|
|
|
题名
|
作者
|
年代
|
出处
|
被引量
|
| 1 | Balancing BEC and IAQ in civil buildings during rapid urbanization in China : Regulation, interplay and collaboration显示文摘 | Zhang Jiefeng Bai Zhipeng Chang Victor W C | 2011 | Energy Policy2011，39，10： | 1 |
| 2 | The developments and challenges of cerium half-cell in zinc–cerium redox flow battery for energy storage显示文摘 | Zhipeng Xie Qingchao Liu Zhiwen Chang Xinbo Zhang | 2012 | Electrochimica Acta2012，，： | 1 |
| 3 | Dosimetric properties of a commercial PTW 60019 synthetic diamond detector in small photon fields显示文摘 | Chang Xue Wang Kun Zhang Jian Wang Zhipeng Jin Sunjun | 2018 | 中华放射医学与防护杂志2018，38，2： | 1 |
| 4 | Spatial Distribution of Different Types of Villages for Rural Revitalization Strategy and Their Influencing Factors:A Case of Jilin Province,China显示文摘Village classification is the first step to implementing China’s rural revitalization(RR)strategy,and understanding the geographic differences in the distribution of village types helps to grasp the pathway of their unique development.This study spatialized9250 villages in Jilin Province(divided into six types)of China,and their distribution characteristics and influencing factors were examined using methods such as kernel density estimation,Ripley’s K function,the co-location quotient,and Geodetector.The results indicate that the spatial distribution balance and density of village types are different.All types of villages show an agglomeration distribution pattern,but the scale and intensity vary.There is a strong spatial association between agglomerative promotion(AP)and stable improvement(SIm)villages,as well as between characteristic protection(CP)and prospering frontier and enriching people(PE)villages.The factors affecting their distribution include terrain undulation,the percentage of arable land,the distance to the county town,road network density,population density,gross domestic product(GDP),and industrial enterprise density.The influencing factors for the distribution of village types are closely related to the function of each village.Based on the differences in the spatial distribution and influencing factors of different village types,policy suggestions are given for classified development. | YANG Zhipeng WANG Shijun HAO Feilong MA Li CHANG Xiaodong LONG Wang | 2023 | Chinese Geographical Science2023，33，5： | 0 |
| 5 | High Order Deep Neural Network for Solving High Frequency Partial Differential Equations显示文摘This paper proposes a high order deep neural network(HOrderDNN)for solving high frequency partial differential equations(PDEs),which incorporates the idea of“high order”from finite element methods(FEMs)into commonly-used deep neural networks(DNNs)to obtain greater approximation ability.The main idea of HOrderDNN is introducing a nonlinear transformation layer between the input layer and the first hidden layer to form a high order polynomial space with the degree not exceeding p,followed by a normal DNN.The order p can be guided by the regularity of solutions of PDEs.The performance of HOrderDNNis evaluated on high frequency function fitting problems and high frequency Poisson and Helmholtz equations.The results demonstrate that:HOrderDNNs(p>1)can efficiently capture the high frequency information in target functions;and when compared to physics-informed neural network(PINN),HOrderDNNs(p>1)converge faster and achieve much smaller relative errors with same number of trainable parameters.In particular,when solving the high frequency Helmholtz equation in Section 3.5,the relative error of PINN stays around 1 with its depth and width increase,while the relative error can be reduced to around 0.02 as p increases(see Table 5). | Zhipeng Chang Ke Li Xiufen Zou Xueshuang Xiang | 2022 | Communications in Computational Physics2022，31，2： | 0 |
| 6 | High Order Deep Domain Decomposition Method for Solving High Frequency Interface Problems显示文摘This paper proposes a high order deep domain decomposition method(HOrderDeepDDM)for solving high-frequency interface problems,which combines high order deep neural network(HOrderDNN)with domain decomposition method(DDM).The main idea of HOrderDeepDDM is to divide the computational domain into some sub-domains by DDM,and apply HOrderDNNs to solve the high-frequency problem on each sub-domain.Besides,we consider an adaptive learning rate annealing method to balance the errors inside the sub-domains,on the interface and the boundary during the optimization process.The performance of HOrderDeepDDM is evaluated on high-frequency elliptic and Helmholtz interface problems.The results indicate that:HOrderDeepDDM inherits the ability of DeepDDM to handle discontinuous interface problems and the power of HOrderDNN to approximate high-frequency problems.In detail,HOrderDeepDDMs(p>1)could capture the high-frequency information very well.When compared to the deep domain decomposition method(DeepDDM),HOrderDeepDDMs(p>1)converge faster and achieve much smaller relative errors with the same number of trainable parameters.For example,when solving the high-frequency interface elliptic problems in Section 3.3.1,the minimum relative errors obtained by HOrderDeepDDMs(p=9)are one order of magnitude smaller than that obtained by DeepDDMs when the number of the parameters keeps the same,as shown in Fig.4. | Zhipeng Chang Ke Li Xiufen Zou Xueshuang Xiang | 2023 | Advances in Applied Mathematics and Mechanics2023，15，6： | 0 |
您所在的机构暂未开通此部分的功能，请联系管理员