Faulty-feeder detection in neutral point noneffectively grounded distribution networks consistently attracts research attention since it directly affects quality and safety of energy supply.Most modern research on fau...Faulty-feeder detection in neutral point noneffectively grounded distribution networks consistently attracts research attention since it directly affects quality and safety of energy supply.Most modern research on faulty-feeder detection tends to apply more complex digital signal processing techniques and deeper neural networks in order to better extract and learn as many detailed characteristics as possible.However,these approaches may easily result in overfitting and high computational cost,which cannot meet requirements for detection accuracy and efficiency in practical applications.This paper proposes an innovative waveform encoding method and details a simple convolutional neural network(CNN)with one layer of convolution used for identification,which seeks to improve detection accuracy and efficiency simultaneously.First,sparse characteristics of waveforms are utilized to encode into compact vectors,and a waveform-vector matrix is generated.Second,to deduce waveform-vector matrix,a simple CNN with multi-scale filters and one layer of convolution is established.Finally,a methodology for faulty-feeder detection is proposed,and both detection accuracy and efficiency are considerably enhanced.Comparative studies have confirmed clear superiority of the developed method,which outperforms existing approaches in both detection accuracy and efficiency,thus highlighting its significant potential for application.展开更多
This paper introduces a novel method for medical image retrieval and classification by integrating a multi-scale encoding mechanism with Vision Transformer(ViT)architectures and a dynamic multi-loss function.The multi...This paper introduces a novel method for medical image retrieval and classification by integrating a multi-scale encoding mechanism with Vision Transformer(ViT)architectures and a dynamic multi-loss function.The multi-scale encoding significantly enhances the model’s ability to capture both fine-grained and global features,while the dynamic loss function adapts during training to optimize classification accuracy and retrieval performance.Our approach was evaluated on the ISIC-2018 and ChestX-ray14 datasets,yielding notable improvements.Specifically,on the ISIC-2018 dataset,our method achieves an F1-Score improvement of+4.84% compared to the standard ViT,with a precision increase of+5.46% for melanoma(MEL).On the ChestX-ray14 dataset,the method delivers an F1-Score improvement of 5.3%over the conventional ViT,with precision gains of+5.0% for pneumonia(PNEU)and+5.4%for fibrosis(FIB).Experimental results demonstrate that our approach outperforms traditional CNN-based models and existing ViT variants,particularly in retrieving relevant medical cases and enhancing diagnostic accuracy.These findings highlight the potential of the proposedmethod for large-scalemedical image analysis,offering improved tools for clinical decision-making through superior classification and case comparison.展开更多
This paper examines the changes in the time series of water discharge and sediment load of the Yellow River into the Bohai Sea. To determine the characteristics of abrupt changes and multi-scale periods of water disch...This paper examines the changes in the time series of water discharge and sediment load of the Yellow River into the Bohai Sea. To determine the characteristics of abrupt changes and multi-scale periods of water discharge and sediment load, data from Lijin station were analyzed, and the resonance periods were then calculated. The Mann-Kendall test, order clustering, power-spectrum, and wavelet analysis were used to observe water discharge and sediment load into the sea over the last 62 years. The most significant abrupt change in water discharge into the sea occurred in 1985, and an abrupt change in sediment load happened in the same year. Significant decreases of 64.6% and 73.8% were observed in water discharge and sediment load, respectively, before 1985. More significant abrupt changes in water discharge and sediment load were observed in 1968 and 1996. The characteristics of water discharge and sediment load into the Bohai Sea show periodic oscillation at inter-annual and decadal scales. The main periods of water discharge are 9.14 years and 3.05 years, whereas the main periods of sediment load are 10.67 years, 4.27 years, and 2.78 years. The significant resonance periods between water discharge and sediment load are observed at the following temporal scales： 2.86 years, 4.44 years, and 13.33 years. Water discharge and sediment load started to decrease after 1970 and has decreased significantly since 1985 for several reasons. Firstly, the precipitation of the Yellow River drainage area has reduced since 1970. Secondly, large-scale human activities, such as the building of reservoirs and floodgates, have increased. Thirdly, water and soil conservation have taken effect since 1985.展开更多
The specific good properties of cellular materials and composite materials, such as low density and high permeability, make the optimal design of such materials necessary and at- tractive. However, the given materials...The specific good properties of cellular materials and composite materials, such as low density and high permeability, make the optimal design of such materials necessary and at- tractive. However, the given materials for the structures may not be optimal or suitable, since the boundary condition and applied loads vary in practical applications; hence the macro-structure and its material micro-structure should be considered simultaneously. Although abundant studies have been reported on the structural and material optimization at each level, very few of them considered the mutual coordination on both scales. In this paper, two FE models are built for the macro-structure and the micro-structure, respectively; and the effective elastic properties of the periodic micro-structure are blended into the analysis of macro-structure by the homogenization theory. Here, a topological optimum is obtained by gradually re-distributing the constituents within the micro-structure and updating the topological shape at the macro-structure until converges are achieved on both scales. The mutual coordination between the roles of micro-scale and macro-scale is considered. Some numerical examples are presented, which illustrate that the proposed optimization algorithm is effective and highly efficient for the micro-structure design and macro-structure optimization. For the composite design, one can see reasonable effects of the stiffness of base materials on the resultant topologies.展开更多
针对基于FPGA/ASIC的全数字硬件化实现时存在内部参数界确定以及字长选取等问题,通过分析离散周期对全数字硬件化实现的影响机理,得到离散周期对全数字硬件化系统的稳定性以及动态性能指标的影响规律。建立角度解算单元的连续域模型,并...针对基于FPGA/ASIC的全数字硬件化实现时存在内部参数界确定以及字长选取等问题,通过分析离散周期对全数字硬件化实现的影响机理,得到离散周期对全数字硬件化系统的稳定性以及动态性能指标的影响规律。建立角度解算单元的连续域模型,并对稳定性进行分析;利用delta算子进行离散化,对比分析了有无反馈滞后一拍的离散角度解算单元的稳定性,得到包含离散周期信息的系数取值范围;以衰减度为满意控制指标,求得了满足性能指标的最大离散周期。分析结果表明,全数字硬件化实现全闭环数字算法时所存在的反馈滞后一拍会使K p T<2,从而使实际系统的稳定性降低。通过求取最大离散周期,能够平衡系统性能与数字实现代价之间的矛盾关系,为控制器参数设计提供理论依据。实验结果验证了理论分析的正确性。展开更多
文摘Faulty-feeder detection in neutral point noneffectively grounded distribution networks consistently attracts research attention since it directly affects quality and safety of energy supply.Most modern research on faulty-feeder detection tends to apply more complex digital signal processing techniques and deeper neural networks in order to better extract and learn as many detailed characteristics as possible.However,these approaches may easily result in overfitting and high computational cost,which cannot meet requirements for detection accuracy and efficiency in practical applications.This paper proposes an innovative waveform encoding method and details a simple convolutional neural network(CNN)with one layer of convolution used for identification,which seeks to improve detection accuracy and efficiency simultaneously.First,sparse characteristics of waveforms are utilized to encode into compact vectors,and a waveform-vector matrix is generated.Second,to deduce waveform-vector matrix,a simple CNN with multi-scale filters and one layer of convolution is established.Finally,a methodology for faulty-feeder detection is proposed,and both detection accuracy and efficiency are considerably enhanced.Comparative studies have confirmed clear superiority of the developed method,which outperforms existing approaches in both detection accuracy and efficiency,thus highlighting its significant potential for application.
基金funded by the Deanship of Research and Graduate Studies at King Khalid University through small group research under grant number RGP1/278/45.
文摘This paper introduces a novel method for medical image retrieval and classification by integrating a multi-scale encoding mechanism with Vision Transformer(ViT)architectures and a dynamic multi-loss function.The multi-scale encoding significantly enhances the model’s ability to capture both fine-grained and global features,while the dynamic loss function adapts during training to optimize classification accuracy and retrieval performance.Our approach was evaluated on the ISIC-2018 and ChestX-ray14 datasets,yielding notable improvements.Specifically,on the ISIC-2018 dataset,our method achieves an F1-Score improvement of+4.84% compared to the standard ViT,with a precision increase of+5.46% for melanoma(MEL).On the ChestX-ray14 dataset,the method delivers an F1-Score improvement of 5.3%over the conventional ViT,with precision gains of+5.0% for pneumonia(PNEU)and+5.4%for fibrosis(FIB).Experimental results demonstrate that our approach outperforms traditional CNN-based models and existing ViT variants,particularly in retrieving relevant medical cases and enhancing diagnostic accuracy.These findings highlight the potential of the proposedmethod for large-scalemedical image analysis,offering improved tools for clinical decision-making through superior classification and case comparison.
基金National Natural Science Foundation of China, No.41271026
文摘This paper examines the changes in the time series of water discharge and sediment load of the Yellow River into the Bohai Sea. To determine the characteristics of abrupt changes and multi-scale periods of water discharge and sediment load, data from Lijin station were analyzed, and the resonance periods were then calculated. The Mann-Kendall test, order clustering, power-spectrum, and wavelet analysis were used to observe water discharge and sediment load into the sea over the last 62 years. The most significant abrupt change in water discharge into the sea occurred in 1985, and an abrupt change in sediment load happened in the same year. Significant decreases of 64.6% and 73.8% were observed in water discharge and sediment load, respectively, before 1985. More significant abrupt changes in water discharge and sediment load were observed in 1968 and 1996. The characteristics of water discharge and sediment load into the Bohai Sea show periodic oscillation at inter-annual and decadal scales. The main periods of water discharge are 9.14 years and 3.05 years, whereas the main periods of sediment load are 10.67 years, 4.27 years, and 2.78 years. The significant resonance periods between water discharge and sediment load are observed at the following temporal scales： 2.86 years, 4.44 years, and 13.33 years. Water discharge and sediment load started to decrease after 1970 and has decreased significantly since 1985 for several reasons. Firstly, the precipitation of the Yellow River drainage area has reduced since 1970. Secondly, large-scale human activities, such as the building of reservoirs and floodgates, have increased. Thirdly, water and soil conservation have taken effect since 1985.
基金supported by the Science Funds from Educational Commission of Yunnan Province,China(No.2016zzx005)
文摘The specific good properties of cellular materials and composite materials, such as low density and high permeability, make the optimal design of such materials necessary and at- tractive. However, the given materials for the structures may not be optimal or suitable, since the boundary condition and applied loads vary in practical applications; hence the macro-structure and its material micro-structure should be considered simultaneously. Although abundant studies have been reported on the structural and material optimization at each level, very few of them considered the mutual coordination on both scales. In this paper, two FE models are built for the macro-structure and the micro-structure, respectively; and the effective elastic properties of the periodic micro-structure are blended into the analysis of macro-structure by the homogenization theory. Here, a topological optimum is obtained by gradually re-distributing the constituents within the micro-structure and updating the topological shape at the macro-structure until converges are achieved on both scales. The mutual coordination between the roles of micro-scale and macro-scale is considered. Some numerical examples are presented, which illustrate that the proposed optimization algorithm is effective and highly efficient for the micro-structure design and macro-structure optimization. For the composite design, one can see reasonable effects of the stiffness of base materials on the resultant topologies.
文摘针对基于FPGA/ASIC的全数字硬件化实现时存在内部参数界确定以及字长选取等问题,通过分析离散周期对全数字硬件化实现的影响机理,得到离散周期对全数字硬件化系统的稳定性以及动态性能指标的影响规律。建立角度解算单元的连续域模型,并对稳定性进行分析;利用delta算子进行离散化,对比分析了有无反馈滞后一拍的离散角度解算单元的稳定性,得到包含离散周期信息的系数取值范围;以衰减度为满意控制指标,求得了满足性能指标的最大离散周期。分析结果表明,全数字硬件化实现全闭环数字算法时所存在的反馈滞后一拍会使K p T<2,从而使实际系统的稳定性降低。通过求取最大离散周期,能够平衡系统性能与数字实现代价之间的矛盾关系,为控制器参数设计提供理论依据。实验结果验证了理论分析的正确性。
