To analyze the bending properties of GCr15 steel guide rail based on the elastic-plastic theory, the novel bending loading method consisting of multi-step loading and corresponding unloading was applied in three speci...To analyze the bending properties of GCr15 steel guide rail based on the elastic-plastic theory, the novel bending loading method consisting of multi-step loading and corresponding unloading was applied in three specimens with different cross section shape and different heat treatment condition. According to the experimental results, using numerical calculation software program and the numerical simulation with finite element analysis （FEA）, the relationships among the maximal load and displacement on cross section shape with each step bend loading, the loading stroke with the heat treatment condition, and the loading stroke with cross section shape were gained, and also those curves were discussed qualitatively. Finally, the contrast results between the numerical simulation and experiment were carried out to study the influence about the multi-step loading on specimen. It is put forward that enlightenment for the straightening stroke in the precision linear guide rail manufacture process.展开更多
Management and efficient operations in critical infrastructures such as smart grids take huge advantage of accurate power load forecasting,which,due to its non-linear nature,remains a challenging task.Recently,deep le...Management and efficient operations in critical infrastructures such as smart grids take huge advantage of accurate power load forecasting,which,due to its non-linear nature,remains a challenging task.Recently,deep learning has emerged in the machine learning field achieving impressive performance in a vast range of tasks,from image classification to machine translation.Applications of deep learning models to the electric load forecasting problem are gaining interest among researchers as well as the industry,but a comprehensive and sound comparison among different-also traditional-architectures is not yet available in the literature.This work aims at filling the gap by reviewing and experimentally evaluating four real world datasets on the most recent trends in electric load forecasting,by contrasting deep learning architectures on short-term forecast(oneday-ahead prediction).Specifically,the focus is on feedforward and recurrent neural networks,sequence-to-sequence models and temporal convolutional neural networks along with architectural variants,which are known in the signal processing community but are novel to the load forecasting one.展开更多
The role of heating load forecasts in the energy transition is significant,given the considerable increase in the number of heat pumps and the growing prevalence of fluctuating electricity generation.While machine lea...The role of heating load forecasts in the energy transition is significant,given the considerable increase in the number of heat pumps and the growing prevalence of fluctuating electricity generation.While machine learning methods offer promising forecasting capabilities,their black-box nature makes them difficult to interpret and explain.The deployment of explainable artificial intelligence methodologies enables the actions of these machine learning models to be made transparent.In this study,a multi-step forecast was employed using an Encoder–Decoder model to forecast the hourly heating load for an multifamily residential building and a district heating system over a forecast horizon of 24-h.By using 24 instead of 48 lagged hours,the simulation time was reduced from 92.75 s to 45.80 s and the forecast accuracy was increased.The feature selection was conducted for four distinct methods.The Tree and Deep SHAP method yielded superior results in feature selection.The application of feature selection according to the Deep SHAP values resulted in a reduction of 3.98%in the training time and a 8.11%reduction in the NRMSE.The utilisation of local Deep SHAP values enables the visualisation of the influence of past input hours and individual features.By mapping temporal attention,it was possible to demonstrate the importance of the most recent time steps in a intrinsic way.The combination of explainable methods enables plant operators to gain further insights and trustworthiness from the purely data-driven forecast model,and to identify the importance of individual features and time steps.展开更多
近年来,由于Web缓存技术对缓解因特网上热点现象的有效性,它已迅速得到了研究人员和业界的关注。适应性Web缓存(adaptive Web caching)由于能够根据用户的不同访问模式,自适应地调整热点数据在缓存系统中的分布,自动均衡整个缓存系统的...近年来,由于Web缓存技术对缓解因特网上热点现象的有效性,它已迅速得到了研究人员和业界的关注。适应性Web缓存(adaptive Web caching)由于能够根据用户的不同访问模式,自适应地调整热点数据在缓存系统中的分布,自动均衡整个缓存系统的负载,因而成为了缓存技术研究的一个新的热点。本文介绍了适应性Web缓存领域的研究状况,详细分析了基于组播和基于单播这两种主要的适应性缓存技术。最后,指出了适应性Web缓存研究存在的问题和值得进一步改进的方向。展开更多
基金Funded by the Open Research Foundation of State Key Lab of Digital Manufacturing Equipment & Technology in Huazhong University of Science & Technology (No. DMETKF2009016)the Hubei Province Science Founda-tion (No.2008CDB274)+1 种基金the Wuhan High-Tech Development Project Founda-tion (No.200812121559)the International Collaborative Research Funds of Chonbuk National University, 2008
文摘To analyze the bending properties of GCr15 steel guide rail based on the elastic-plastic theory, the novel bending loading method consisting of multi-step loading and corresponding unloading was applied in three specimens with different cross section shape and different heat treatment condition. According to the experimental results, using numerical calculation software program and the numerical simulation with finite element analysis （FEA）, the relationships among the maximal load and displacement on cross section shape with each step bend loading, the loading stroke with the heat treatment condition, and the loading stroke with cross section shape were gained, and also those curves were discussed qualitatively. Finally, the contrast results between the numerical simulation and experiment were carried out to study the influence about the multi-step loading on specimen. It is put forward that enlightenment for the straightening stroke in the precision linear guide rail manufacture process.
基金Innosuisse-Schweizerische Agentur für Innovationsförderung,Grant/Award Number:1155002544。
文摘Management and efficient operations in critical infrastructures such as smart grids take huge advantage of accurate power load forecasting,which,due to its non-linear nature,remains a challenging task.Recently,deep learning has emerged in the machine learning field achieving impressive performance in a vast range of tasks,from image classification to machine translation.Applications of deep learning models to the electric load forecasting problem are gaining interest among researchers as well as the industry,but a comprehensive and sound comparison among different-also traditional-architectures is not yet available in the literature.This work aims at filling the gap by reviewing and experimentally evaluating four real world datasets on the most recent trends in electric load forecasting,by contrasting deep learning architectures on short-term forecast(oneday-ahead prediction).Specifically,the focus is on feedforward and recurrent neural networks,sequence-to-sequence models and temporal convolutional neural networks along with architectural variants,which are known in the signal processing community but are novel to the load forecasting one.
基金the German Federal Ministry for Economic Affairs and Climate Action in the framework of the research program EnOB:ML-EBESR 03EN1076B.
文摘The role of heating load forecasts in the energy transition is significant,given the considerable increase in the number of heat pumps and the growing prevalence of fluctuating electricity generation.While machine learning methods offer promising forecasting capabilities,their black-box nature makes them difficult to interpret and explain.The deployment of explainable artificial intelligence methodologies enables the actions of these machine learning models to be made transparent.In this study,a multi-step forecast was employed using an Encoder–Decoder model to forecast the hourly heating load for an multifamily residential building and a district heating system over a forecast horizon of 24-h.By using 24 instead of 48 lagged hours,the simulation time was reduced from 92.75 s to 45.80 s and the forecast accuracy was increased.The feature selection was conducted for four distinct methods.The Tree and Deep SHAP method yielded superior results in feature selection.The application of feature selection according to the Deep SHAP values resulted in a reduction of 3.98%in the training time and a 8.11%reduction in the NRMSE.The utilisation of local Deep SHAP values enables the visualisation of the influence of past input hours and individual features.By mapping temporal attention,it was possible to demonstrate the importance of the most recent time steps in a intrinsic way.The combination of explainable methods enables plant operators to gain further insights and trustworthiness from the purely data-driven forecast model,and to identify the importance of individual features and time steps.
文摘近年来,由于Web缓存技术对缓解因特网上热点现象的有效性,它已迅速得到了研究人员和业界的关注。适应性Web缓存(adaptive Web caching)由于能够根据用户的不同访问模式,自适应地调整热点数据在缓存系统中的分布,自动均衡整个缓存系统的负载,因而成为了缓存技术研究的一个新的热点。本文介绍了适应性Web缓存领域的研究状况,详细分析了基于组播和基于单播这两种主要的适应性缓存技术。最后,指出了适应性Web缓存研究存在的问题和值得进一步改进的方向。
