Human motion modeling is a core technology in computer animation,game development,and humancomputer interaction.In particular,generating natural and coherent in-between motion using only the initial and terminal frame...Human motion modeling is a core technology in computer animation,game development,and humancomputer interaction.In particular,generating natural and coherent in-between motion using only the initial and terminal frames remains a fundamental yet unresolved challenge.Existing methods typically rely on dense keyframe inputs or complex prior structures,making it difficult to balance motion quality and plausibility under conditions such as sparse constraints,long-term dependencies,and diverse motion styles.To address this,we propose a motion generation framework based on a frequency-domain diffusion model,which aims to better model complex motion distributions and enhance generation stability under sparse conditions.Our method maps motion sequences to the frequency domain via the Discrete Cosine Transform(DCT),enabling more effective modeling of low-frequency motion structures while suppressing high-frequency noise.A denoising network based on self-attention is introduced to capture long-range temporal dependencies and improve global structural awareness.Additionally,a multi-objective loss function is employed to jointly optimize motion smoothness,pose diversity,and anatomical consistency,enhancing the realism and physical plausibility of the generated sequences.Comparative experiments on the Human3.6M and LaFAN1 datasets demonstrate that our method outperforms state-of-the-art approaches across multiple performance metrics,showing stronger capabilities in generating intermediate motion frames.This research offers a new perspective and methodology for human motion generation and holds promise for applications in character animation,game development,and virtual interaction.展开更多
Accurate traffic flow prediction has a profound impact on modern traffic management. Traffic flow has complex spatial-temporal correlations and periodicity, which poses difficulties for precise prediction. To address ...Accurate traffic flow prediction has a profound impact on modern traffic management. Traffic flow has complex spatial-temporal correlations and periodicity, which poses difficulties for precise prediction. To address this problem, a Multi-head Self-attention and Spatial-Temporal Graph Convolutional Network (MSSTGCN) for multiscale traffic flow prediction is proposed. Firstly, to capture the hidden traffic periodicity of traffic flow, traffic flow is divided into three kinds of periods, including hourly, daily, and weekly data. Secondly, a graph attention residual layer is constructed to learn the global spatial features across regions. Local spatial-temporal dependence is captured by using a T-GCN module. Thirdly, a transformer layer is introduced to learn the long-term dependence in time. A position embedding mechanism is introduced to label position information for all traffic sequences. Thus, this multi-head self-attention mechanism can recognize the sequence order and allocate weights for different time nodes. Experimental results on four real-world datasets show that the MSSTGCN performs better than the baseline methods and can be successfully adapted to traffic prediction tasks.展开更多
Microrobots powered by an external magnetic field could be used for sophisticated medical applications such as cell treatment,micromanipulation,and noninvasive surgery inside the body.Untethered microrobot application...Microrobots powered by an external magnetic field could be used for sophisticated medical applications such as cell treatment,micromanipulation,and noninvasive surgery inside the body.Untethered microrobot applications can benefit from haptic technology and telecommunication,enabling telemedical micro-manipulation.Users can manipulate the microrobots with haptic feedback by interacting with the robot operating system remotely in such applications.Artificially created haptic forces based on wirelessly transmitted data and model-based guidance can aid human operators with haptic sensations while manipulating microrobots.The system presented here includes a haptic device and a magnetic tweezer system linked together using a network-based teleoperation method with motion models in fluids.The magnetic microrobots can be controlled remotely,and the haptic interactions with the remote environment can be felt in real time.A time-domain passivity controller is applied to overcome network delay and ensure stability of communication.This study develops and tests a motion model for microrobots and evaluates two image-based 3D tracking algorithms to improve tracking accuracy in various Newtonian fluids.Additionally,it demonstrates that microrobots can group together to transport multiple larger objects,move through microfluidic channels for detailed tasks,and use a novel method for disassembly,greatly expanding their range of use in microscale operations.Remote medical treatment in multiple locations,remote delivery of medication without the need for physical penetration of the skin,and remotely controlled cell manipulations are some of the possible uses of the proposed technology.展开更多
To mill fine and well-defined micro-dimpled structures,a machining manner of spiral trajectory tool reciprocating motion,where the tool repeats the process of‘feed milling–retract–cutting feed–feed milling again’...To mill fine and well-defined micro-dimpled structures,a machining manner of spiral trajectory tool reciprocating motion,where the tool repeats the process of‘feed milling–retract–cutting feed–feed milling again’along the spiral trajectory,was proposed.From the kinematics analysis,it is found that the machining quality of micro-dimpled structures is highly dependent on the machining trajectory using spiral trajectory tool reciprocating motion.To reveal this causation,simulation modelling and experimental studies were carried out.A simulation model was developed to quantitatively and qualitatively investigate the influence of the trajectory discretization strategies(constant-angle and constant-arc length)and parameters(discrete angle,discrete arc length,and pitch)on surface texture and residual height of micro-dimpled structures.Subsequently,micro-dimpled structures were milled under different trajectory discretization strategies and parameters with spiral trajectory tool reciprocating motion.A comprehensive comparison between the milled results and simulation analysis was made based on geometry accuracy,surface morphology and surface roughness of milled dimples.Meanwhile,the errors and factors affecting the above three aspects were analyzed.The results demonstrate both the feasibility of the established simulation model and the machining capability of this machining way in milling high-quality micro-dimpled structures.Spiral trajectory tool reciprocating motion provides a new machining way for milling micro-dimpled structures and micro-dimpled functional surfaces.And an appropriate machining trajectory can be generated based on the optimized trajectory parameters,thus contributing to the improvement of machining quality and efficiency.展开更多
Basin effect was first described following the analysis of seismic ground motion associated with the 1985 MW8.1 earthquake in Mexico.Basins affect the propagation of seismic waves through various mechanisms,and severa...Basin effect was first described following the analysis of seismic ground motion associated with the 1985 MW8.1 earthquake in Mexico.Basins affect the propagation of seismic waves through various mechanisms,and several unique phenomena,such as the basin edge effect,basin focusing effect,and basin-induced secondary waves,have been observed.Understanding and quantitatively predicting these phenomena are crucial for earthquake disaster reduction.Some pioneering studies in this field have proposed a quantitative relationship between the basin effect on ground motion and basin depth.Unfortunately,basin effect phenomena predicted using a model based only on basin depth exhibit large deviations from actual distributions,implying the severe shortcomings of single-parameter basin effect modeling.Quaternary sediments are thick and widely distributed in the Beijing-Tianjin-Hebei region.The seismic media inside and outside of this basin have significantly different physical properties,and the basin bottom forms an interface with strong seismic reflections.In this study,we established a three-dimensional structure model of the Quaternary sedimentary basin based on the velocity structure model of the North China Craton and used it to simulate the ground motion under a strong earthquake following the spectral element method,obtaining the spatial distribution characteristics of the ground motion amplification ratio throughout the basin.The back-propagation(BP)neural network algorithm was then introduced to establish a multi-parameter mathematical model for predicting ground motion amplification ratios,with the seismic source location,physical property ratio of the media inside and outside the basin,seismic wave frequency,and basin shape as the input parameters.We then examined the main factors influencing the amplification of seismic ground motion in basins based on the prediction results,and concluded that the main factors influencing the basin effect are basin shape and differences in the physical properties of media inside and outside the basin.展开更多
Human trajectory prediction is essential and promising in many related applications. This is challenging due to the uncertainty of human behaviors, which can be influenced not only by himself, but also by the surround...Human trajectory prediction is essential and promising in many related applications. This is challenging due to the uncertainty of human behaviors, which can be influenced not only by himself, but also by the surrounding environment. Recent works based on long-short term memory(LSTM) models have brought tremendous improvements on the task of trajectory prediction. However, most of them focus on the spatial influence of humans but ignore the temporal influence. In this paper, we propose a novel spatial-temporal attention(ST-Attention) model,which studies spatial and temporal affinities jointly. Specifically,we introduce an attention mechanism to extract temporal affinity,learning the importance for historical trajectory information at different time instants. To explore spatial affinity, a deep neural network is employed to measure different importance of the neighbors. Experimental results show that our method achieves competitive performance compared with state-of-the-art methods on publicly available datasets.展开更多
The goal of this paper is to develop a unified online motion generation scheme for quadruped lateral-sequence walk and trot gaits based on a linear model predictive control formulation.Specifically,the dynamics of the...The goal of this paper is to develop a unified online motion generation scheme for quadruped lateral-sequence walk and trot gaits based on a linear model predictive control formulation.Specifically,the dynamics of the linear pendulum model is formulated over a predictive horizon by dimensional analysis.Through gait pattern conversion,the lateral-sequence walk and trot gaits of the quadruped can be regarded as unified biped gaits,allowing the dynamics of the linear inverted pendulum model to serve quadruped motion generation.In addition,a simple linearization of the center of pressure constraints for these quadruped gaits is developed for linear model predictive control problem.Furthermore,the motion generation problem can be solved online by quadratic programming with foothold adaptation.It is demonstrated that the proposed unified scheme can generate stable locomotion online for quadruped lateral-sequence walk and trot gaits,both in simulation and on hardware.The results show significant performance improvements compared to previous work.Moreover,the results also suggest the linearly simplified scheme has the ability to robustness against unexpected disturbances.展开更多
In this paper, the online parameter identification problem of the mathematical model of an unmanned surface vehicle (USV) considering the characteristics of the actuator is studied. A data-driven mathematical model of...In this paper, the online parameter identification problem of the mathematical model of an unmanned surface vehicle (USV) considering the characteristics of the actuator is studied. A data-driven mathematical model of motion is very meaningful to realize trajectory prediction and adaptive motion control of the USV. An interactive identification algorithm (ESO–MILS, extended state observer–multi-innovation least squares) based on ESO is proposed. The robustness of online identification is improved by expanding the state observer to estimate the current disturbance without making artificial assumptions. Specifically, the three-degree-of-freedom dynamic equation of the double propeller propulsion USV is constructed. A linear model for online identification is derived by parameterization. Based on the least square criterion function, it is proved that the interactive identification method with disturbance estimation can improve the identification accuracy from the perspective of mathematical expectation. The extended state observer is designed to estimate the unknown disturbance in the model. The online interactive update improves the disturbance immunity of the identification algorithm. Finally, the effectiveness of the interactive identification algorithm is verified by simulation experiment and real ship experiment.展开更多
Internal learning-based video inpainting methods have shown promising results by exploiting the intrinsic properties of the video to fill in the missing region without external dataset supervision.However,existing int...Internal learning-based video inpainting methods have shown promising results by exploiting the intrinsic properties of the video to fill in the missing region without external dataset supervision.However,existing internal learning-based video inpainting methods would produce inconsistent structures or blurry textures due to the insufficient utilisation of motion priors within the video sequence.In this paper,the authors propose a new internal learning-based video inpainting model called appearance consistency and motion coherence network(ACMC-Net),which can not only learn the recurrence of appearance prior but can also capture motion coherence prior to improve the quality of the inpainting results.In ACMC-Net,a transformer-based appearance network is developed to capture global context information within the video frame for representing appearance consistency accurately.Additionally,a novel motion coherence learning scheme is proposed to learn the motion prior in a video sequence effectively.Finally,the learnt internal appearance consistency and motion coherence are implicitly propagated to the missing regions to achieve inpainting well.Extensive experiments conducted on the DAVIS dataset show that the proposed model obtains the superior performance in terms of quantitative measurements and produces more visually plausible results compared with the state-of-the-art methods.展开更多
Coalbed methane(CBM)is a vital unconventional energy resource,and predicting its spatiotemporal pressure dynamics is crucial for efficient development strategies.This paper proposes a novel deep learningebased data-dr...Coalbed methane(CBM)is a vital unconventional energy resource,and predicting its spatiotemporal pressure dynamics is crucial for efficient development strategies.This paper proposes a novel deep learningebased data-driven surrogate model,AxialViT-ConvLSTM,which integrates AxialAttention Vision Transformer,ConvLSTM,and an enhanced loss function to predict pressure dynamics in CBM reservoirs.The results showed that the model achieves a mean square error of 0.003,a learned perceptual image patch similarity of 0.037,a structural similarity of 0.979,and an R^(2) of 0.982 between predictions and actual pressures,indicating excellent performance.The model also demonstrates strong robustness and accuracy in capturing spatialetemporal pressure features.展开更多
On the basis of the model tests,this paper explores the coupled hydrodynamic performance of the moonpool and the hull.This study aims to compare and analyze the variation in the hull heave response between the piston ...On the basis of the model tests,this paper explores the coupled hydrodynamic performance of the moonpool and the hull.This study aims to compare and analyze the variation in the hull heave response between the piston resonance state of the moonpool under wave excitation and the non-resonance state of the moonpool under wave-current excitation.A novel damping device specifically designed and fabricated for stepped moonpools has been developed.Before and after the installation of the damping device,the free surface response characteristics of the moonpool and heave motion response characteristics of the hull are compared.The findings show a clear correlation between the current speed and heave response characteristics of the hull.During the seakeeping design phase of the drilling vessel,the current speed is an additional critical factor that cannot be disregarded,alongside the moonpool effect.A correlation exists between the fluid dynamics occurring within the moonpool and the heave motion of the vessel hull.A reduction in the amplitude of the motion of the moonpool water results in a decrease in the heave motion of the hull.This study provides a reference for alleviating the seakeeping of a drill ship’s heave response and enhancing the safety and efficiency of the operation.展开更多
The design and analysis of continuum robots have consistently been a prominent research focus in the field of mechanics.However,portable continuum robots with minimal spatial occupancy,which have great potential for a...The design and analysis of continuum robots have consistently been a prominent research focus in the field of mechanics.However,portable continuum robots with minimal spatial occupancy,which have great potential for applications such as search and rescue,are scarcely available.This paper presents a novel helical-coiled multi-segment flexible continuum robot featuring helical deployment and compact design,with an integrated framework for structural design,kinematic modeling,and experimental validation.The design of the helical-coiled multi-segment flexible continuum robot for unstructured environment detection,including a flexible body,an actuation module,a feed module,and a sensing module,is presented systematically.Kinematic models of both single-and multisegment continuum robots were established based on the constant curvature model to analyze the parameter mapping relationship from the end-effector position and orientation to the driving inputs.Furthermore,the feedforward motion of the robot was examined,and an uncoiling strategy based on S-curve compensation was employed to complete the kinematic analysis.Finally,the accuracy of the kinematic model considering the active uncoiling feed motion was validated through experimental analysis,demonstrating the motion characteristics of the continuum robot.Altogether,this study provides a framework for the design and analysis of helical-coiled continuum robots.展开更多
The intelligent vehicle corner module system,which integrates four-wheel independent drive,independent steering,independent braking and active suspension,can accurately and efficiently perform vehicle driving tasks an...The intelligent vehicle corner module system,which integrates four-wheel independent drive,independent steering,independent braking and active suspension,can accurately and efficiently perform vehicle driving tasks and is the best carrier of intelligent vehicles.Nevertheless,too many angle/torque control inputs make control difficult and non-real-time.In this paper,a hierarchical real-time motion control framework for corner module configuration intelligent electric vehicles is proposed.In the trajectory planning module,an improved driving risk field is designed to describe the surrounding environment’s driving risk.Combined with the kinematic vehicle-road model,model predictive control(MPC)method,spline curve method,the local reference trajectory of safety,comfort and smoothness is planned in real time.The optimal steering angle is determined using MPC method in path tracking module.In the motion control module,a feedforward-feedback controller assigns the optimal steering angle to the front/rear axles,and an angle allocation controller distributes the target angles of the front/rear axles to four steered wheels.Finally,the PreScan-Simulink-CarSim joint simulation environment is established for conducting the human-in-the-loop emergency obstacle avoidance experiment.It took only 0.005 s for the hierarchical motion control system to determine its average solution time.This proves the effectiveness of the hierarchical motion control system.展开更多
The prediction and compensation control of marine ship motion is crucial for ensuring the safety of offshore wind turbine loading and unloading operations.However,the accuracy of prediction and control is significantl...The prediction and compensation control of marine ship motion is crucial for ensuring the safety of offshore wind turbine loading and unloading operations.However,the accuracy of prediction and control is significantly affected by the hysteresis phenomenon in the wave compensation system.To address this issue,a ship heave motion prediction is proposed in this paper on the basis of the Gauss-DeepAR(AR stands for autoregressive recurrent)model and the Hilbert−Huang time-delay compensation control strategy.Initially,the zero upward traveling wave period of the level 4−6 sea state ship heave motion is analyzed,which serves as the input sliding window for the Gauss-DeepAR prediction model,and probability predictions at different wave direction angles are conducted.Next,considering the hysteresis characteristics of the ship heave motion compensation platform,the Hilbert−Huang transform is employed to analyze and calculate the hysteresis delay of the compensation platform.After the optimal control action value is subsequently calculated,simulations and hardware platform tests are conducted.The simulation results demonstrated that the Gauss-DeepAR model outperforms autoregressive integrated moving average model(ARIMA),support vector machine(SVM),and longshort-term memory(LSTM)in predicting non-independent identically distributed datasets at a 90°wave direction angle in the level 4−6 sea states.Furthermore,the model has good predictive performance and generalizability for non-independent and non-uniformly distributed datasets at a 180°wave direction angle.The hardware platform compensation test results revealed that the Hilbert–Huang method has an outstanding effect on determining the hysteretic delay and selecting the optimal control action value,and the compensation efficiency was higher than 90%in the level 4−6 sea states.展开更多
Based on the Timoshenko beam theory,this paper proposes a nonlocal bi-gyroscopic model for spinning functionally graded(FG)nanotubes conveying fluid,and the thermal–mechanical vibration and stability of such composit...Based on the Timoshenko beam theory,this paper proposes a nonlocal bi-gyroscopic model for spinning functionally graded(FG)nanotubes conveying fluid,and the thermal–mechanical vibration and stability of such composite nanostructures under small scale,rotor,and temperature coupling effects are investigated.The nanotube is composed of functionally graded materials(FGMs),and different volume fraction functions are utilized to control the distribution of material properties.Eringen’s nonlocal elasticity theory and Hamilton’s principle are applied for dynamical modeling,and the forward and backward precession frequencies as well as 3D mode configurations of the nanotube are obtained.By conducting dimensionless analysis,it is found that compared to the Timoshenko nano-beam model,the conventional Euler–Bernoulli(E-B)model holds the same flutter frequency in the supercritical region,while it usually overestimates the higher-order precession frequencies.The nonlocal,thermal,and flowing effects all can lead to buckling or different kinds of coupled flutter in the system.The material distribution of the P-type FGM nanotube can also induce coupled flutter,while that of the S-type FGM nanotube has no impact on the stability of the system.This paper is expected to provide a theoretical foundation for the design of motional composite nanodevices.展开更多
This paper develops an Ito-type fractional pathwise integration theory for fractional Brownian motion with Hurst parameters H∈(1/3,1/2],using the Lyons'rough path framework.This approach is designed to fill gaps ...This paper develops an Ito-type fractional pathwise integration theory for fractional Brownian motion with Hurst parameters H∈(1/3,1/2],using the Lyons'rough path framework.This approach is designed to fill gaps in conventional stochastic calculus models that fail to account for temporal persistence prevalent in dynamic systems such as those found in economics,finance,and engineering.The pathwise-defined method not only meets the zero expectation criterion but also addresses the challenges of integrating non-semimartingale processes,which traditional Ito calculus cannot handle.We apply this theory to fractional Black–Scholes models and high-dimensional fractional Ornstein–Uhlenbeck processes,illustrating the advantages of this approach.Additionally,the paper discusses the generalization of It?integrals to rough differential equations(RDE)driven by f BM,emphasizing the necessity of integrand-specific adaptations in the It?rough path lift for stochastic modeling.展开更多
Captive model tests are one of the most common methods to calculate the maneuvering hydrodynamic coefficients and characteristics of surface and underwater vehicles.Considerable attention must be paid to selecting and...Captive model tests are one of the most common methods to calculate the maneuvering hydrodynamic coefficients and characteristics of surface and underwater vehicles.Considerable attention must be paid to selecting and designing the most suitable laboratory equipment for towing tanks.A computational fluid dynamics(CFD)-based method is implemented to determine the loads acting on the towing facility of the submarine model.A reversed topology is also used to ensure the appropriateness of the load cells in the developed method.In this study,the numerical simulations were evaluated using the experimental results of the SUBOFF benchmark submarine model of the Defence Advanced Research Projects Agency.The maximum and minimum loads acting on the 2.5-meter submarine model were measured by determining the body’s lightest and heaviest maneuvering test scenarios.In addition to having sufficient endurance against high loads,the precision in measuring the light load was also investigated.The horizontal planar motion mechanism(HPMM)facilities in the National Iranian Marine Laboratory were developed by locating the load cells inside the submarine model.The results were presented as a case study.A numerical-based method was developed to obtain the appropriate load measurement facilities.Load cells of HPMM test basins can be selected by following the two-way procedure presented in this study.展开更多
Currently,there are a limited number of dynamic models available for braided composite plates with large overall motions,despite the incorporation of three-dimensional(3D)braided composites into rotating blade compone...Currently,there are a limited number of dynamic models available for braided composite plates with large overall motions,despite the incorporation of three-dimensional(3D)braided composites into rotating blade components.In this paper,a dynamic model of 3D 4-directional braided composite thin plates considering braiding directions is established.Based on Kirchhoff's plate assumptions,the displacement variables of the plate are expressed.By incorporating the braiding directions into the constitutive equation of the braided composites,the dynamic model of the plate considering braiding directions is obtained.The effects of the speeds,braiding directions,and braided angles on the responses of the plate with fixed-axis rotation and translational motion,respectively,are investigated.This paper presents a dynamic theory for calculating the deformation of 3D braided composite structures undergoing both translational and rotational motions.It also provides a simulation method for investigating the dynamic behavior of non-isotropic material plates in various applications.展开更多
This work investigates water-based micropolar hybrid nanofluid(MHNF) flow on an elongating variable porous sheet.Nanoparticles of diamond and copper have been used in the water to boost its thermal conductivity. The m...This work investigates water-based micropolar hybrid nanofluid(MHNF) flow on an elongating variable porous sheet.Nanoparticles of diamond and copper have been used in the water to boost its thermal conductivity. The motion of the fluid is taken as two-dimensional with the impact of a magnetic field in the normal direction. The variable, permeable, and stretching nature of sheet's surface sets the fluid into motion. Thermal and mass diffusions are controlled through the use of the Cattaneo–Christov flux model. A dataset is generated using MATLAB bvp4c package solver and employed to train an artificial neural network(ANN) based on the Levenberg–Marquardt back-propagation(LMBP) algorithm. It has been observed as an outcome of this study that the modeled problem achieves peak performance at epochs 637, 112, 4848, and 344 using ANN-LMBP. The linear velocity of the fluid weakens with progression in variable porous and magnetic factors.With an augmentation in magnetic factor, the micro-rotational velocity profiles are augmented on the domain 0 ≤ η < 1.5 due to the support of micro-rotations by Lorentz forces close to the sheet's surface, while they are suppressed on the domain 1.5 ≤ η < 6.0 due to opposing micro-rotations away from the sheet's surface. Thermal distributions are augmented with an upsurge in thermophoresis, Brownian motion, magnetic, and radiation factors, while they are suppressed with an upsurge in thermal relaxation parameter. Concentration profiles increase with an expansion in thermophoresis factor and are suppressed with an intensification of Brownian motion factor and solute relaxation factor. The absolute errors(AEs) are evaluated for all the four scenarios that fall within the range 10^(-3)–10^(-8) and are associated with the corresponding ANN configuration that demonstrates a fine degree of accuracy.展开更多
基金supported by the National Natural Science Foundation of China(Grant No.72161034).
文摘Human motion modeling is a core technology in computer animation,game development,and humancomputer interaction.In particular,generating natural and coherent in-between motion using only the initial and terminal frames remains a fundamental yet unresolved challenge.Existing methods typically rely on dense keyframe inputs or complex prior structures,making it difficult to balance motion quality and plausibility under conditions such as sparse constraints,long-term dependencies,and diverse motion styles.To address this,we propose a motion generation framework based on a frequency-domain diffusion model,which aims to better model complex motion distributions and enhance generation stability under sparse conditions.Our method maps motion sequences to the frequency domain via the Discrete Cosine Transform(DCT),enabling more effective modeling of low-frequency motion structures while suppressing high-frequency noise.A denoising network based on self-attention is introduced to capture long-range temporal dependencies and improve global structural awareness.Additionally,a multi-objective loss function is employed to jointly optimize motion smoothness,pose diversity,and anatomical consistency,enhancing the realism and physical plausibility of the generated sequences.Comparative experiments on the Human3.6M and LaFAN1 datasets demonstrate that our method outperforms state-of-the-art approaches across multiple performance metrics,showing stronger capabilities in generating intermediate motion frames.This research offers a new perspective and methodology for human motion generation and holds promise for applications in character animation,game development,and virtual interaction.
基金supported by the National Natural Science Foundation of China(Grant Nos.62472149,62376089,62202147)Hubei Provincial Science and Technology Plan Project(2023BCB04100).
文摘Accurate traffic flow prediction has a profound impact on modern traffic management. Traffic flow has complex spatial-temporal correlations and periodicity, which poses difficulties for precise prediction. To address this problem, a Multi-head Self-attention and Spatial-Temporal Graph Convolutional Network (MSSTGCN) for multiscale traffic flow prediction is proposed. Firstly, to capture the hidden traffic periodicity of traffic flow, traffic flow is divided into three kinds of periods, including hourly, daily, and weekly data. Secondly, a graph attention residual layer is constructed to learn the global spatial features across regions. Local spatial-temporal dependence is captured by using a T-GCN module. Thirdly, a transformer layer is introduced to learn the long-term dependence in time. A position embedding mechanism is introduced to label position information for all traffic sequences. Thus, this multi-head self-attention mechanism can recognize the sequence order and allocate weights for different time nodes. Experimental results on four real-world datasets show that the MSSTGCN performs better than the baseline methods and can be successfully adapted to traffic prediction tasks.
基金supported by National Science Foundation Grant No.2123824.
文摘Microrobots powered by an external magnetic field could be used for sophisticated medical applications such as cell treatment,micromanipulation,and noninvasive surgery inside the body.Untethered microrobot applications can benefit from haptic technology and telecommunication,enabling telemedical micro-manipulation.Users can manipulate the microrobots with haptic feedback by interacting with the robot operating system remotely in such applications.Artificially created haptic forces based on wirelessly transmitted data and model-based guidance can aid human operators with haptic sensations while manipulating microrobots.The system presented here includes a haptic device and a magnetic tweezer system linked together using a network-based teleoperation method with motion models in fluids.The magnetic microrobots can be controlled remotely,and the haptic interactions with the remote environment can be felt in real time.A time-domain passivity controller is applied to overcome network delay and ensure stability of communication.This study develops and tests a motion model for microrobots and evaluates two image-based 3D tracking algorithms to improve tracking accuracy in various Newtonian fluids.Additionally,it demonstrates that microrobots can group together to transport multiple larger objects,move through microfluidic channels for detailed tasks,and use a novel method for disassembly,greatly expanding their range of use in microscale operations.Remote medical treatment in multiple locations,remote delivery of medication without the need for physical penetration of the skin,and remotely controlled cell manipulations are some of the possible uses of the proposed technology.
基金co-supported the National Natural Science Foundation of China(No.52235010)the Heilongjiang Postdoctoral Fund(No.LBH-Z22136)the New Era Longjiang Excellent Master and Doctoral Dissertation Fund(No.LJYXL2022-057).
文摘To mill fine and well-defined micro-dimpled structures,a machining manner of spiral trajectory tool reciprocating motion,where the tool repeats the process of‘feed milling–retract–cutting feed–feed milling again’along the spiral trajectory,was proposed.From the kinematics analysis,it is found that the machining quality of micro-dimpled structures is highly dependent on the machining trajectory using spiral trajectory tool reciprocating motion.To reveal this causation,simulation modelling and experimental studies were carried out.A simulation model was developed to quantitatively and qualitatively investigate the influence of the trajectory discretization strategies(constant-angle and constant-arc length)and parameters(discrete angle,discrete arc length,and pitch)on surface texture and residual height of micro-dimpled structures.Subsequently,micro-dimpled structures were milled under different trajectory discretization strategies and parameters with spiral trajectory tool reciprocating motion.A comprehensive comparison between the milled results and simulation analysis was made based on geometry accuracy,surface morphology and surface roughness of milled dimples.Meanwhile,the errors and factors affecting the above three aspects were analyzed.The results demonstrate both the feasibility of the established simulation model and the machining capability of this machining way in milling high-quality micro-dimpled structures.Spiral trajectory tool reciprocating motion provides a new machining way for milling micro-dimpled structures and micro-dimpled functional surfaces.And an appropriate machining trajectory can be generated based on the optimized trajectory parameters,thus contributing to the improvement of machining quality and efficiency.
基金funded by the General Program of the National Natural Science Foundation of China(No.42174070)the General Program of the Beijing Natural Science Foundation(No.8222035).
文摘Basin effect was first described following the analysis of seismic ground motion associated with the 1985 MW8.1 earthquake in Mexico.Basins affect the propagation of seismic waves through various mechanisms,and several unique phenomena,such as the basin edge effect,basin focusing effect,and basin-induced secondary waves,have been observed.Understanding and quantitatively predicting these phenomena are crucial for earthquake disaster reduction.Some pioneering studies in this field have proposed a quantitative relationship between the basin effect on ground motion and basin depth.Unfortunately,basin effect phenomena predicted using a model based only on basin depth exhibit large deviations from actual distributions,implying the severe shortcomings of single-parameter basin effect modeling.Quaternary sediments are thick and widely distributed in the Beijing-Tianjin-Hebei region.The seismic media inside and outside of this basin have significantly different physical properties,and the basin bottom forms an interface with strong seismic reflections.In this study,we established a three-dimensional structure model of the Quaternary sedimentary basin based on the velocity structure model of the North China Craton and used it to simulate the ground motion under a strong earthquake following the spectral element method,obtaining the spatial distribution characteristics of the ground motion amplification ratio throughout the basin.The back-propagation(BP)neural network algorithm was then introduced to establish a multi-parameter mathematical model for predicting ground motion amplification ratios,with the seismic source location,physical property ratio of the media inside and outside the basin,seismic wave frequency,and basin shape as the input parameters.We then examined the main factors influencing the amplification of seismic ground motion in basins based on the prediction results,and concluded that the main factors influencing the basin effect are basin shape and differences in the physical properties of media inside and outside the basin.
基金supported by the National Key Research and Development Program of China(2018AAA0101005,2018AAA0102404)the Program of the Huawei Technologies Co.Ltd.(FA2018111061SOW12)+1 种基金the National Natural Science Foundation of China(61773054)the Youth Research Fund of the State Key Laboratory of Complex Systems Management and Control(20190213)。
文摘Human trajectory prediction is essential and promising in many related applications. This is challenging due to the uncertainty of human behaviors, which can be influenced not only by himself, but also by the surrounding environment. Recent works based on long-short term memory(LSTM) models have brought tremendous improvements on the task of trajectory prediction. However, most of them focus on the spatial influence of humans but ignore the temporal influence. In this paper, we propose a novel spatial-temporal attention(ST-Attention) model,which studies spatial and temporal affinities jointly. Specifically,we introduce an attention mechanism to extract temporal affinity,learning the importance for historical trajectory information at different time instants. To explore spatial affinity, a deep neural network is employed to measure different importance of the neighbors. Experimental results show that our method achieves competitive performance compared with state-of-the-art methods on publicly available datasets.
基金supported by the National Natural Science Foundation of China(Nos.52305072 and 52122503)Natural Science Foundation of Hebei Province of China(No.E2022203095)+2 种基金University-Industry Collaborative Education Program(No.220603936245709)Cultivation Project for Basic Research and Innovation of Yanshan University(No.2021LGQN004)henzhen Special Fund for Future Industrial Development(No.KJZD20230923114222045).
文摘The goal of this paper is to develop a unified online motion generation scheme for quadruped lateral-sequence walk and trot gaits based on a linear model predictive control formulation.Specifically,the dynamics of the linear pendulum model is formulated over a predictive horizon by dimensional analysis.Through gait pattern conversion,the lateral-sequence walk and trot gaits of the quadruped can be regarded as unified biped gaits,allowing the dynamics of the linear inverted pendulum model to serve quadruped motion generation.In addition,a simple linearization of the center of pressure constraints for these quadruped gaits is developed for linear model predictive control problem.Furthermore,the motion generation problem can be solved online by quadratic programming with foothold adaptation.It is demonstrated that the proposed unified scheme can generate stable locomotion online for quadruped lateral-sequence walk and trot gaits,both in simulation and on hardware.The results show significant performance improvements compared to previous work.Moreover,the results also suggest the linearly simplified scheme has the ability to robustness against unexpected disturbances.
基金supported by the National Natural Science Foundation of China(No.52271367).
文摘In this paper, the online parameter identification problem of the mathematical model of an unmanned surface vehicle (USV) considering the characteristics of the actuator is studied. A data-driven mathematical model of motion is very meaningful to realize trajectory prediction and adaptive motion control of the USV. An interactive identification algorithm (ESO–MILS, extended state observer–multi-innovation least squares) based on ESO is proposed. The robustness of online identification is improved by expanding the state observer to estimate the current disturbance without making artificial assumptions. Specifically, the three-degree-of-freedom dynamic equation of the double propeller propulsion USV is constructed. A linear model for online identification is derived by parameterization. Based on the least square criterion function, it is proved that the interactive identification method with disturbance estimation can improve the identification accuracy from the perspective of mathematical expectation. The extended state observer is designed to estimate the unknown disturbance in the model. The online interactive update improves the disturbance immunity of the identification algorithm. Finally, the effectiveness of the interactive identification algorithm is verified by simulation experiment and real ship experiment.
基金Shenzhen Science and Technology Programme,Grant/Award Number:JCYJ202308071208000012023 Shenzhen sustainable supporting funds for colleges and universities,Grant/Award Number:20231121165240001Guangdong Provincial Key Laboratory of Ultra High Definition Immersive Media Technology,Grant/Award Number:2024B1212010006。
文摘Internal learning-based video inpainting methods have shown promising results by exploiting the intrinsic properties of the video to fill in the missing region without external dataset supervision.However,existing internal learning-based video inpainting methods would produce inconsistent structures or blurry textures due to the insufficient utilisation of motion priors within the video sequence.In this paper,the authors propose a new internal learning-based video inpainting model called appearance consistency and motion coherence network(ACMC-Net),which can not only learn the recurrence of appearance prior but can also capture motion coherence prior to improve the quality of the inpainting results.In ACMC-Net,a transformer-based appearance network is developed to capture global context information within the video frame for representing appearance consistency accurately.Additionally,a novel motion coherence learning scheme is proposed to learn the motion prior in a video sequence effectively.Finally,the learnt internal appearance consistency and motion coherence are implicitly propagated to the missing regions to achieve inpainting well.Extensive experiments conducted on the DAVIS dataset show that the proposed model obtains the superior performance in terms of quantitative measurements and produces more visually plausible results compared with the state-of-the-art methods.
基金the National Natural Science Foundation of China(No.52474068)the Major Collab-orative Innovation Project of Prospecting Breakthrough Stra-tegic Action in Guizhou Province(No.[2022]ZD001-003).
文摘Coalbed methane(CBM)is a vital unconventional energy resource,and predicting its spatiotemporal pressure dynamics is crucial for efficient development strategies.This paper proposes a novel deep learningebased data-driven surrogate model,AxialViT-ConvLSTM,which integrates AxialAttention Vision Transformer,ConvLSTM,and an enhanced loss function to predict pressure dynamics in CBM reservoirs.The results showed that the model achieves a mean square error of 0.003,a learned perceptual image patch similarity of 0.037,a structural similarity of 0.979,and an R^(2) of 0.982 between predictions and actual pressures,indicating excellent performance.The model also demonstrates strong robustness and accuracy in capturing spatialetemporal pressure features.
基金supported by the National Natural Science Foundation of Jiangsu Province,China(Grant No.BK20231255).
文摘On the basis of the model tests,this paper explores the coupled hydrodynamic performance of the moonpool and the hull.This study aims to compare and analyze the variation in the hull heave response between the piston resonance state of the moonpool under wave excitation and the non-resonance state of the moonpool under wave-current excitation.A novel damping device specifically designed and fabricated for stepped moonpools has been developed.Before and after the installation of the damping device,the free surface response characteristics of the moonpool and heave motion response characteristics of the hull are compared.The findings show a clear correlation between the current speed and heave response characteristics of the hull.During the seakeeping design phase of the drilling vessel,the current speed is an additional critical factor that cannot be disregarded,alongside the moonpool effect.A correlation exists between the fluid dynamics occurring within the moonpool and the heave motion of the vessel hull.A reduction in the amplitude of the motion of the moonpool water results in a decrease in the heave motion of the hull.This study provides a reference for alleviating the seakeeping of a drill ship’s heave response and enhancing the safety and efficiency of the operation.
基金Supported by National Natural Science Foundation of China(Grant Nos.52305003,52175019)National Key R&D Program of China(Grant No.2023YFD2001100)+2 种基金Beijing Natural Science Foundation(Grant No.L222038)Beijing Nova Programme Interdisciplinary Cooperation Project(Grant No.20240484699)Project“Vice President of Science and Technology”of Changping District of Beijing.
文摘The design and analysis of continuum robots have consistently been a prominent research focus in the field of mechanics.However,portable continuum robots with minimal spatial occupancy,which have great potential for applications such as search and rescue,are scarcely available.This paper presents a novel helical-coiled multi-segment flexible continuum robot featuring helical deployment and compact design,with an integrated framework for structural design,kinematic modeling,and experimental validation.The design of the helical-coiled multi-segment flexible continuum robot for unstructured environment detection,including a flexible body,an actuation module,a feed module,and a sensing module,is presented systematically.Kinematic models of both single-and multisegment continuum robots were established based on the constant curvature model to analyze the parameter mapping relationship from the end-effector position and orientation to the driving inputs.Furthermore,the feedforward motion of the robot was examined,and an uncoiling strategy based on S-curve compensation was employed to complete the kinematic analysis.Finally,the accuracy of the kinematic model considering the active uncoiling feed motion was validated through experimental analysis,demonstrating the motion characteristics of the continuum robot.Altogether,this study provides a framework for the design and analysis of helical-coiled continuum robots.
基金Supported by National Natural Science Foundation of China(Grant No.52332013)。
文摘The intelligent vehicle corner module system,which integrates four-wheel independent drive,independent steering,independent braking and active suspension,can accurately and efficiently perform vehicle driving tasks and is the best carrier of intelligent vehicles.Nevertheless,too many angle/torque control inputs make control difficult and non-real-time.In this paper,a hierarchical real-time motion control framework for corner module configuration intelligent electric vehicles is proposed.In the trajectory planning module,an improved driving risk field is designed to describe the surrounding environment’s driving risk.Combined with the kinematic vehicle-road model,model predictive control(MPC)method,spline curve method,the local reference trajectory of safety,comfort and smoothness is planned in real time.The optimal steering angle is determined using MPC method in path tracking module.In the motion control module,a feedforward-feedback controller assigns the optimal steering angle to the front/rear axles,and an angle allocation controller distributes the target angles of the front/rear axles to four steered wheels.Finally,the PreScan-Simulink-CarSim joint simulation environment is established for conducting the human-in-the-loop emergency obstacle avoidance experiment.It took only 0.005 s for the hierarchical motion control system to determine its average solution time.This proves the effectiveness of the hierarchical motion control system.
基金supported by the National Natural Science Foundation of China(Grant No.52105466).
文摘The prediction and compensation control of marine ship motion is crucial for ensuring the safety of offshore wind turbine loading and unloading operations.However,the accuracy of prediction and control is significantly affected by the hysteresis phenomenon in the wave compensation system.To address this issue,a ship heave motion prediction is proposed in this paper on the basis of the Gauss-DeepAR(AR stands for autoregressive recurrent)model and the Hilbert−Huang time-delay compensation control strategy.Initially,the zero upward traveling wave period of the level 4−6 sea state ship heave motion is analyzed,which serves as the input sliding window for the Gauss-DeepAR prediction model,and probability predictions at different wave direction angles are conducted.Next,considering the hysteresis characteristics of the ship heave motion compensation platform,the Hilbert−Huang transform is employed to analyze and calculate the hysteresis delay of the compensation platform.After the optimal control action value is subsequently calculated,simulations and hardware platform tests are conducted.The simulation results demonstrated that the Gauss-DeepAR model outperforms autoregressive integrated moving average model(ARIMA),support vector machine(SVM),and longshort-term memory(LSTM)in predicting non-independent identically distributed datasets at a 90°wave direction angle in the level 4−6 sea states.Furthermore,the model has good predictive performance and generalizability for non-independent and non-uniformly distributed datasets at a 180°wave direction angle.The hardware platform compensation test results revealed that the Hilbert–Huang method has an outstanding effect on determining the hysteretic delay and selecting the optimal control action value,and the compensation efficiency was higher than 90%in the level 4−6 sea states.
基金National Natural Science Foundation of China,12372025,Feng Liang,12072311,Feng Liang.
文摘Based on the Timoshenko beam theory,this paper proposes a nonlocal bi-gyroscopic model for spinning functionally graded(FG)nanotubes conveying fluid,and the thermal–mechanical vibration and stability of such composite nanostructures under small scale,rotor,and temperature coupling effects are investigated.The nanotube is composed of functionally graded materials(FGMs),and different volume fraction functions are utilized to control the distribution of material properties.Eringen’s nonlocal elasticity theory and Hamilton’s principle are applied for dynamical modeling,and the forward and backward precession frequencies as well as 3D mode configurations of the nanotube are obtained.By conducting dimensionless analysis,it is found that compared to the Timoshenko nano-beam model,the conventional Euler–Bernoulli(E-B)model holds the same flutter frequency in the supercritical region,while it usually overestimates the higher-order precession frequencies.The nonlocal,thermal,and flowing effects all can lead to buckling or different kinds of coupled flutter in the system.The material distribution of the P-type FGM nanotube can also induce coupled flutter,while that of the S-type FGM nanotube has no impact on the stability of the system.This paper is expected to provide a theoretical foundation for the design of motional composite nanodevices.
基金Supported by Shanghai Artificial Intelligence Laboratory。
文摘This paper develops an Ito-type fractional pathwise integration theory for fractional Brownian motion with Hurst parameters H∈(1/3,1/2],using the Lyons'rough path framework.This approach is designed to fill gaps in conventional stochastic calculus models that fail to account for temporal persistence prevalent in dynamic systems such as those found in economics,finance,and engineering.The pathwise-defined method not only meets the zero expectation criterion but also addresses the challenges of integrating non-semimartingale processes,which traditional Ito calculus cannot handle.We apply this theory to fractional Black–Scholes models and high-dimensional fractional Ornstein–Uhlenbeck processes,illustrating the advantages of this approach.Additionally,the paper discusses the generalization of It?integrals to rough differential equations(RDE)driven by f BM,emphasizing the necessity of integrand-specific adaptations in the It?rough path lift for stochastic modeling.
文摘Captive model tests are one of the most common methods to calculate the maneuvering hydrodynamic coefficients and characteristics of surface and underwater vehicles.Considerable attention must be paid to selecting and designing the most suitable laboratory equipment for towing tanks.A computational fluid dynamics(CFD)-based method is implemented to determine the loads acting on the towing facility of the submarine model.A reversed topology is also used to ensure the appropriateness of the load cells in the developed method.In this study,the numerical simulations were evaluated using the experimental results of the SUBOFF benchmark submarine model of the Defence Advanced Research Projects Agency.The maximum and minimum loads acting on the 2.5-meter submarine model were measured by determining the body’s lightest and heaviest maneuvering test scenarios.In addition to having sufficient endurance against high loads,the precision in measuring the light load was also investigated.The horizontal planar motion mechanism(HPMM)facilities in the National Iranian Marine Laboratory were developed by locating the load cells inside the submarine model.The results were presented as a case study.A numerical-based method was developed to obtain the appropriate load measurement facilities.Load cells of HPMM test basins can be selected by following the two-way procedure presented in this study.
基金Project supported by the National Natural Science Foundation of China(Nos.12372071 and 12372070)the Aeronautical Science Fund of China(No.2022Z055052001)the Foundation of China Scholarship Council(No.202306830079)。
文摘Currently,there are a limited number of dynamic models available for braided composite plates with large overall motions,despite the incorporation of three-dimensional(3D)braided composites into rotating blade components.In this paper,a dynamic model of 3D 4-directional braided composite thin plates considering braiding directions is established.Based on Kirchhoff's plate assumptions,the displacement variables of the plate are expressed.By incorporating the braiding directions into the constitutive equation of the braided composites,the dynamic model of the plate considering braiding directions is obtained.The effects of the speeds,braiding directions,and braided angles on the responses of the plate with fixed-axis rotation and translational motion,respectively,are investigated.This paper presents a dynamic theory for calculating the deformation of 3D braided composite structures undergoing both translational and rotational motions.It also provides a simulation method for investigating the dynamic behavior of non-isotropic material plates in various applications.
基金the Deanship of Research and Graduate Studies at King Khalid University for funding this work through large Research Group Project (Grant No. RGP2/198/45)Project supported by Prince Sattam bin Abdulaziz University (Grant No. PSAU/2025/R/1446)。
文摘This work investigates water-based micropolar hybrid nanofluid(MHNF) flow on an elongating variable porous sheet.Nanoparticles of diamond and copper have been used in the water to boost its thermal conductivity. The motion of the fluid is taken as two-dimensional with the impact of a magnetic field in the normal direction. The variable, permeable, and stretching nature of sheet's surface sets the fluid into motion. Thermal and mass diffusions are controlled through the use of the Cattaneo–Christov flux model. A dataset is generated using MATLAB bvp4c package solver and employed to train an artificial neural network(ANN) based on the Levenberg–Marquardt back-propagation(LMBP) algorithm. It has been observed as an outcome of this study that the modeled problem achieves peak performance at epochs 637, 112, 4848, and 344 using ANN-LMBP. The linear velocity of the fluid weakens with progression in variable porous and magnetic factors.With an augmentation in magnetic factor, the micro-rotational velocity profiles are augmented on the domain 0 ≤ η < 1.5 due to the support of micro-rotations by Lorentz forces close to the sheet's surface, while they are suppressed on the domain 1.5 ≤ η < 6.0 due to opposing micro-rotations away from the sheet's surface. Thermal distributions are augmented with an upsurge in thermophoresis, Brownian motion, magnetic, and radiation factors, while they are suppressed with an upsurge in thermal relaxation parameter. Concentration profiles increase with an expansion in thermophoresis factor and are suppressed with an intensification of Brownian motion factor and solute relaxation factor. The absolute errors(AEs) are evaluated for all the four scenarios that fall within the range 10^(-3)–10^(-8) and are associated with the corresponding ANN configuration that demonstrates a fine degree of accuracy.
