Deep neural networks(DNNs)are effective in solving both forward and inverse problems for nonlinear partial differential equations(PDEs).However,conventional DNNs are not effective in handling problems such as delay di...Deep neural networks(DNNs)are effective in solving both forward and inverse problems for nonlinear partial differential equations(PDEs).However,conventional DNNs are not effective in handling problems such as delay differential equations(DDEs)and delay integrodifferential equations(DIDEs)with constant delays,primarily due to their low regularity at delayinduced breaking points.In this paper,a DNN method that combines multi-task learning(MTL)which is proposed to solve both the forward and inverse problems of DIDEs.The core idea of this approach is to divide the original equation into multiple tasks based on the delay,using auxiliary outputs to represent the integral terms,followed by the use of MTL to seamlessly incorporate the properties at the breaking points into the loss function.Furthermore,given the increased training dificulty associated with multiple tasks and outputs,we employ a sequential training scheme to reduce training complexity and provide reference solutions for subsequent tasks.This approach significantly enhances the approximation accuracy of solving DIDEs with DNNs,as demonstrated by comparisons with traditional DNN methods.We validate the effectiveness of this method through several numerical experiments,test various parameter sharing structures in MTL and compare the testing results of these structures.Finally,this method is implemented to solve the inverse problem of nonlinear DIDE and the results show that the unknown parameters of DIDE can be discovered with sparse or noisy data.展开更多
桥梁车辆移动载荷识别MFI(Moving Force Identification)是结构动力学领域中的一个典型反问题.针对现有基于共轭梯度方法的载荷识别方法对多轴车辆荷载识别效果不佳的问题,提出了一种基于改进分数阶共轭梯度算法IFCG(Improved Fractiona...桥梁车辆移动载荷识别MFI(Moving Force Identification)是结构动力学领域中的一个典型反问题.针对现有基于共轭梯度方法的载荷识别方法对多轴车辆荷载识别效果不佳的问题,提出了一种基于改进分数阶共轭梯度算法IFCG(Improved Fractional Conjugate Gradient)的载荷识别方法.基于车辆行驶过程在时域中建立车桥动力系统,通过模态叠加原理得到桥梁动态响应,将MFI问题转化为无约束优化问题;其次,引入新的搜索方向标量,使所提算法能够针对多轴以及高噪声情况下保持精度和识别效率;接着,通过识别两轴车辆移动载荷验证了所提方法的有效性;然后,对分数阶次进行定量对比研究,选择最优分数阶次;最后,通过识别多种工况下的三轴车辆载荷,将所提方法与现有方法进行对比,验证了IFCG方法在不同工况下的桥梁多轴车辆MFI都具有较高的识别精度和速度.展开更多
Developing intelligent unmanned swarm systems(IUSSs)is a highly intricate process.Although current simulators and toolchains have made a notable contribution to the develop-ment of algorithms for IUSSs,they tend to co...Developing intelligent unmanned swarm systems(IUSSs)is a highly intricate process.Although current simulators and toolchains have made a notable contribution to the develop-ment of algorithms for IUSSs,they tend to concentrate on iso-lated technical elements and are deficient in addressing the full spectrum of critical technologies and development needs in a systematic and integrative manner.Furthermore,the current suite of tools has not adequately addressed the challenge of bridging the gap between simulation and real-world deployment of algorithms.Therefore,a comprehensive solution must be developed that encompasses the entire IUSS development life-cycle.In this study,we present the RflySim ToolChain,which has been developed with the specific aim of facilitating the rapid development and validation of IUSSs.The RflySim ToolChain employs a model-based design(MBD)approach,integrating a modeling and simulation module,a lower reliable control mo-dule,and an upper swarm decision-making module.This compre-hensive integration encompasses the entire process,from mo-deling and simulation to testing and deployment,thereby enabling users to rapidly construct and validate IUSSs.The prin-cipal advantages of the RflySim ToolChain are as follows:it pro-vides a comprehensive solution that meets the full-stack devel-opment needs of IUSSs;the highly modular architecture and comprehensive software development kit(SDK)facilitate the automation of the entire IUSS development process.Further-more,the high-fidelity model design and reliable architecture solution ensure a seamless transition from simulation to real-world deployment,which is known as the simulation to reality(Sim2Real)process.This paper presents a series of case stu-dies that illustrate the effectiveness of the RflySim ToolChain in supporting the research and application of IUSSs.展开更多
Carbon nanotubes(CNTs)have garnered great attention in recent years due to their outstanding electrical,thermal,and mechanical properties.The incorporation of small amounts of CNTs in polymers can substantially improv...Carbon nanotubes(CNTs)have garnered great attention in recent years due to their outstanding electrical,thermal,and mechanical properties.The incorporation of small amounts of CNTs in polymers can substantially improve the sensitivity of the polymer's electrical conductivity.This paper presents a modified Maxwell model to evaluate the electrical conductivity of CNTs-filled polymer composites by introducing a transition zone to account for the tunneling effect.In this modified Maxwell model,the CNTs-filled polymer composite is modeled as a three-phase composite,consisting of a matrix(polymer),inclusions(CNTs),and a transition zone(tunneling zone).The effective electrical conductivity(EEC)of the composite is calculated based on the volume fractions and electrical conductivities of the matrix,inclusions,and transition zone.The model's validity is confirmed through the use of available test data,which demonstrates its capability to accurately capture the nonlinear conductivity behavior observed in CNTs-polymer composites.This study offers valuable insights into the design of high-performance conductive polymer nanocomposites,and enhances the understanding of electrical conduction mechanisms in CNT-dispersed polymer composites.展开更多
文摘Deep neural networks(DNNs)are effective in solving both forward and inverse problems for nonlinear partial differential equations(PDEs).However,conventional DNNs are not effective in handling problems such as delay differential equations(DDEs)and delay integrodifferential equations(DIDEs)with constant delays,primarily due to their low regularity at delayinduced breaking points.In this paper,a DNN method that combines multi-task learning(MTL)which is proposed to solve both the forward and inverse problems of DIDEs.The core idea of this approach is to divide the original equation into multiple tasks based on the delay,using auxiliary outputs to represent the integral terms,followed by the use of MTL to seamlessly incorporate the properties at the breaking points into the loss function.Furthermore,given the increased training dificulty associated with multiple tasks and outputs,we employ a sequential training scheme to reduce training complexity and provide reference solutions for subsequent tasks.This approach significantly enhances the approximation accuracy of solving DIDEs with DNNs,as demonstrated by comparisons with traditional DNN methods.We validate the effectiveness of this method through several numerical experiments,test various parameter sharing structures in MTL and compare the testing results of these structures.Finally,this method is implemented to solve the inverse problem of nonlinear DIDE and the results show that the unknown parameters of DIDE can be discovered with sparse or noisy data.
基金supported by the National Natural Science Foundation of China(62406345).
文摘Developing intelligent unmanned swarm systems(IUSSs)is a highly intricate process.Although current simulators and toolchains have made a notable contribution to the develop-ment of algorithms for IUSSs,they tend to concentrate on iso-lated technical elements and are deficient in addressing the full spectrum of critical technologies and development needs in a systematic and integrative manner.Furthermore,the current suite of tools has not adequately addressed the challenge of bridging the gap between simulation and real-world deployment of algorithms.Therefore,a comprehensive solution must be developed that encompasses the entire IUSS development life-cycle.In this study,we present the RflySim ToolChain,which has been developed with the specific aim of facilitating the rapid development and validation of IUSSs.The RflySim ToolChain employs a model-based design(MBD)approach,integrating a modeling and simulation module,a lower reliable control mo-dule,and an upper swarm decision-making module.This compre-hensive integration encompasses the entire process,from mo-deling and simulation to testing and deployment,thereby enabling users to rapidly construct and validate IUSSs.The prin-cipal advantages of the RflySim ToolChain are as follows:it pro-vides a comprehensive solution that meets the full-stack devel-opment needs of IUSSs;the highly modular architecture and comprehensive software development kit(SDK)facilitate the automation of the entire IUSS development process.Further-more,the high-fidelity model design and reliable architecture solution ensure a seamless transition from simulation to real-world deployment,which is known as the simulation to reality(Sim2Real)process.This paper presents a series of case stu-dies that illustrate the effectiveness of the RflySim ToolChain in supporting the research and application of IUSSs.
基金Project supported by the National Natural Science Foundation of China(Nos.11972203 and 11572162)the Science and Technology Innovation 2025 Major Project of Ningbo City of China(No.2022Z209)Ningbo Key Technology Breakthrough Plan Project of“Science and Technology Innovation Yongjiang 2035”(No.2024Z256)。
文摘Carbon nanotubes(CNTs)have garnered great attention in recent years due to their outstanding electrical,thermal,and mechanical properties.The incorporation of small amounts of CNTs in polymers can substantially improve the sensitivity of the polymer's electrical conductivity.This paper presents a modified Maxwell model to evaluate the electrical conductivity of CNTs-filled polymer composites by introducing a transition zone to account for the tunneling effect.In this modified Maxwell model,the CNTs-filled polymer composite is modeled as a three-phase composite,consisting of a matrix(polymer),inclusions(CNTs),and a transition zone(tunneling zone).The effective electrical conductivity(EEC)of the composite is calculated based on the volume fractions and electrical conductivities of the matrix,inclusions,and transition zone.The model's validity is confirmed through the use of available test data,which demonstrates its capability to accurately capture the nonlinear conductivity behavior observed in CNTs-polymer composites.This study offers valuable insights into the design of high-performance conductive polymer nanocomposites,and enhances the understanding of electrical conduction mechanisms in CNT-dispersed polymer composites.
