar Savalkar, Supriya Department of Civil and Environmental Engineering University of Illinois at Urbana Champaign UrbanaIL61801-2352 United States Biological Systems Engineering Washington State University PullmanWA99163 United States

Artificial Intelligence (AI) has emerged as a transformative force in the field of water resource management. It has helped in better learning from the past, improved decision-making in the present, and provides a multitude of opportunities for the future. This review is an attempt to understand the progression in the use of AI techniques across applications related to water resource management. Traditionally in this field, there is reliance on on-site data collection and simplistic to more physics-based models, which sometimes fail to explain the inefficiencies and limitations of the system at large, are inept at capturing nuances of the system and impede decision-making. AI techniques have increasingly been adept in handling complex, nonlinear relationships within water system models and enable more accurate predictions and optimization frameworks. This paper attempts to present a review and rudimentary categorization of different types of applications of AI in the water resource management domain, spanning typical applications like modeling, prediction and forecasting, decision support frameworks, and optimization. The ability of AI methods to learn from data, derive appropriate classification, and model intricate dynamics of the system further underscores their versatility and modularity. The combination of these techniques aids the decision-makers with precise insights, leading to improved water management, allocation, and utilization frameworks. The ethical implications of AI in water resource management cannot be overlooked as responsible and fair use of AI technologies is imperative in development and deployment of these systems. © 2024, The Authors. All rights reserved.

关键词： Support vector machines

Online Min Cost Circulation for Multi-Object Tracking on Fragments

学校读者我要写书评

暂无评论

arXiv

arXiv 2023年

作者： Wang, Yanbing Ji, Junyi Barbour, William Work, Daniel B. Department of Civil and Environmental Engineering The Institute for Software Integrated Systems Vanderbilt University NashvilleTN37240 United States

Multi-object tracking (MOT) or global data association problem is commonly approached as a minimum-cost-flow or minimum-cost-circulation problem on a graph. While there have been numerous studies aimed at enhancing algorithm efficiency, most of them focus on the batch problem, where all the data must be available simultaneously to construct a static graph. However, with the growing number of applications that generate streaming data, an efficient online algorithm is required to handle the streaming nature of the input. In this paper, we present an online extension of the well-known negative cycle canceling algorithm for solving the multi-object tracking problem with streaming fragmented data. We provide a proof of correctness for the proposed algorithm and demonstrate its efficiency through numerical experiments. © 2023, CC BY-NC-ND.

关键词： Flow graphs

Routing Guidance for Emerging Transportation systems with Improved Dynamic Trip Equity

学校读者我要写书评

暂无评论

arXiv

arXiv 2025年

作者： Bai, Ting Li, Anni Xu, Gehui Cassandras, Christos G. Malikopoulos, Andreas A. Information and Decision Science Lab School of Civil & Environmental Engineering Cornell University IthacaNY United States Division of Systems Engineering Center for Information and Systems Engineering Boston University BrooklineMA United States Department of Electrical and Electronic Engineering Imperial College London LondonSW7 2AZ United Kingdom

In this letter, we present a dynamic routing guidance system that optimizes route recommendations for individual vehicles within an emerging transportation system while enhancing travelers’ trip equity. We develop a framework to quantify trip quality and equity in a dynamic travel environment, providing new insights into how routing guidance influences equity in road transportation. Our approach enables real-time routing by incorporating both monitored and anticipated traffic congestion. We provide conditions that ensure achieving perfect trip equity for all travelers in a free-flow network. Finally, simulation studies on 1,000 vehicles traversing an urban road network in Boston demonstrate that our proposed method improves trip equity by approximately 13.3% compared to the shortest-route strategy. In addition, the results reveal that our approach redistributes travel costs across vehicle types through route optimization, contributing to a more equitable transportation system. Copyright © 2025, The Authors. All rights reserved.

关键词： Traffic congestion

Effect of Skeletonization on Energy Consumption of Water Distribution System

学校读者我要写书评

暂无评论

Effect of Skeletonization on Energy Consumption of Water Dis...

World environmental and Water Resources Congress 2023: Adaptive Planning and Design in an Age of Risk and Uncertainty

作者： Pasha, M. Fayzul K. Perez, Luis Weathers, Matthew Smith, Brennan Dept. of Civil and Geomatics Engineering California State Univ FresnoCA United States Water Power Program and Energy-Water Resource Systems Group Environmental Sciences Division Oak Ridge National Laboratory Oak RidgeTN United States

ISBN: (数字)9780784484852

ISBN: (纸本)9780784484852

A skeletonized water distribution system (WDS) model plays an important role in decision making process for its design and operations in planning phase. Given energy is the main driving force to operate a WDS efficiently and with the recent hikes in energy price, the investigation of energy flow in WDS is much more important than ever before. While a skeletonized network is easy to handle and takes less amount of time to run, it should represent the real-world scenario including the demand and hydraulics as accurately as possible. Failure to represent real-world scenario can mislead design and operational decisions including energy consumptions and delivery pressure. The purpose of this paper is to investigate how the energy flow in a WDS varies with the extent of the skeletonized network. Keeping the total demand constant for a network and the spatial distribution of the demand within a range in the skeletonized networks, how the energy consumption at the pump station, energy loss in the pipe, and the energy storage in the tank vary with the size of the skeletonized networks are investigated in this study. Energy balance model has been set up for each skeletonized model to observe the impact on energy flow for a series of models. Since the number of pipes and nodes can impact hydraulics, which eventually impact the energy flow, the paper considers two types of networks: branch and loop water distribution systems. The study has been applied to two hypothetical literature networks. Due to skeletonization, the flow pattern in the loop system changes more than that in the branch system causing higher percentage change of frictional energy loss in the loop system. The energy consumption or loss per unit demand per node in the skeletonized networks is found almost linear for the branch system. However, this parameter changes non-linearly in the skeletonized networks for the loop system. © World environmental and Water Resources Congress *** rights reserved

关键词： Energy utilization

A Framework for Location-Specific Feasibility Studies of Green Hydrogen Production for Urban Bus Fleets

学校读者我要写书评

暂无评论

SSRN 2024年

作者： Adekola, Kamaldeen Korede Ghafoori, Samim Dechamp, François Prada, Alessandro Department of Civil Environmental and Mechanical Engineering University of Trento Trento Italy Research and Development Unit ABMI Engineering Company Nanterre France Department of Energy Systems and Environment IMT Atlantique Nantes France

In the EU, most key sectors have shown a downward trend in CO2 emissions between 1990 and 2020 except for road transport. There is an opportunity for hydrogen-powered fuel-cell electric buses to play a huge role in the decarbonization of city buses. However, one key roadblock to the adoption of fuel cell vehicles is the high cost of green hydrogen and insufficient green hydrogen infrastructure to support mass transit. In this study, a simulation tool has been developed for conducting detailed feasibility studies at an hourly granularity on the deployment of green hydrogen hubs for fuel cell bus fleets in any location in Europe. The study evaluated the operational and economic performance of five distinct green hydrogen hub deployment configurations, each of which must meet the required hydrogen demand for a metropolitan bus fleet on an hourly basis. Each configuration differs based on the mix of energy sources (PV, wind, grid), capacity sizing, financial structure, and grid interaction mechanisms. Among the key findings, a grid-connected configuration is noted for the highest levelized cost of hydrogen (LCOH), exceeding 20 €/kg.H2, primarily due to skyrocketing wholesale electricity prices in Europe. Conversely, the grid-interactive renewable energy plant and grid-interactive renewable PPA yield the lowest LCOH at 4 and 5 €/kg respectively, benefiting from revenue derived from surplus electricity sales. It is noteworthy that the LCOH also varies significantly by location with Brandenburg, Germany presenting the lowest and Andalucia, Spain the highest across most of the configurations, highlighting the need for location specific planning of green hydrogen hubs for transport fleet decarbonization. © 2024, The Authors. All rights reserved.

关键词： Renewable energy