Heat transfers at the interface of adjacent saturated soil primarily through the soil particles and the water in the voids.The presence of water induces the contraction of heat flow lines at the interface,leading to t...Heat transfers at the interface of adjacent saturated soil primarily through the soil particles and the water in the voids.The presence of water induces the contraction of heat flow lines at the interface,leading to the emergence of the thermal contact resistance effect.In this paper,four thermal contact models were developed to predict the thermal contact resistance at the interface of multilayered saturated soils.Based on the theory of thermal-hydro-mechanical coupling,semi-analytical solutions of thermal consolidation subjected to time-dependent heating and loading were obtained by employing Laplace transform and its inverse transformation.Thermal consolidation characteristics of multilayered saturated soils under four different thermal contact models were discussed,and the effects of thermal resistance coefficient,partition thermal contact coefficient,and temperature amplitude on the thermal consolidation process were investigated.The outcomes indicate that the general thermal contact model results in the most pronounced thermal gradient at the interface,which can be degenerated to the other three thermal contact models.The perfect thermal contact model overestimates the deformation of the saturated soil during the thermal consolidation.Moreover,the effect of temperature on consolidation properties decreases gradually with increasing interfacial contact thermal resistance.展开更多
智能电网的发展认识到短期电力净负荷预测对综合能源系统(integrated energy system,IES)的重要性。净负荷预测代表用电负荷与安装的可再生能源之间的差异,是能量管理和优化调度的基础。为解决IES波动性大,传统统计模型预测精较差的问题...智能电网的发展认识到短期电力净负荷预测对综合能源系统(integrated energy system,IES)的重要性。净负荷预测代表用电负荷与安装的可再生能源之间的差异,是能量管理和优化调度的基础。为解决IES波动性大,传统统计模型预测精较差的问题,该文提出一种基于时空图卷积网络(spatial temporal graph convolutional networks,STGCN)和Transformer相结合的综合能源系统短期负荷预测模型。首先,利用STGCN作为输入嵌入层对多元输入序列进行编码,填补Transformer中没有充分考虑相关信息的空白。然后,利用Transformer中的自注意机制捕获序列数据的时间依赖性。最后,利用前馈神经网络输出预测负荷值。以浙江省某地区电力数据集为例,与其他4种预测模型相比较平均绝对百分比误差均在5%以内,结果表明该文模型具有较高的预测精度和稳定性。展开更多
At present, an automatic-mechanic contact tap-changer is widely used in power system, but it can not frequently operate. In addition, arc will occur when the switch changes. In order to solve these two problems, this ...At present, an automatic-mechanic contact tap-changer is widely used in power system, but it can not frequently operate. In addition, arc will occur when the switch changes. In order to solve these two problems, this paper presented an automatic on-load voltage-regulating distributing transformer which employed non-contact solid-state relay as tap-changer, and mainly introduced its structure, basic principal, design method of each key link and experimental results. Laboratory simulation experiments informed that the scheme was feasible. It was a smooth and effective experiment device, which was practical in application.展开更多
建设智能教育平台是推动教育智能化的一个重要过程,但智能教育平台依赖的人工智能模型在训练过程中会消耗大量电力,因此,开展短期电力负荷预测对建设智能教育平台具有重要意义.针对在考虑多个属性开展短期电力负荷预测时,由于部分属性...建设智能教育平台是推动教育智能化的一个重要过程,但智能教育平台依赖的人工智能模型在训练过程中会消耗大量电力,因此,开展短期电力负荷预测对建设智能教育平台具有重要意义.针对在考虑多个属性开展短期电力负荷预测时,由于部分属性与电力负荷数据的相关性不强并且Transformer无法捕捉电力负荷数据的时间相关性,而导致电力负荷预测不够准确的问题,基于SR(Székely and Rizzo)距离相关系数、融合时间定位编码和Transformer,提出了一种短期电力负荷预测模型SF-Transformer.SF-Transformer通过SR距离相关系数对影响电力负荷数据的属性进行筛选,选择与电力负荷数据之间SR距离相关系数较大的属性.SF-Transformer采用一种全局时间编码与局部位置编码相结合的融合时间定位编码,有助于模型全面获取电力负荷数据的时间定位信息.在数据集上开展了实验,实验结果表明SF-Transformer与其他模型相比,在两种时长上进行电力负荷预测具有更低的均方根误差和平均绝对误差.展开更多
基于数据驱动的方法已广泛应用于电力负荷预测领域,以提升预测精度。然而,当售电公司接入新用户时,由于缺乏用户历史用电数据,常规数据驱动方法的适用性会受到一定限制。为解决这一问题,文章提出了一种基于域对抗迁移网络(domain advers...基于数据驱动的方法已广泛应用于电力负荷预测领域,以提升预测精度。然而,当售电公司接入新用户时,由于缺乏用户历史用电数据,常规数据驱动方法的适用性会受到一定限制。为解决这一问题,文章提出了一种基于域对抗迁移网络(domain adversarial transfer network,DATN)的短期电力负荷预测方法。该模型利用Transformer模型作为特征提取器,以捕捉负荷数据中的动态特征和时间依赖性。随后,负荷预测器基于这些特征精准预测未来的负荷情况。通过域判别器与特征提取器的对抗学习,确保模型能够学习到深层域不变特征,同时结合多核最大均值差异(multi-kernel maximum mean discrepancy,MK-MMD)和相关性对齐(correlation alignment,CORAL)进一步减小源域与目标域数据的分布差异。所提模型在南方某省工业用户的用电数据上进行了验证,实验结果表明,在小样本场景下,该方法具备较好的预测精度和场景适应性。展开更多
基金Projects(U24B20113,42477162) supported by the National Natural Science Foundation of ChinaProject(2025C02228) supported by the Primary Research and Development Plan of Zhejiang Province,China。
文摘Heat transfers at the interface of adjacent saturated soil primarily through the soil particles and the water in the voids.The presence of water induces the contraction of heat flow lines at the interface,leading to the emergence of the thermal contact resistance effect.In this paper,four thermal contact models were developed to predict the thermal contact resistance at the interface of multilayered saturated soils.Based on the theory of thermal-hydro-mechanical coupling,semi-analytical solutions of thermal consolidation subjected to time-dependent heating and loading were obtained by employing Laplace transform and its inverse transformation.Thermal consolidation characteristics of multilayered saturated soils under four different thermal contact models were discussed,and the effects of thermal resistance coefficient,partition thermal contact coefficient,and temperature amplitude on the thermal consolidation process were investigated.The outcomes indicate that the general thermal contact model results in the most pronounced thermal gradient at the interface,which can be degenerated to the other three thermal contact models.The perfect thermal contact model overestimates the deformation of the saturated soil during the thermal consolidation.Moreover,the effect of temperature on consolidation properties decreases gradually with increasing interfacial contact thermal resistance.
文摘At present, an automatic-mechanic contact tap-changer is widely used in power system, but it can not frequently operate. In addition, arc will occur when the switch changes. In order to solve these two problems, this paper presented an automatic on-load voltage-regulating distributing transformer which employed non-contact solid-state relay as tap-changer, and mainly introduced its structure, basic principal, design method of each key link and experimental results. Laboratory simulation experiments informed that the scheme was feasible. It was a smooth and effective experiment device, which was practical in application.
文摘建设智能教育平台是推动教育智能化的一个重要过程,但智能教育平台依赖的人工智能模型在训练过程中会消耗大量电力,因此,开展短期电力负荷预测对建设智能教育平台具有重要意义.针对在考虑多个属性开展短期电力负荷预测时,由于部分属性与电力负荷数据的相关性不强并且Transformer无法捕捉电力负荷数据的时间相关性,而导致电力负荷预测不够准确的问题,基于SR(Székely and Rizzo)距离相关系数、融合时间定位编码和Transformer,提出了一种短期电力负荷预测模型SF-Transformer.SF-Transformer通过SR距离相关系数对影响电力负荷数据的属性进行筛选,选择与电力负荷数据之间SR距离相关系数较大的属性.SF-Transformer采用一种全局时间编码与局部位置编码相结合的融合时间定位编码,有助于模型全面获取电力负荷数据的时间定位信息.在数据集上开展了实验,实验结果表明SF-Transformer与其他模型相比,在两种时长上进行电力负荷预测具有更低的均方根误差和平均绝对误差.
文摘基于数据驱动的方法已广泛应用于电力负荷预测领域,以提升预测精度。然而,当售电公司接入新用户时,由于缺乏用户历史用电数据,常规数据驱动方法的适用性会受到一定限制。为解决这一问题,文章提出了一种基于域对抗迁移网络(domain adversarial transfer network,DATN)的短期电力负荷预测方法。该模型利用Transformer模型作为特征提取器,以捕捉负荷数据中的动态特征和时间依赖性。随后,负荷预测器基于这些特征精准预测未来的负荷情况。通过域判别器与特征提取器的对抗学习,确保模型能够学习到深层域不变特征,同时结合多核最大均值差异(multi-kernel maximum mean discrepancy,MK-MMD)和相关性对齐(correlation alignment,CORAL)进一步减小源域与目标域数据的分布差异。所提模型在南方某省工业用户的用电数据上进行了验证,实验结果表明,在小样本场景下,该方法具备较好的预测精度和场景适应性。
