检索结果-内蒙古大学图书馆

10th International Conference on Structural Health Monitoring of Intelligent Infrastructure, SHMII 2021

作者： Bogomolov, Denis Testoni, Nicola Zonzini, Federica Malatesta, Michelangelo Maria de Marchi, Luca Marzani, Alessandro Advanced Research Center on Electronic Systems University of Bologna Bologna40126 Italy Department of Electrical Electronic and Information Engineering University of Bologna Bologna40136 Italy Department of Civil Chemical Environmental and Materials Engineering University of Bologna Bologna40136 Italy

In this work, we propose an innovative, low-cost and low-weight Sensor Node (SN) which can yield fast deployable sensor networks for long-term and real-time acoustic emission (AE) monitoring. Thanks to the interface and architecture of the developed system, Digital Signal Processing (DSP) functionalities were embedded in the proposed SN which are exploited for AE features extraction and signal characterization, compliant with a complete Structural Monitoring analysis. The on-board DSP strategy, performed in close proximity to AE transducers at monitoring facility, permits to significantly minimize the sensitivity to external noise which is the key reason for the poor signal-to-noise ratio of AE equipment in situ. The results of versatile testing experimental campaign demonstrated the applicability of the developed low-cost AE prototype to confidently detect and monitor AE activity in various materials. © 2021 International Conference on Structural Health Monitoring of Intelligent Infrastructure: Transferring Research into Practice, SHMII. All rights reserved.

关键词： Sensor nodes

来源：评论

学校读者我要写书评

暂无评论

A Recurrent Neural Network Enhanced Unscented Kalman Filter for Human Motion Prediction

arXiv

引用

arXiv 2024年

作者： Liu, Wansong Tian, Sibo Hu, Boyi Liang, Xiao Zheng, Minghui The Mechanical and Aerospace Engineering Department University at Buffalo BuffaloNY14260 United States J. Mike Walker’66 Department of Mechanical Engineering Texas A&M University College StationTX77840 United States The Industrial and Systems Engineering Department University of Florida GainesvilleFL32611 United States The Department of Civil & Environmental Engineering Texas A&M University College StationTX77840 United States

This paper presents a deep learning enhanced adaptive unscented Kalman filter (UKF) for predicting human arm motion in the context of manufacturing. Unlike previous network-based methods that solely rely on captured human motion data, which is represented as bone vectors in this paper, we incorporate a human arm dynamic model into the motion prediction algorithm and use the UKF to iteratively forecast human arm motions. Specifically, a Lagrangian-mechanics-based physical model is employed to correlate arm motions with associated muscle forces. Then a Recurrent Neural Network (RNN) is integrated into the framework to predict future muscle forces, which are transferred back to future arm motions based on the dynamic model. Given the absence of measurement data for future human motions that can be input into the UKF to update the state, we integrate another RNN to directly predict human future motions and treat the prediction as surrogate measurement data fed into the UKF. A noteworthy aspect of this study involves the quantification of uncertainties associated with both the data-driven and physical models in one unified framework. These quantified uncertainties are used to dynamically adapt the measurement and process noises of the UKF over time. This adaption, driven by the uncertainties of the RNN models, addresses inaccuracies stemming from the data-driven model and mitigates discrepancies between the assumed and true physical models, ultimately enhancing the accuracy and robustness of our predictions. One unique point of our method is that, it integrates a dynamic model of human arms and two RNN models, and uses Monte Carlo dropout sampling to quantify the uncertainties inherent in our RNN prediction models and transforms them into the covariances of the UKF’s measurement and process noises respectively. Compared to the traditional RNN-based prediction, our method demonstrates improved accuracy and robustness in extensive experimental validations of various types

关键词： Recurrent neural networks

来源：评论

学校读者我要写书评

暂无评论

Co-Optimization of Charging Scheduling and Platooning for Long-Haul Electric Freight Vehicles

SSRN

引用

SSRN 2022年

作者： Alam, Md Rakibul Guo, Zhaomiao Department of Civil Environmental and Construction Engineering Resilient Intelligent and Sustainable Energy Systems Cluster University of Central Florida FL32766 United States

Freight mileages have been significantly increasing over the past decade, accounting for 11% of global greenhouse gas (GHG) emissions. Freight electrification and platooning are two promising technologies to mitigate the energy and environmental impacts of freight transportation. Effective coordination of charging and platooning are urgently needed to maximize the benefits of these two technologies, especially considering the current inadequate charging infrastructure, long charging duration, higher energy usage, and tight delivery schedules for long-haul electric freight vehicles (EFVs). In this study, we aim to co-optimize the platooning and charging strategies of EFVs. To achieve this goal, we developed a mixed-integer linear programming model to minimize the total system costs, including en-route charging cost, delivery delay cost, and hub charging cost. The proposed model was tested using a case study of a 595-mile Florida interstate highway route and solved by the state-of-the-art branch-and-cut algorithms, through which we demonstrated the effectiveness of using our model to identify the optimal charging and platooning schedules and quantify the spatial distribution of charging demand and platoon energy savings. We also performed sensitivity analyses to better understand the impacts of some critical factors, including the EFV models, charging station (CS) capacity, number of CSs, charging speed, and departure-time windows. © 2022, The Authors. All rights reserved.

关键词： Scheduling

来源：评论

学校读者我要写书评

暂无评论

Organ-Specific Biotransformation in Salmonids: Insight into Intrinsic Enzyme Activity and Biotransformation of Three Micro-Pollutants

SSRN

引用

SSRN 2024年

作者： Franco, Marco E. Schönenberger, René Hollender, Juliane Schirmer, Kristin Department of Environmental Toxicology Swiss Federal Institute of Aquatic Science and Technology Eawag Dübendorf8600 Switzerland Department of Environmental Chemistry Swiss Federal Institute of Aquatic Science and Technology Eawag Dübendorf8600 Switzerland Department of Environmental Systems Science ETH Zürich Zürich8092 Switzerland School of Architecture Civil and Environmental Engineering EPF Lausanne Lausanne1015 Switzerland

Aquatic ecosystems continue to be threatened by chemical pollution. To what extent organisms are able to cope with chemical exposure depends on their ability to display mechanisms of defense across different organs. Among these mechanisms, biotransformation processes represent key physiological responses that facilitate detoxification and reduce the bioaccumulation potential of chemicals. Biotransformation does not only depend on the ability of different organs to display biotransformation enzymes but also on the affinity of chemicals towards these enzymes. In the present study, we explored the ability of different organs and of two freshwater fish to support biotransformation processes through the determination of in vitro phase I and II biotransformation enzyme activity, and their role in supporting intrinsic clearance and the formation of biotransformation products (BTPs). Three environmentally relevant pollutants were evaluated: the polycyclic aromatic hydrocarbon (PAH) pyrene (as recommended by the OECD 319b test guideline), the fungicide azoxystrobin, and the pharmaceutical propranolol. Comparative studies using S9 sub-cellular fractions derived from the liver, intestine, gills, and brain of brown trout (Salmo trutta) and rainbow trout (Oncorhynchus mykiss) revealed significant phase I and II enzyme activity in all organs. However, organ- and species-specific differences were found. In brown trout, significant extrahepatic biotransformation was observed for pyrene but not for azoxystrobin and propranolol. In rainbow trout, the brain appeared to biotransform azoxystrobin. In this same species, propranolol appeared to be biotransformed by the intestine and gills. BTPs could be detected only from hepatic biotransformation, and their profiles and formation rates displayed species-specific patterns and occurred at different magnitudes. Altogether, our findings further contribute to the current understanding of organ-specific biotransformation capacity, beyond the e

关键词： Fish

来源：评论

学校读者我要写书评

暂无评论

Model Predictive Control for Price-Based Demand-Responsive Building Control by Leveraging Active Latent Heat Storage

Model Predictive Control for Price-Based Demand-Responsive B...

引用

IEEE Conference on Decision and Control

作者： Shiyu Yang H. Oliver Gao Fengqi You Systems Engineering Cornell University Ithaca NY USA School of Civil and Environmental Engineering Cornell University Ithaca NY USA Robert Frederick Smith School of Chemical and Biomolecular Engineering Cornell University Ithaca NY USA

ISBN: (数字)9781665467612

ISBN: (纸本)9781665467629

Active latent heat storage (ALHS) involving phase-change materials constitutes a promising energy-efficient solution for building energy management (BEM). Current BEM systems based on conventional reactive control lack the level of control delicacy required to exploit the full potential of ALHS for BEM. This study proposes a smart model predictive control (MPC) approach for BEM to minimize energy costs while maintaining indoor climate by fully applying ALHS. An MPC framework considering ALHS dynamics and dynamic electricity prices is proposed. A case study entailing a set of simulations is designed based on a single-family house with a space heating system integrated with ALHS. The proposed MPC approach, compared to conventional reactive control, enables more than 70% of reductions in electricity costs. Further analysis reveals that coupling ALHS with MPC is critical to exploiting the ALHS potential for BEM: while conventional reactive control of an ALHS-equipped building increases the electricity cost, an MPC-enabled building could reduce the electricity cost by 45.1% due to ALHS adoption.

关键词： Couplings Electric potential Costs Aerospace electronics Energy efficiency Space heating Optimization

来源：评论

学校读者我要写书评

暂无评论

Graph Pyramid Autoformer for Long- Term Traffic Forecasting 22

Graph Pyramid Autoformer for Long- Term Traffic Forecasting

引用

22nd IEEE International Conference on Machine Learning and Applications, ICMLA 2023

作者： Zhong, Weiheng Mallick, Tanwi MacFarlane, Jane Meidani, Hadi Balaprakash, Prasanna University of Illinois at Urbana-Champaign Department of Civil Environmental Engineering ChampaignIL United States Mathematics and Computer Science Division Argonne National Laboratory LemontIL United States Sustainable Energy Systems Group Lawrence Berkeley National Laboratory BerkeleyCA United States Computing and Computational Sciences Directorate Oak Ridge National Laboratory Oak RidgeTN United States

ISBN: (纸本)9798350345346

Accurate traffic forecasting is vital to an intelligent transportation system. Although many deep learning models have achieved state-of-art performance for short-term traffic forecasting of up to 1 hour, long-term traffic forecasting that spans multiple hours remains a major challenge. To that end, we develop Graph Pyramid Autoformer (GPA), an attention-based spatial-temporal graph neural network that uses a novel pyramid autocorrelation attention mechanism. It enables learning from long temporal sequences on graphs and improves long-term traffic forecasting accuracy. We demonstrate the efficacy of the GPA using two benchmark traffic datasets: Los Angeles' METR-LA and the Bay Area's PEMS-BAY. Notably, our model has outperformed a range of existing state-of-the-art methods, delivering up to a 25 % improvement in the accuracy of long-term traffic forecasts. Our code is available at: https://***/WeiheneZlExplainable-Graph-Autoformer. © 2023 IEEE.

关键词： Graph Neural Network Long-term forecasting Pyramid Autocorrelation attention

来源：评论

学校读者我要写书评

暂无评论

Downscaled Satellite Estimates of Snow-Covered Areas Using Unoccupied Aerial systems (Uas) Lidar and Visible Imagery in Southeastern New Hampshire

SSRN

引用

SSRN 2024年

作者： Johnston, Jeremy M. Jacobs, Jennifer M. Hunsaker, Adam Wagner, Cameron Verfaillie, Megan Department of Civil and Environmental Engineering University of New Hampshire DurhamNH United States Earth Systems Research Center Institute for the Study of Earth Oceans and Space University of New Hampshire DurhamNH United States HanoverNH United States

Satellite remote sensing observations of snow-covered areas (SCA) are important for monitoring and modeling energy balances, hydrologic processes, and climate change. However, observations can be limited by cloud cover and have trade-offs between temporal and spatial resolutions. Unoccupied aerial systems (UAS) can provide higher-resolution snow cover maps on demand over moderate spatial scales ( © 2024, The Authors. All rights reserved.

关键词： Landsat

来源：评论

学校读者我要写书评

暂无评论

Bias Correction Methods for Generating Climate Data as Input to Hygrothermal Simulations 5th

Bias Correction Methods for Generating Climate Data as Input...

引用

5th International Conference on Building Energy and Environment, COBEE 2022

作者： Lu, Henry Gaur, Abhishek Ge, Hua Lacasse, Michael Façade Systems and Products Group Construction Research Centre National Research Council Canada 1200 Montreal Road OttawaK2J 6N4 Canada Department of Building Civil and Environmental Engineering Concordia University 1455 Boulevard de Maisonneuve O MontréalQCH3G 1M8 Canada

ISBN: (纸本)9789811998218

The objective of this research is to investigate the effects of different bias correction (BC) methods applied to climate data used to assess the hygrothermal performance on building envelopes based on simulations. To this end, a univariate and two multivariate distribution based bias correction methods were used to prepare weather files to assess the hygrothermal response of a wood frame wall assembly at the Ottawa International Airport. The effectiveness of the bias correction methods was evaluated by comparing the bias corrected climate data to observational data, as well as by comparing their hygrothermal responses as obtained through simulations. The bias correction improved upon the raw Regional Climate Model (RCM), which significantly overestimated the average annual rainfall, relative humidity (RH), and temperature, whilst underestimating the wind-driven rain (WDR). Despite improvements made to the climate data through bias correction, performance indicators such as the moisture content (MC), mould index (MI), and RH on the exterior of the OSB had a diverse response to the climatic conditions. Generally, multivariate BC methods are seen to perform marginally better than the univariate method in this context. However, BC was not able to produce the same time series of climate variables, which have a significant impact on the wetting and drying conditions, and consequently the risk to mould growth in wood frame wall assemblies. © 2023, The Author(s), under exclusive license to Springer Nature Singapore Pte Ltd.

关键词： Rain

来源：评论

学校读者我要写书评

暂无评论

Learning Eco-Driving Strategies at Signalized Intersections

arXiv

引用

arXiv 2022年

作者： Jayawardana, Vindula Wu, Cathy MIT Laboratory for Information & Decision Systems Department of Electrical Engineering and Computer Science CambridgeMA02139 United States Laboratory for Information & Decision Systems Department of Civil and Environmental Engineering Institute of Data Systems and Society CambridgeMA02139 United States

Signalized intersections in arterial roads result in persistent vehicle idling and excess accelerations, contributing to fuel consumption and CO2 emissions. There has thus been a line of work studying eco-driving control strategies to reduce fuel consumption and emission levels at intersections. However, methods to devise effective control strategies across a variety of traffic settings remain elusive. In this paper, we propose a reinforcement learning (RL) approach to learn effective eco-driving control strategies. We analyze the potential impact of a learned strategy on fuel consumption, CO2 emission, and travel time and compare with naturalistic driving and model-based baselines. We further demonstrate the generalizability of the learned policies under mixed traffic scenarios. Simulation results indicate that scenarios with 100% penetration of connected autonomous vehicles (CAV) may yield as high as 18% reduction in fuel consumption and 25% reduction in CO2 emission levels while even improving travel speed by 20%. Furthermore, results indicate that even 25% CAV penetration can bring at least 50% of the total fuel and emission reduction benefits. Copyright © 2022, The Authors. All rights reserved.

关键词： Travel time

来源：评论

学校读者我要写书评

暂无评论

Modelling future changes in social vulnerability and bushfire risk 24

Modelling future changes in social vulnerability and bushfir...

引用

24th International Congress on Modelling and Simulation, MODSIM 2021

作者： Moore, E. Zhar, Y. Radford, P. O'Callaghan, M. Maier, H.R. Riddell, G. van Delden, H. Wouters, M. School of Civil Environmental & Mining Engineering University of Adelaide AdelaideSA Australia Research Institute for Knowledge Systems Maastricht Netherlands South Australian Department for Environment and Water AdelaideSA Australia

ISBN: (纸本)9780987214393

A natural hazard becomes a natural disaster when individuals, communities and infrastructure are impacted. The impact of a natural disaster is a function of the type and magnitude of the hazard, and the vulnerability of the people and assets exposed to the hazard. Consequently, bushfire risk is not only a function of bushfire likelihood and intensity, but also the social vulnerability of affected communities. In this paper, a framework is presented that enables the spatial distribution of bushfire risk to be quantified by considering bushfire likelihood and social vulnerability. The framework also caters to the assessment of how this risk could change into the future in response to climate change and socio-economic development. The framework is applied to the case study of Greater Adelaide, South Australia. The current distribution of social vulnerability is calculated based on a number of indicators and the current distribution of bushfire likelihood determined using the Unified Natural Hazard Risk Mitigation Exploratory Decision Support System (UNHaRMED), enabling the spatial distribution of current bushfire risk to be determined based on social vulnerability. Plausible spatial distributions of future bushfire risk based on social vulnerability are obtained in response to a number of climate and socio-economic exploratory scenarios. The impact of climate change scenarios on bushfire likelihood is quantified with UNHaRMED. The impact of the socio-economic scenarios on social vulnerability is quantified using a combination of changes in the distribution of land use and population with the aid of UNHaRMED, as well as "clues" in the narrative scenario storylines about likely changes in factors affecting social vulnerability. The results indicate that future changes in social vulnerability are likely to affect long-term bushfire risk in greater Adelaide, with spatial distributions of social vulnerability and bushfire risk changing in different ways under different plau

关键词： Risk perception

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：