Accurate estimation of mineralogy from geophysical well logs is crucial for characterizing geological formations,particularly in hydrocarbon exploration,CO_(2) sequestration,and geothermal energy development.Current t...Accurate estimation of mineralogy from geophysical well logs is crucial for characterizing geological formations,particularly in hydrocarbon exploration,CO_(2) sequestration,and geothermal energy development.Current techniques,such as multimineral petrophysical analysis,offer details into mineralogical distribution.However,it is inherently time-intensive and demands substantial geological expertise for accurate model evaluation.Furthermore,traditional machine learning techniques often struggle to predict mineralogy accurately and sometimes produce estimations that violate fundamental physical principles.To address this,we present a new approach using Physics-Integrated Neural Networks(PINNs),that combines data-driven learning with domain-specific physical constraints,embedding petrophysical relationships directly into the neural network architecture.This approach enforces that predictions adhere to physical laws.The methodology is applied to the Broom Creek Deep Saline aquifer,a CO_(2) sequestration site in the Williston Basin,to predict the volumes of key mineral constituents—quartz,dolomite,feldspar,anhydrite,illite—along with porosity.Compared to traditional artificial neural networks (ANN),the PINN approach demonstrates higher accuracy and better generalizability,significantly enhancing predictive performance on unseen well datasets.The average mean error across the three blind wells is 0.123 for ANN and 0.042 for PINN,highlighting the superior accuracy of the PINN approach.This method reduces uncertainties in reservoir characterization by improving the reliability of mineralogy and porosity predictions,providing a more robust tool for decision-making in various subsurface geoscience applications.展开更多
Optical solitons,as self-sustaining waveforms in a nonlinear medium where dispersion and nonlinear effects are balanced,have key applications in ultrafast laser systems and optical communications.Physics-informed neur...Optical solitons,as self-sustaining waveforms in a nonlinear medium where dispersion and nonlinear effects are balanced,have key applications in ultrafast laser systems and optical communications.Physics-informed neural networks(PINN)provide a new way to solve the nonlinear Schrodinger equation describing the soliton evolution by fusing data-driven and physical constraints.However,the grid point sampling strategy of traditional PINN suffers from high computational complexity and unstable gradient flow,which makes it difficult to capture the physical details efficiently.In this paper,we propose a residual-based adaptive multi-distribution(RAMD)sampling method to optimize the PINN training process by dynamically constructing a multi-modal loss distribution.With a 50%reduction in the number of grid points,RAMD significantly reduces the relative error of PINN and,in particular,optimizes the solution error of the(2+1)Ginzburg–Landau equation from 4.55%to 1.98%.RAMD breaks through the lack of physical constraints in the purely data-driven model by the innovative combination of multi-modal distribution modeling and autonomous sampling control for the design of all-optical communication devices.RAMD provides a high-precision numerical simulation tool for the design of all-optical communication devices,optimization of nonlinear laser devices,and other studies.展开更多
This paper describes an optimal power allocation scheme for orthogonal frequency division multiple access two-way relay networks with physical network coding. The aim is to enhance the achievable sum rate of the termi...This paper describes an optimal power allocation scheme for orthogonal frequency division multiple access two-way relay networks with physical network coding. The aim is to enhance the achievable sum rate of the terminals for a constrained total transmit power. Convex optimization is used to derive a closed-form solution for the power allocation between the relay node and the two terminals. This reduces the variable dimensionality of the objective function for the power assignment problem among multiple carriers when the total transmit power is constrained. This solution is then used to derive the optimal power control scheme. This method reduces the implementation complexity compared with the traditional resource allocation scheme. Numerical and simulation results show that the approach achieves almost the optimal sum rate and outperforms the fixed power assignment method with less computational load in various scenarios.展开更多
In RFID(Radio Frequency IDentification)system,when multiple tags are in the operating range of one reader and send their information to the reader simultaneously,the signals of these tags are superimposed in the air,w...In RFID(Radio Frequency IDentification)system,when multiple tags are in the operating range of one reader and send their information to the reader simultaneously,the signals of these tags are superimposed in the air,which results in a collision and leads to the degrading of tags identifying efficiency.To improve the multiple tags’identifying efficiency due to collision,a physical layer network coding based binary search tree algorithm(PNBA)is proposed in this paper.PNBA pushes the conflicting signal information of multiple tags into a stack,which is discarded by the traditional anti-collision algorithm.In addition,physical layer network coding is exploited by PNBA to obtain unread tag information through the decoding operation of physical layer network coding using the conflicting information in the stack.Therefore,PNBA reduces the number of interactions between reader and tags,and improves the tags identification efficiency.Theoretical analysis and simulation results using MATLAB demonstrate that PNBA reduces the number of readings,and improve RFID identification efficiency.Especially,when the number of tags to be identified is 100,the average needed reading number of PNBA is 83%lower than the basic binary search tree algorithm,43%lower than reverse binary search tree algorithm,and its reading efficiency reaches 0.93.展开更多
The tremendous performance gain of heterogeneous networks(Het Nets) is at the cost of complicated resource allocation. Considering information security, the resource allocation for Het Nets becomes much more challengi...The tremendous performance gain of heterogeneous networks(Het Nets) is at the cost of complicated resource allocation. Considering information security, the resource allocation for Het Nets becomes much more challenging and this is the focus of this paper. In this paper, the eavesdropper is hidden from the macro base stations. To relax the unpractical assumption on the channel state information on eavesdropper, a localization based algorithm is first given. Then a joint resource allocation algorithm is proposed in our work, which simultaneously considers physical layer security, cross-tier interference and joint optimization of power and subcarriers under fairness requirements. It is revealed in our work that the considered optimization problem can be efficiently solved relying on convex optimization theory and the Lagrangian dual decomposition method is exploited to solve the considered problem effectively. Moreover, in each iteration the closed-form optimal resource allocation solutions can be obtained based on the Karush-Kuhn-Tucker(KKT) conditions. Finally, the simulation results are given to show the performance advantages of the proposed algorithm.展开更多
With the advent of physics informed neural networks(PINNs),deep learning has gained interest for solving nonlinear partial differential equations(PDEs)in recent years.In this paper,physics informed memory networks(PIM...With the advent of physics informed neural networks(PINNs),deep learning has gained interest for solving nonlinear partial differential equations(PDEs)in recent years.In this paper,physics informed memory networks(PIMNs)are proposed as a new approach to solving PDEs by using physical laws and dynamic behavior of PDEs.Unlike the fully connected structure of the PINNs,the PIMNs construct the long-term dependence of the dynamics behavior with the help of the long short-term memory network.Meanwhile,the PDEs residuals are approximated using difference schemes in the form of convolution filter,which avoids information loss at the neighborhood of the sampling points.Finally,the performance of the PIMNs is assessed by solving the Kd V equation and the nonlinear Schr?dinger equation,and the effects of difference schemes,boundary conditions,network structure and mesh size on the solutions are discussed.Experiments show that the PIMNs are insensitive to boundary conditions and have excellent solution accuracy even with only the initial conditions.展开更多
Physics informed neural networks(PINNs)are a deep learning approach designed to solve partial differential equations(PDEs).Accurately learning the initial conditions is crucial when employing PINNs to solve PDEs.Howev...Physics informed neural networks(PINNs)are a deep learning approach designed to solve partial differential equations(PDEs).Accurately learning the initial conditions is crucial when employing PINNs to solve PDEs.However,simply adjusting weights and imposing hard constraints may not always lead to better learning of the initial conditions;sometimes it even makes it difficult for the neural networks to converge.To enhance the accuracy of PINNs in learning the initial conditions,this paper proposes a novel strategy named causally enhanced initial conditions(CEICs).This strategy works by embedding a new loss in the loss function:the loss is constructed by the derivative of the initial condition and the derivative of the neural network at the initial condition.Furthermore,to respect the causality in learning the derivative,a novel causality coefficient is introduced for the training when selecting multiple derivatives.Additionally,because CEICs can provide more accurate pseudo-labels in the first subdomain,they are compatible with the temporal-marching strategy.Experimental results demonstrate that CEICs outperform hard constraints and improve the overall accuracy of pre-training PINNs.For the 1D-Korteweg–de Vries,reaction and convection equations,the CEIC method proposed in this paper reduces the relative error by at least 60%compared to the previous methods.展开更多
5G is envisioned to guarantee high transmission rate,ultra-low latency,high reliability and massive connections.To satisfy the above requirements,the 5G architecture is designed with the properties of using service-ba...5G is envisioned to guarantee high transmission rate,ultra-low latency,high reliability and massive connections.To satisfy the above requirements,the 5G architecture is designed with the properties of using service-based architecture,cloud-native oriented,adopting IT-based API interfaces and introduction of the Network Repository Function.However,with the wide commercialization of 5G network and the exploration towards 6G,the 5G architecture exposes the disadvantages of high architecture complexity,difficult inter-interface communication,low cognitive capability,bad instantaneity,and deficient intelligence.To overcome these limitations,this paper investigates 6G network architecture,and proposes a cognitive intelligence based distributed 6G network architecture.This architecture consists of a physical network layer and an intelligent decision layer.The two layers coordinate through flexible service interfaces,supporting function decoupling and joint evolution of intelligence services and network services.With the above design,the proposed 6G architecture can be updated autonomously to deal with the future unpredicted complex services.展开更多
A novel identification method of aerodynamicmodels using a physics neural network,named the attitude dynamics network,which incorporates the attitude dynamics of an aircraft without any prior aerodynamic knowledge,is ...A novel identification method of aerodynamicmodels using a physics neural network,named the attitude dynamics network,which incorporates the attitude dynamics of an aircraft without any prior aerodynamic knowledge,is proposed.Then a learning controller,which combines feedback linearization with sliding mode control,is developed by introducing the learned aerodynamicmodels.The merit of the identification method is that the aerodynamicmodels can be learned end-to-end by the physics network directly from the flight data.Consequently,the paper uses an offline scheme and an online scheme to combine the identification process and the control process.In the offline scheme,learning the aerodynamic models and controlling the aircraft compose a cascade system,whereas the online scheme,similar to Learn-to-Fly,is a parallel system.Specifically,in the offline scheme,the physics neural network is trained by sufficient offline flight data,and then the trained network is substituted into the controller.The online scheme refers to the controller making the aircraft fly to generate flight data and sending these data to the deep network at the time of training,while the deep network provides the trained aerodynamic models to the controller at other times.Simulation results show that both under nominal and disturbance aerodynamic conditions,the network trained offline with a large amount of nominal data approximate the aerodynamicmodels well.Thus,the performance of the controller reaches a good level;for the online scheme,the predictive capability of the network increases and the performance of the controller improves with more training data.展开更多
Neural network methods have been widely used in many fields of scientific research with the rapid increase of computing power.The physics-informed neural networks(PINNs)have received much attention as a major breakthr...Neural network methods have been widely used in many fields of scientific research with the rapid increase of computing power.The physics-informed neural networks(PINNs)have received much attention as a major breakthrough in solving partial differential equations using neural networks.In this paper,a resampling technique based on the expansion-shrinkage point(ESP)selection strategy is developed to dynamically modify the distribution of training points in accordance with the performance of the neural networks.In this new approach both training sites with slight changes in residual values and training points with large residuals are taken into account.In order to make the distribution of training points more uniform,the concept of continuity is further introduced and incorporated.This method successfully addresses the issue that the neural network becomes ill or even crashes due to the extensive alteration of training point distribution.The effectiveness of the improved physics-informed neural networks with expansion-shrinkage resampling is demonstrated through a series of numerical experiments.展开更多
Heat transport has been significantly enhanced by the widespread usage of extended surfaces in various engi-neering domains.Gas turbine blade cooling,refrigeration,and electronic equipment cooling are a few prevalent ...Heat transport has been significantly enhanced by the widespread usage of extended surfaces in various engi-neering domains.Gas turbine blade cooling,refrigeration,and electronic equipment cooling are a few prevalent applications.Thus,the thermal analysis of extended surfaces has been the subject of a significant assessment by researchers.Motivated by this,the present study describes the unsteady thermal dispersal phenomena in a wavy fin with the presence of convection heat transmission.This analysis also emphasizes a novel mathematical model in accordance with transient thermal change in a wavy profiled fin resulting from convection using the finite difference method(FDM)and physics informed neural network(PINN).The time and space-dependent governing partial differential equation(PDE)for the suggested heat problem has been translated into a dimensionless form using the relevant dimensionless terms.The graph depicts the effect of thermal parameters on the fin’s thermal profile.The temperature dispersion in the fin decreases as the dimensionless convection-conduction variable rises.The heat dispersion in the fin is decreased by increasing the aspect ratio,whereas the reverse behavior is seen with the time change.Furthermore,FDM-PINN results are validated against the outcomes of the FDM.展开更多
In this paper,we introduce a new deep learning framework for discovering the phase-field models from existing image data.The new framework embraces the approximation power of physics informed neural networks(PINNs)and...In this paper,we introduce a new deep learning framework for discovering the phase-field models from existing image data.The new framework embraces the approximation power of physics informed neural networks(PINNs)and the computational efficiency of the pseudo-spectral methods,which we named pseudo-spectral PINN or SPINN.Unlike the baseline PINN,the pseudo-spectral PINN has several advantages.First of all,it requires less training data.A minimum of two temporal snapshots with uniform spatial resolution would be adequate.Secondly,it is computationally efficient,as the pseudo-spectral method is used for spatial discretization.Thirdly,it requires less trainable parameters compared with the baseline PINN,which significantly simplifies the training process and potentially assures fewer local minima or saddle points.We illustrate the effectiveness of pseudo-spectral PINN through several numerical examples.The newly proposed pseudo-spectral PINN is rather general,and it can be readily applied to discover other FDE-based models from image data.展开更多
This paper introduces federated services as a smart service ecology with federated security to align distributed data supply with diversified service demands spanning digital and societal contexts.It presents the comp...This paper introduces federated services as a smart service ecology with federated security to align distributed data supply with diversified service demands spanning digital and societal contexts.It presents the comprehensive researches on the theoretical foundation and technical system of federated services,aiming at advancing our understanding and implementation of this novel service paradigm.First,a thorough examination of the characteristics of federated security within federated services is conducted.Then,a five-layer technical framework is formulated under a decentralized intelligent architecture,ensuring secure,agile,and adaptable service provision.On this basis,the operational mechanisms underlying data federation and service confederation is analyzed,with emphasis on the smart supply-demand matching model.Furthermore,a scenario-oriented taxonomy of federated services accompanied by illustrative examples is proposed.Our work offers actionable insights and roadmap for realizing and advancing federated services,contributing to the refinement and wider adoption of this transformative service paradigm in the digital era.展开更多
The synthesis of a new azobenzene(azo)-containing main-chain crystalline polymer with reactive secondary amino groups in its backbone and photodeformation behaviors of its supramolecular hydrogen-bonded fibers are des...The synthesis of a new azobenzene(azo)-containing main-chain crystalline polymer with reactive secondary amino groups in its backbone and photodeformation behaviors of its supramolecular hydrogen-bonded fibers are described. This main-chain azo polymer(namely Azo-MP6) was prepared via first the synthesis of a diacrylate-type azo monomer and its subsequent Michael addition copolymerization with trans-1,4-cyclohexanediamine under a mild reaction condition. Azo-MP6 was found to have a linear main-chain chemical structure instead of a branched one, as verified by comparing its ~1H-NMR spectrum with that of the azo polymer prepared via the polymer analogous reaction of AzoMP6 with acetic anhydride. The thermal stability, phase transition behavior, and photoresponsivity of Azo-MP6 were characterized with TGA,DSC, POM, XRD, and UV-Vis spectroscopy. The experimental results revealed that it had good thermal stability, low glass transition temperature,broad crystalline phase temperature range, and highly reversible photoresponsivity. Physically crosslinked supramolecular hydrogen-bonded fibers with good mechanical properties and a high alignment order of azo mesogens were readily fabricated from Azo-MP6 by using the simple melt spinning method, and they could show "reversible" photoinduced bending under the same UV light irradiation and good anti-fatigue properties.展开更多
With the access to large amounts of renewable energy sources(RES),operation uncertainty of distribution networks increases significantly.Fortunately,adopting advanced information and communication technology,a cyber-p...With the access to large amounts of renewable energy sources(RES),operation uncertainty of distribution networks increases significantly.Fortunately,adopting advanced information and communication technology,a cyber-physical distribution network(CPDS)provides the possibility to solve this problem via aggregative management of decentralized controllable loads.However,information flow in cyber space deeply interacts with energy flow in physical space,leading to a complexity in modeling,design and analysis of the whole control process.To deal with this problem,a general hybrid flow model of CPDS is first proposed in this paper.In this model,the control process is abstracted into interactions among three types of cyber nodes through cyber branches.The mathematic model of cyber nodes and branches is developed as well as that of the controlled physical object for hybrid flow computation.Then,based on the hybrid model,an instantiated application to compensate feeder power deviation caused by RES fluctuation through aggregative control of large-scale air-conditioners(ACs)is investigated.In this application,coordinative control of the AC cluster is achieved through a decentralized control strategy with very little communication cost and very good privacy protection.Results of numerical examples verify the correctness and flexibility of the hybrid flow model in reflecting interactions between cyber flow and energy flow as well as system operations.The proposed decentralized control strategy of the AC cluster is also proven to be effective and robust in FCE compensation.展开更多
Physical neural networks are artificial neural networks that mimic synapses and neurons using physical systems or materials.These networks harness the distinctive characteristics of physical systems to carry out compu...Physical neural networks are artificial neural networks that mimic synapses and neurons using physical systems or materials.These networks harness the distinctive characteristics of physical systems to carry out computations effectively,potentially surpassing the constraints of conventional digital neural networks.A recent advancement known as“physical self-learning”aims to achieve learning through intrinsic physical processes rather than relying on external computations.This article offers a comprehensive review of the progress made in implementing physical self-learning across various physical systems.Prevailing learning strategies that contribute to the realization of physical self-learning are discussed.Despite challenges in understanding the fundamental mechanism of learning,this work highlights the progress towards constructing intelligent hardware from the ground up,incorporating embedded self-organizing and self-adaptive dynamics in physical systems.展开更多
Systems are always designed and optimized based on full traffic load in the current literatures. However, practical systems are seldom operating at full load, even at peak traffic hours. Instead of maximizing system r...Systems are always designed and optimized based on full traffic load in the current literatures. However, practical systems are seldom operating at full load, even at peak traffic hours. Instead of maximizing system rate to achieve the full load, an optimal energy-efficient scheme to minimize the transmit power with required rates is investigated in this article. The considered scenario is a two-way relay channel using amplify-and-forward protocol of physical layer network coding, where two end nodes exchange messages via multiple relay nodes within two timeslots. A joint power allocation and relay selection scheme is designed to achieve the minimum transmit power. Through convex optimization theory, we firstly prove that single relay selection scheme is the most energy-efficient way for physical layer network coding. The closed-form expressions of power allocation are also given. Numerical simulations demonstrate the performance of the designed scheme as well as the comparison among different schemes.展开更多
Previous research on security of network coding focused on the protection of data dissemination procedures and the detection of malicious activities such as pollution attacks. The capabilities of network coding to det...Previous research on security of network coding focused on the protection of data dissemination procedures and the detection of malicious activities such as pollution attacks. The capabilities of network coding to detect other attacks have not been fully explored. In this paper, we propose a new mechanism based on physical layer network coding to detect wormhole attacks. When two signal sequences collide at the receiver, the starting point of the collision is determined by the distances between the receiver and the senders. Therefore, by comparing the starting points of the collisions at two receivers, we can estimate the distance between them and detect fake neighbor connections via wormholes. While the basic idea is clear, we have proposed several schemes at both physical and network layers to transform the idea into a practical approach. Simulations using BPSK modulation at the physical layer show that the wireless nodes can effectively detect fake neighbor connections without the adoption of special hardware or time synchronization.展开更多
基金the North Dakota Industrial Commission (NDIC) for their financial supportprovided by the University of North Dakota Computational Research Center。
文摘Accurate estimation of mineralogy from geophysical well logs is crucial for characterizing geological formations,particularly in hydrocarbon exploration,CO_(2) sequestration,and geothermal energy development.Current techniques,such as multimineral petrophysical analysis,offer details into mineralogical distribution.However,it is inherently time-intensive and demands substantial geological expertise for accurate model evaluation.Furthermore,traditional machine learning techniques often struggle to predict mineralogy accurately and sometimes produce estimations that violate fundamental physical principles.To address this,we present a new approach using Physics-Integrated Neural Networks(PINNs),that combines data-driven learning with domain-specific physical constraints,embedding petrophysical relationships directly into the neural network architecture.This approach enforces that predictions adhere to physical laws.The methodology is applied to the Broom Creek Deep Saline aquifer,a CO_(2) sequestration site in the Williston Basin,to predict the volumes of key mineral constituents—quartz,dolomite,feldspar,anhydrite,illite—along with porosity.Compared to traditional artificial neural networks (ANN),the PINN approach demonstrates higher accuracy and better generalizability,significantly enhancing predictive performance on unseen well datasets.The average mean error across the three blind wells is 0.123 for ANN and 0.042 for PINN,highlighting the superior accuracy of the PINN approach.This method reduces uncertainties in reservoir characterization by improving the reliability of mineralogy and porosity predictions,providing a more robust tool for decision-making in various subsurface geoscience applications.
基金supported by the National Key R&D Program of China(Grant No.2022YFA1604200)National Natural Science Foundation of China(Grant No.12261131495)+1 种基金Beijing Municipal Science and Technology Commission,Adminitrative Commission of Zhongguancun Science Park(Grant No.Z231100006623006)Institute of Systems Science,Beijing Wuzi University(Grant No.BWUISS21)。
文摘Optical solitons,as self-sustaining waveforms in a nonlinear medium where dispersion and nonlinear effects are balanced,have key applications in ultrafast laser systems and optical communications.Physics-informed neural networks(PINN)provide a new way to solve the nonlinear Schrodinger equation describing the soliton evolution by fusing data-driven and physical constraints.However,the grid point sampling strategy of traditional PINN suffers from high computational complexity and unstable gradient flow,which makes it difficult to capture the physical details efficiently.In this paper,we propose a residual-based adaptive multi-distribution(RAMD)sampling method to optimize the PINN training process by dynamically constructing a multi-modal loss distribution.With a 50%reduction in the number of grid points,RAMD significantly reduces the relative error of PINN and,in particular,optimizes the solution error of the(2+1)Ginzburg–Landau equation from 4.55%to 1.98%.RAMD breaks through the lack of physical constraints in the purely data-driven model by the innovative combination of multi-modal distribution modeling and autonomous sampling control for the design of all-optical communication devices.RAMD provides a high-precision numerical simulation tool for the design of all-optical communication devices,optimization of nonlinear laser devices,and other studies.
基金Supported by the Fundamental Research Funds for the Central Universities (No. K50510010027)
文摘This paper describes an optimal power allocation scheme for orthogonal frequency division multiple access two-way relay networks with physical network coding. The aim is to enhance the achievable sum rate of the terminals for a constrained total transmit power. Convex optimization is used to derive a closed-form solution for the power allocation between the relay node and the two terminals. This reduces the variable dimensionality of the objective function for the power assignment problem among multiple carriers when the total transmit power is constrained. This solution is then used to derive the optimal power control scheme. This method reduces the implementation complexity compared with the traditional resource allocation scheme. Numerical and simulation results show that the approach achieves almost the optimal sum rate and outperforms the fixed power assignment method with less computational load in various scenarios.
基金the National Natural Science Foundation of China under Grant 61502411Natural Science Foundation of Jiangsu Province under Grant BK20150432 and BK20151299+7 种基金Natural Science Research Project for Universities of Jiangsu Province under Grant 15KJB520034China Postdoctoral Science Foundation under Grant 2015M581843Jiangsu Provincial Qinglan ProjectTeachers Overseas Study Program of Yancheng Institute of TechnologyJiangsu Provincial Government Scholarship for Overseas StudiesTalents Project of Yancheng Institute of Technology under Grant KJC2014038“2311”Talent Project of Yancheng Institute of TechnologyOpen Fund of Modern Agricultural Resources Intelligent Management and Application Laboratory of Huzhou Normal University.
文摘In RFID(Radio Frequency IDentification)system,when multiple tags are in the operating range of one reader and send their information to the reader simultaneously,the signals of these tags are superimposed in the air,which results in a collision and leads to the degrading of tags identifying efficiency.To improve the multiple tags’identifying efficiency due to collision,a physical layer network coding based binary search tree algorithm(PNBA)is proposed in this paper.PNBA pushes the conflicting signal information of multiple tags into a stack,which is discarded by the traditional anti-collision algorithm.In addition,physical layer network coding is exploited by PNBA to obtain unread tag information through the decoding operation of physical layer network coding using the conflicting information in the stack.Therefore,PNBA reduces the number of interactions between reader and tags,and improves the tags identification efficiency.Theoretical analysis and simulation results using MATLAB demonstrate that PNBA reduces the number of readings,and improve RFID identification efficiency.Especially,when the number of tags to be identified is 100,the average needed reading number of PNBA is 83%lower than the basic binary search tree algorithm,43%lower than reverse binary search tree algorithm,and its reading efficiency reaches 0.93.
基金supported by the National Natural Science Foundation of China under Grant No.61371075the 863 project SS2015AA011306
文摘The tremendous performance gain of heterogeneous networks(Het Nets) is at the cost of complicated resource allocation. Considering information security, the resource allocation for Het Nets becomes much more challenging and this is the focus of this paper. In this paper, the eavesdropper is hidden from the macro base stations. To relax the unpractical assumption on the channel state information on eavesdropper, a localization based algorithm is first given. Then a joint resource allocation algorithm is proposed in our work, which simultaneously considers physical layer security, cross-tier interference and joint optimization of power and subcarriers under fairness requirements. It is revealed in our work that the considered optimization problem can be efficiently solved relying on convex optimization theory and the Lagrangian dual decomposition method is exploited to solve the considered problem effectively. Moreover, in each iteration the closed-form optimal resource allocation solutions can be obtained based on the Karush-Kuhn-Tucker(KKT) conditions. Finally, the simulation results are given to show the performance advantages of the proposed algorithm.
文摘With the advent of physics informed neural networks(PINNs),deep learning has gained interest for solving nonlinear partial differential equations(PDEs)in recent years.In this paper,physics informed memory networks(PIMNs)are proposed as a new approach to solving PDEs by using physical laws and dynamic behavior of PDEs.Unlike the fully connected structure of the PINNs,the PIMNs construct the long-term dependence of the dynamics behavior with the help of the long short-term memory network.Meanwhile,the PDEs residuals are approximated using difference schemes in the form of convolution filter,which avoids information loss at the neighborhood of the sampling points.Finally,the performance of the PIMNs is assessed by solving the Kd V equation and the nonlinear Schr?dinger equation,and the effects of difference schemes,boundary conditions,network structure and mesh size on the solutions are discussed.Experiments show that the PIMNs are insensitive to boundary conditions and have excellent solution accuracy even with only the initial conditions.
基金supported by the National Natural Science Foundation of China(Grant Nos.1217211 and 12372244).
文摘Physics informed neural networks(PINNs)are a deep learning approach designed to solve partial differential equations(PDEs).Accurately learning the initial conditions is crucial when employing PINNs to solve PDEs.However,simply adjusting weights and imposing hard constraints may not always lead to better learning of the initial conditions;sometimes it even makes it difficult for the neural networks to converge.To enhance the accuracy of PINNs in learning the initial conditions,this paper proposes a novel strategy named causally enhanced initial conditions(CEICs).This strategy works by embedding a new loss in the loss function:the loss is constructed by the derivative of the initial condition and the derivative of the neural network at the initial condition.Furthermore,to respect the causality in learning the derivative,a novel causality coefficient is introduced for the training when selecting multiple derivatives.Additionally,because CEICs can provide more accurate pseudo-labels in the first subdomain,they are compatible with the temporal-marching strategy.Experimental results demonstrate that CEICs outperform hard constraints and improve the overall accuracy of pre-training PINNs.For the 1D-Korteweg–de Vries,reaction and convection equations,the CEIC method proposed in this paper reduces the relative error by at least 60%compared to the previous methods.
基金funded by Beijing University of Posts and Telecommunications-China Mobile Research Institute Joint Innovation Center,the National Key R&D Program of China(2018YFE0205503)the National Natural Science Foundation of China(61902036,62032003,61922017)Fundamental Research Funds for the Central Universities。
文摘5G is envisioned to guarantee high transmission rate,ultra-low latency,high reliability and massive connections.To satisfy the above requirements,the 5G architecture is designed with the properties of using service-based architecture,cloud-native oriented,adopting IT-based API interfaces and introduction of the Network Repository Function.However,with the wide commercialization of 5G network and the exploration towards 6G,the 5G architecture exposes the disadvantages of high architecture complexity,difficult inter-interface communication,low cognitive capability,bad instantaneity,and deficient intelligence.To overcome these limitations,this paper investigates 6G network architecture,and proposes a cognitive intelligence based distributed 6G network architecture.This architecture consists of a physical network layer and an intelligent decision layer.The two layers coordinate through flexible service interfaces,supporting function decoupling and joint evolution of intelligence services and network services.With the above design,the proposed 6G architecture can be updated autonomously to deal with the future unpredicted complex services.
文摘A novel identification method of aerodynamicmodels using a physics neural network,named the attitude dynamics network,which incorporates the attitude dynamics of an aircraft without any prior aerodynamic knowledge,is proposed.Then a learning controller,which combines feedback linearization with sliding mode control,is developed by introducing the learned aerodynamicmodels.The merit of the identification method is that the aerodynamicmodels can be learned end-to-end by the physics network directly from the flight data.Consequently,the paper uses an offline scheme and an online scheme to combine the identification process and the control process.In the offline scheme,learning the aerodynamic models and controlling the aircraft compose a cascade system,whereas the online scheme,similar to Learn-to-Fly,is a parallel system.Specifically,in the offline scheme,the physics neural network is trained by sufficient offline flight data,and then the trained network is substituted into the controller.The online scheme refers to the controller making the aircraft fly to generate flight data and sending these data to the deep network at the time of training,while the deep network provides the trained aerodynamic models to the controller at other times.Simulation results show that both under nominal and disturbance aerodynamic conditions,the network trained offline with a large amount of nominal data approximate the aerodynamicmodels well.Thus,the performance of the controller reaches a good level;for the online scheme,the predictive capability of the network increases and the performance of the controller improves with more training data.
基金Project supported by the National Key Research and Development Program of China(Grant No.2020YFC1807905)the National Natural Science Foundation of China(Grant Nos.52079090 and U20A20316)the Basic Research Program of Qinghai Province(Grant No.2022-ZJ-704).
文摘Neural network methods have been widely used in many fields of scientific research with the rapid increase of computing power.The physics-informed neural networks(PINNs)have received much attention as a major breakthrough in solving partial differential equations using neural networks.In this paper,a resampling technique based on the expansion-shrinkage point(ESP)selection strategy is developed to dynamically modify the distribution of training points in accordance with the performance of the neural networks.In this new approach both training sites with slight changes in residual values and training points with large residuals are taken into account.In order to make the distribution of training points more uniform,the concept of continuity is further introduced and incorporated.This method successfully addresses the issue that the neural network becomes ill or even crashes due to the extensive alteration of training point distribution.The effectiveness of the improved physics-informed neural networks with expansion-shrinkage resampling is demonstrated through a series of numerical experiments.
基金supported by the Researchers Supporting Project number (RSPD2024R526),King Saud University,Riyadh,Saudi Arabi.
文摘Heat transport has been significantly enhanced by the widespread usage of extended surfaces in various engi-neering domains.Gas turbine blade cooling,refrigeration,and electronic equipment cooling are a few prevalent applications.Thus,the thermal analysis of extended surfaces has been the subject of a significant assessment by researchers.Motivated by this,the present study describes the unsteady thermal dispersal phenomena in a wavy fin with the presence of convection heat transmission.This analysis also emphasizes a novel mathematical model in accordance with transient thermal change in a wavy profiled fin resulting from convection using the finite difference method(FDM)and physics informed neural network(PINN).The time and space-dependent governing partial differential equation(PDE)for the suggested heat problem has been translated into a dimensionless form using the relevant dimensionless terms.The graph depicts the effect of thermal parameters on the fin’s thermal profile.The temperature dispersion in the fin decreases as the dimensionless convection-conduction variable rises.The heat dispersion in the fin is decreased by increasing the aspect ratio,whereas the reverse behavior is seen with the time change.Furthermore,FDM-PINN results are validated against the outcomes of the FDM.
基金the support from NSF DMS-1816783NVIDIA Corporation for their donation of a Quadro P6000 GPU for conducting some of the numerical simulations in this paper.
文摘In this paper,we introduce a new deep learning framework for discovering the phase-field models from existing image data.The new framework embraces the approximation power of physics informed neural networks(PINNs)and the computational efficiency of the pseudo-spectral methods,which we named pseudo-spectral PINN or SPINN.Unlike the baseline PINN,the pseudo-spectral PINN has several advantages.First of all,it requires less training data.A minimum of two temporal snapshots with uniform spatial resolution would be adequate.Secondly,it is computationally efficient,as the pseudo-spectral method is used for spatial discretization.Thirdly,it requires less trainable parameters compared with the baseline PINN,which significantly simplifies the training process and potentially assures fewer local minima or saddle points.We illustrate the effectiveness of pseudo-spectral PINN through several numerical examples.The newly proposed pseudo-spectral PINN is rather general,and it can be readily applied to discover other FDE-based models from image data.
基金supported by the National Key Research and Development Program of China(2021YFB2104800)the National Natural Science Foundation of China(62103411,62436010,72171230)the Science and Technology Development Fund of Macao SAR(0093/2023/RIA2,0050/2020/A1).
文摘This paper introduces federated services as a smart service ecology with federated security to align distributed data supply with diversified service demands spanning digital and societal contexts.It presents the comprehensive researches on the theoretical foundation and technical system of federated services,aiming at advancing our understanding and implementation of this novel service paradigm.First,a thorough examination of the characteristics of federated security within federated services is conducted.Then,a five-layer technical framework is formulated under a decentralized intelligent architecture,ensuring secure,agile,and adaptable service provision.On this basis,the operational mechanisms underlying data federation and service confederation is analyzed,with emphasis on the smart supply-demand matching model.Furthermore,a scenario-oriented taxonomy of federated services accompanied by illustrative examples is proposed.Our work offers actionable insights and roadmap for realizing and advancing federated services,contributing to the refinement and wider adoption of this transformative service paradigm in the digital era.
基金This work was supported by the National Natural Science Foundation of China(Grant No.52006232)the Youth Innovation Promotion Association of Chinese Academy of Sciences(Grant No.2019020)。
基金financially supported by the National Natural Science Foundation of China (Nos. 21574070 and 21774063)Natural Science Foundation of Tianjin (No. 16JCZDJC36800)
文摘The synthesis of a new azobenzene(azo)-containing main-chain crystalline polymer with reactive secondary amino groups in its backbone and photodeformation behaviors of its supramolecular hydrogen-bonded fibers are described. This main-chain azo polymer(namely Azo-MP6) was prepared via first the synthesis of a diacrylate-type azo monomer and its subsequent Michael addition copolymerization with trans-1,4-cyclohexanediamine under a mild reaction condition. Azo-MP6 was found to have a linear main-chain chemical structure instead of a branched one, as verified by comparing its ~1H-NMR spectrum with that of the azo polymer prepared via the polymer analogous reaction of AzoMP6 with acetic anhydride. The thermal stability, phase transition behavior, and photoresponsivity of Azo-MP6 were characterized with TGA,DSC, POM, XRD, and UV-Vis spectroscopy. The experimental results revealed that it had good thermal stability, low glass transition temperature,broad crystalline phase temperature range, and highly reversible photoresponsivity. Physically crosslinked supramolecular hydrogen-bonded fibers with good mechanical properties and a high alignment order of azo mesogens were readily fabricated from Azo-MP6 by using the simple melt spinning method, and they could show "reversible" photoinduced bending under the same UV light irradiation and good anti-fatigue properties.
基金supported in part by the National Key Research and Development Program of China(Basic Research Class 2017YFB0903000)the National Natural Science Foundation of China(51677116)the Science and Technology Project of State Grid Corporation of China:Basic Theory and Method of Analysis and Control of Cyber Physical System for Power Grid(Supporting Project).
文摘With the access to large amounts of renewable energy sources(RES),operation uncertainty of distribution networks increases significantly.Fortunately,adopting advanced information and communication technology,a cyber-physical distribution network(CPDS)provides the possibility to solve this problem via aggregative management of decentralized controllable loads.However,information flow in cyber space deeply interacts with energy flow in physical space,leading to a complexity in modeling,design and analysis of the whole control process.To deal with this problem,a general hybrid flow model of CPDS is first proposed in this paper.In this model,the control process is abstracted into interactions among three types of cyber nodes through cyber branches.The mathematic model of cyber nodes and branches is developed as well as that of the controlled physical object for hybrid flow computation.Then,based on the hybrid model,an instantiated application to compensate feeder power deviation caused by RES fluctuation through aggregative control of large-scale air-conditioners(ACs)is investigated.In this application,coordinative control of the AC cluster is achieved through a decentralized control strategy with very little communication cost and very good privacy protection.Results of numerical examples verify the correctness and flexibility of the hybrid flow model in reflecting interactions between cyber flow and energy flow as well as system operations.The proposed decentralized control strategy of the AC cluster is also proven to be effective and robust in FCE compensation.
基金supported by the National Natural Science Foundation of China(Grant No.91852117)the foundation of National Key Laboratory of Science and Technology on Aerodynamic Design and Research(Grant No.614220121040106)Shanghai Rising-Star Program(Grant No.19QC1400200)。
基金supported by the National Key Research and Development Program of China(Grant Nos.2022YFA1403300,and 2020YFA0309100)the National Natural Science Foundation of China(Grant Nos.12204107,and 12074073)+2 种基金Shanghai Municipal Science and Technology Major Project(Grant No.2019SHZDZX01)Shanghai Pujiang Program(Grant No.21PJ1401500)Shanghai Science and Technology Committee(Grant Nos.21JC1406200,and 20JC1415900)。
文摘Physical neural networks are artificial neural networks that mimic synapses and neurons using physical systems or materials.These networks harness the distinctive characteristics of physical systems to carry out computations effectively,potentially surpassing the constraints of conventional digital neural networks.A recent advancement known as“physical self-learning”aims to achieve learning through intrinsic physical processes rather than relying on external computations.This article offers a comprehensive review of the progress made in implementing physical self-learning across various physical systems.Prevailing learning strategies that contribute to the realization of physical self-learning are discussed.Despite challenges in understanding the fundamental mechanism of learning,this work highlights the progress towards constructing intelligent hardware from the ground up,incorporating embedded self-organizing and self-adaptive dynamics in physical systems.
基金supported by the International Scientific and Technological Cooperation Program (S2010GR0902)
文摘Systems are always designed and optimized based on full traffic load in the current literatures. However, practical systems are seldom operating at full load, even at peak traffic hours. Instead of maximizing system rate to achieve the full load, an optimal energy-efficient scheme to minimize the transmit power with required rates is investigated in this article. The considered scenario is a two-way relay channel using amplify-and-forward protocol of physical layer network coding, where two end nodes exchange messages via multiple relay nodes within two timeslots. A joint power allocation and relay selection scheme is designed to achieve the minimum transmit power. Through convex optimization theory, we firstly prove that single relay selection scheme is the most energy-efficient way for physical layer network coding. The closed-form expressions of power allocation are also given. Numerical simulations demonstrate the performance of the designed scheme as well as the comparison among different schemes.
基金Supported in part by the NSF CNS Award (No. 1143602)
文摘Previous research on security of network coding focused on the protection of data dissemination procedures and the detection of malicious activities such as pollution attacks. The capabilities of network coding to detect other attacks have not been fully explored. In this paper, we propose a new mechanism based on physical layer network coding to detect wormhole attacks. When two signal sequences collide at the receiver, the starting point of the collision is determined by the distances between the receiver and the senders. Therefore, by comparing the starting points of the collisions at two receivers, we can estimate the distance between them and detect fake neighbor connections via wormholes. While the basic idea is clear, we have proposed several schemes at both physical and network layers to transform the idea into a practical approach. Simulations using BPSK modulation at the physical layer show that the wireless nodes can effectively detect fake neighbor connections without the adoption of special hardware or time synchronization.
