The response and failure of brass H62 specimens subjected to different levels of pre-loaded stresses and heating rates were investigated using a Gleeble-1500 thermal-mechanical material testing system. The metallograp...The response and failure of brass H62 specimens subjected to different levels of pre-loaded stresses and heating rates were investigated using a Gleeble-1500 thermal-mechanical material testing system. The metallographs of the tested material were also observed and analyzed. It is found that the increase of either pre-loaded stress or heating-rate decreases the failure temperature. Metallographic analysis shows that high heating-rate may cause stronger local thermal inconsistency(LTI) and remarkably increase the microdefects in the material,which may markedly degrade the macroscopic mechanical properties of the material.展开更多
文章以建筑中可再生能源系统为研究对象,利用长短期记忆(Long Short-Term Memory,LSTM)神经网络建立变频太阳能-空气源热泵(Variable Frequency Solar Air Source Heat Pump,VFAP)系统,在乌鲁木齐市气象条件下选取一个6层办公楼进行分...文章以建筑中可再生能源系统为研究对象,利用长短期记忆(Long Short-Term Memory,LSTM)神经网络建立变频太阳能-空气源热泵(Variable Frequency Solar Air Source Heat Pump,VFAP)系统,在乌鲁木齐市气象条件下选取一个6层办公楼进行分析。首先,在实测数据校验模型的基础上,基于TRNSYS软件搭建VFAP系统,以一个供暖季为研究周期,获取VFAP系统的室外参数和过程运行数据。其次,利用灰色关联度分析(Grey Relation Analysis,GRA)计算各特征与供暖负荷的灰色关联度,并利用局部保留投影算法(Locality Preserving Projection,LPP)进行数据降维,得到VFAP系统的最优预测向量。最后,通过选择合理的网络参数,提出基于LSTM神经网络的VFAP系统的短期负荷预测模型,并与现有预测模型相对比。结果表明,LSTM神经网络对VFAP系统的负荷预测具有较好的识别效果,该精度要优于传统的神经网络预测模型,具有潜在的应用价值。展开更多
基金Projects (10572157, 10272119) supported by the National Natural Science Foundation of China
文摘The response and failure of brass H62 specimens subjected to different levels of pre-loaded stresses and heating rates were investigated using a Gleeble-1500 thermal-mechanical material testing system. The metallographs of the tested material were also observed and analyzed. It is found that the increase of either pre-loaded stress or heating-rate decreases the failure temperature. Metallographic analysis shows that high heating-rate may cause stronger local thermal inconsistency(LTI) and remarkably increase the microdefects in the material,which may markedly degrade the macroscopic mechanical properties of the material.
文摘文章以建筑中可再生能源系统为研究对象,利用长短期记忆(Long Short-Term Memory,LSTM)神经网络建立变频太阳能-空气源热泵(Variable Frequency Solar Air Source Heat Pump,VFAP)系统,在乌鲁木齐市气象条件下选取一个6层办公楼进行分析。首先,在实测数据校验模型的基础上,基于TRNSYS软件搭建VFAP系统,以一个供暖季为研究周期,获取VFAP系统的室外参数和过程运行数据。其次,利用灰色关联度分析(Grey Relation Analysis,GRA)计算各特征与供暖负荷的灰色关联度,并利用局部保留投影算法(Locality Preserving Projection,LPP)进行数据降维,得到VFAP系统的最优预测向量。最后,通过选择合理的网络参数,提出基于LSTM神经网络的VFAP系统的短期负荷预测模型,并与现有预测模型相对比。结果表明,LSTM神经网络对VFAP系统的负荷预测具有较好的识别效果,该精度要优于传统的神经网络预测模型,具有潜在的应用价值。
