深基坑挡土墙是工程实践中常用的支护结构,对限制深基坑变形和预防工程事故起着重要的作用。深基坑工程往往会布置多个不同深度的测点,然而现有研究大多只预测了单个测点的未来侧移,浪费了其余测点的监测数据。以杭州市某深基坑工程为背...深基坑挡土墙是工程实践中常用的支护结构,对限制深基坑变形和预防工程事故起着重要的作用。深基坑工程往往会布置多个不同深度的测点,然而现有研究大多只预测了单个测点的未来侧移,浪费了其余测点的监测数据。以杭州市某深基坑工程为背景,建立基于贝叶斯优化的多输出长短期记忆(Long short term memory,LSTM)神经网络模型,在保证模型最优性能的情况下,采用历史监测数据输入对深基坑的多个测点进行预测,并单独提取墙体每日最大侧移预测值进行分析。研究结果表明:结合贝叶斯优化的多输出LSTM神经网络模型在深基坑墙体多测点侧移预测方面展现出理想的预测效果,模型R^(2)达到了0.94,每日最大侧移预测值的模型R^(2)为0.91,略低于整体预测。展开更多
物理信息神经网络(physics-informed neural networks,PINN)由于嵌入了物理先验知识,可以在少量训练数据的情况下获得自动满足物理约束的代理模型,受到了智能科学计算领域的广泛关注.但是,PINN的离散时间模型(PINN-RK)无法同时近似多个...物理信息神经网络(physics-informed neural networks,PINN)由于嵌入了物理先验知识,可以在少量训练数据的情况下获得自动满足物理约束的代理模型,受到了智能科学计算领域的广泛关注.但是,PINN的离散时间模型(PINN-RK)无法同时近似多个物理量相互耦合的偏微分方程系统,限制了其处理复杂多物理场的能力.为了打破这一限制,文章提出了一种基于龙格库塔法的多输出物理信息神经网络(multi-output physics-informed neural networks based on the Runge-Kutta method,MO-PINN-RK),MO-PINN-RK模型在离散时间模型的基础上采用了并行输出的神经网络结构,通过将神经网络划分为多个子网络,建立了多个神经网络输出层.采用不同输出层近似不同物理量的方式,MO-PINN-RK模型不仅可以同时表征多个物理量,而且还能够实现求解偏微分方程系统的目的.另外,MO-PINN-RK克服了PINN离散时间模型仅适用于一维空间的局限性,将其应用范围扩展到了更为普遍的多维空间.为了验证MO-PINN-RK的有效性,文章对圆柱绕流问题进行了流场预测和参数辨识研究.测试结果表明,与PINN相比,MO-PINN-RK在流场预测问题中的准确性获得了提升,其精度至少提高了2倍,而在参数辨识问题中,MO-PINN-RK的相对误差降低了一个数量级.这凸显了MO-PINN-RK在流体动力学领域的卓越能力,为解决复杂问题提供了更准确、更有效的解决方案.展开更多
As the current medium access control protocols with Multiple Input Multiple Output （MIMO） links only bear point to point service, broadcast scheduling algorithm in ad hoc networks with MIMO links is proposed. The ke...As the current medium access control protocols with Multiple Input Multiple Output （MIMO） links only bear point to point service, broadcast scheduling algorithm in ad hoc networks with MIMO links is proposed. The key to the proposed broadcast scheduling algorithm is the time slot scheduling algorithm which guarantees collisi~）n-free transmissions for every node and the mini- mum frame length. The proposed algorithm increases the simultaneous transmissions of MIMO links efficiently. Due to the interference null capacity of MIMO links, the interference node set of each node can decrease from two-hop neighbors to one-hop neighbors possibly. Simulation results show that our algorithm can greatly improve network capacity and decrease average packet delay.展开更多
The harsh space radiation environment compromises the reliability of an on-board switching fabric by leading to cross-point and switching element(SE)faults.Different from traditional faulttolerant switching fabrics on...The harsh space radiation environment compromises the reliability of an on-board switching fabric by leading to cross-point and switching element(SE)faults.Different from traditional faulttolerant switching fabrics only taking crosspoint faults into account,a novel Input and Output Parallel Clos network,referred to as the(p_1,p_2)-IOPClos,is proposed to tolerate both cross-point and SE faults.In the(p_1,p_2)-IOPClos,there are p_1 and p_2 expanded parallel switching planes in the input and output stages,respectively.The multiple input/output switching planes are interconnected through the middle stage to provide multiple paths in each stage by which the network throughput can be increased remarkably.Furthermore,the network reliability of the(p_1,p_2)-IOPClos under the above both kinds of faults is analyzed.The corresponding implementation cost is also presented along with the network size.Both theoretical analysis and numerical results indicate that the(p_1,p_2)-IOPClos outperforms traditional Clos-type networks at reliability,while has less implementation cost than the multi-plane Clos network.展开更多
Multiple-input multiple-output(MIMO) and cooperative communications have been attracted great attention for the improvements of communication capacity, power consumption, and transmission coverage. The conventional fi...Multiple-input multiple-output(MIMO) and cooperative communications have been attracted great attention for the improvements of communication capacity, power consumption, and transmission coverage. The conventional fixed relaying protocols, amplify-and-forward(AF) and decode-and-forward(DF), have their own advantages and disadvantages, i.e. AF performs better than DF for low signal-to-noise ratio(SNR) region, while the reverse is true for high SNR region. Therefore, this paper proposes an SNR-adaptive forward(SAF) relaying scheme obtaining the advantages of both AF and DF. Furthermore, the proposed SAF does not need to switch between AF and DF when SNR changes. The main idea is to adaptively derive the soft information at the cooperative relay nodes based on the information of the received signal and the SNR. Besides, based on the theoretical analysis and the simulation results, it is affirmed that the proposed SAF achieves superior performance than both AF and DF for all SNRs. Moreover, the performance gain would be improved with the increasing number of parallel cooperative relay nodes.展开更多
文摘深基坑挡土墙是工程实践中常用的支护结构,对限制深基坑变形和预防工程事故起着重要的作用。深基坑工程往往会布置多个不同深度的测点,然而现有研究大多只预测了单个测点的未来侧移,浪费了其余测点的监测数据。以杭州市某深基坑工程为背景,建立基于贝叶斯优化的多输出长短期记忆(Long short term memory,LSTM)神经网络模型,在保证模型最优性能的情况下,采用历史监测数据输入对深基坑的多个测点进行预测,并单独提取墙体每日最大侧移预测值进行分析。研究结果表明:结合贝叶斯优化的多输出LSTM神经网络模型在深基坑墙体多测点侧移预测方面展现出理想的预测效果,模型R^(2)达到了0.94,每日最大侧移预测值的模型R^(2)为0.91,略低于整体预测。
文摘物理信息神经网络(physics-informed neural networks,PINN)由于嵌入了物理先验知识,可以在少量训练数据的情况下获得自动满足物理约束的代理模型,受到了智能科学计算领域的广泛关注.但是,PINN的离散时间模型(PINN-RK)无法同时近似多个物理量相互耦合的偏微分方程系统,限制了其处理复杂多物理场的能力.为了打破这一限制,文章提出了一种基于龙格库塔法的多输出物理信息神经网络(multi-output physics-informed neural networks based on the Runge-Kutta method,MO-PINN-RK),MO-PINN-RK模型在离散时间模型的基础上采用了并行输出的神经网络结构,通过将神经网络划分为多个子网络,建立了多个神经网络输出层.采用不同输出层近似不同物理量的方式,MO-PINN-RK模型不仅可以同时表征多个物理量,而且还能够实现求解偏微分方程系统的目的.另外,MO-PINN-RK克服了PINN离散时间模型仅适用于一维空间的局限性,将其应用范围扩展到了更为普遍的多维空间.为了验证MO-PINN-RK的有效性,文章对圆柱绕流问题进行了流场预测和参数辨识研究.测试结果表明,与PINN相比,MO-PINN-RK在流场预测问题中的准确性获得了提升,其精度至少提高了2倍,而在参数辨识问题中,MO-PINN-RK的相对误差降低了一个数量级.这凸显了MO-PINN-RK在流体动力学领域的卓越能力,为解决复杂问题提供了更准确、更有效的解决方案.
基金supported by the National Natural Science Foundation of China(No.6037 2048)Microsoft Research Asia,TRAP0YT,Natural Science Foundation of China(No.60496 316)+1 种基金China"863"Project on cognitive radio(2005AA123910),M0E(104171)Research Fund for the Doctoral Program of Higher Education(20050701007).
文摘As the current medium access control protocols with Multiple Input Multiple Output （MIMO） links only bear point to point service, broadcast scheduling algorithm in ad hoc networks with MIMO links is proposed. The key to the proposed broadcast scheduling algorithm is the time slot scheduling algorithm which guarantees collisi~）n-free transmissions for every node and the mini- mum frame length. The proposed algorithm increases the simultaneous transmissions of MIMO links efficiently. Due to the interference null capacity of MIMO links, the interference node set of each node can decrease from two-hop neighbors to one-hop neighbors possibly. Simulation results show that our algorithm can greatly improve network capacity and decrease average packet delay.
基金supported by the National Natural Science Foundation of China(91338108,91438206)
文摘The harsh space radiation environment compromises the reliability of an on-board switching fabric by leading to cross-point and switching element(SE)faults.Different from traditional faulttolerant switching fabrics only taking crosspoint faults into account,a novel Input and Output Parallel Clos network,referred to as the(p_1,p_2)-IOPClos,is proposed to tolerate both cross-point and SE faults.In the(p_1,p_2)-IOPClos,there are p_1 and p_2 expanded parallel switching planes in the input and output stages,respectively.The multiple input/output switching planes are interconnected through the middle stage to provide multiple paths in each stage by which the network throughput can be increased remarkably.Furthermore,the network reliability of the(p_1,p_2)-IOPClos under the above both kinds of faults is analyzed.The corresponding implementation cost is also presented along with the network size.Both theoretical analysis and numerical results indicate that the(p_1,p_2)-IOPClos outperforms traditional Clos-type networks at reliability,while has less implementation cost than the multi-plane Clos network.
基金supported in part by the National Natural Science Foundation of China 61501461, 61471269, 71232006, and 61533019the Early Career Development Award of SKLMCCS (Y3S9021F34)
文摘Multiple-input multiple-output(MIMO) and cooperative communications have been attracted great attention for the improvements of communication capacity, power consumption, and transmission coverage. The conventional fixed relaying protocols, amplify-and-forward(AF) and decode-and-forward(DF), have their own advantages and disadvantages, i.e. AF performs better than DF for low signal-to-noise ratio(SNR) region, while the reverse is true for high SNR region. Therefore, this paper proposes an SNR-adaptive forward(SAF) relaying scheme obtaining the advantages of both AF and DF. Furthermore, the proposed SAF does not need to switch between AF and DF when SNR changes. The main idea is to adaptively derive the soft information at the cooperative relay nodes based on the information of the received signal and the SNR. Besides, based on the theoretical analysis and the simulation results, it is affirmed that the proposed SAF achieves superior performance than both AF and DF for all SNRs. Moreover, the performance gain would be improved with the increasing number of parallel cooperative relay nodes.
