查看更多>>摘要：The current study focuses on the motion-pressure coupled control for a multicapsule stratospheric airship and transforms the path-tracking and heading-hold control of airships into guidance tracking with a time-varying weighted sum of longitudinal and lateral velocities by the def-inition of compound speed.Herein,an improved nonlinear predictive control method is provided to reduce the control energy consumption by the rolling optimization of controller parameters based on finite time intervals,ensuring infinite-time path-tracking tasks.Simultaneously,combined with the proposed cyclic regulation process of safe pressure between internal and external capsules,this study can fully reflect the force-thermal coupled rule of airships under the actions of atmospheric environment and maneuvering force,while evaluating the long-endurance capability of airships under the conditions of safe superheating and overpressure.The effectiveness of the motion-pressure coupled controller was verified through numerical simulations,which can overcome the influence of environmental wind and achieve a tracking effect for the desired cruise path and com-pound speed.The airspeed provided during the cyclic circadian time caused the maximum super-heating of the helium controlled within 30 ℃.The helium in the internal and external capsules achieved circadian regulation.The equivalent micropore diameter of the capsule of 5 mm can achieve 55 days of long-endurance flight.The controller satisfies the requirements of cruise-flight application modes for multicapsule stratospheric airships with important engineering value.
查看更多>>摘要：The helicopter Trailing-Edge Flaps(TEFs)technology is one of the recent hot topics in morphing wing research.By employing controlled deflection,TEFs can effectively reduce the vibra-tion level of helicopters.Thus,designing specific vibration reduction control methods for the heli-copters equipped with trailing-edge flaps is of significant practical value.This paper studies the optimal control problem for helicopter-vibration systems with TEFs under the framework of adap-tive dynamic programming combined with Reinforcement Learning(RL).Time-delay and distur-bances,caused by complexity of helicopter dynamics,inevitably deteriorate the control performance of vibration reduction.To solve this problem,a zero-sum game formulation with a linear quadratic form for reducing vibration of helicopter systems is presented with a virtual predic-tor.In this context,an off-policy reinforcement learning algorithm is developed to determine the optimal control policy.The algorithm utilizes only vertical vibration load data to achieve a policy that reduces vibration,attains Nash equilibrium,and addresses disturbances while compensating for time-delay without knowledge of the dynamics of the helicopter system.The effectiveness of the proposed method is demonstrated in a virtual platform.
查看更多>>摘要：Target recognition is a significant part of a Ballistic Missile Defense System(BMDS).However,most existing ballistic target recognition methods overlook the impact of data represen-tation on recognition outcomes.This paper focuses on systematically investigating the influences of three novel data representations in the Range-Doppler(RD)domain.Initially,the Radar Cross Section(RCS)and micro-Doppler(m-D)characteristics of a cone-shaped ballistic target are ana-lyzed.Then,three different data representations are proposed:RD data,RD sequence tensor data,and RD trajectory data.To accommodate various data inputs,deep-learning models are designed,including a two-Dimensional Residual Dense Network(2D RDN),a three-Dimensional Residual Dense Network-Gated Recurrent Unit(3D RDN-GRU),and a Dynamic Trajectory Recognition Network(DTRN).Finally,an Electromagnetic(EM)computation dataset is collected to verify the performances of the networks.A broad range of experimental results demonstrates the effective-ness of the proposed framework.Moreover,several key parameters of the proposed networks and datasets are extensively studied in this research.
查看更多>>摘要：Task allocation is a key aspect of Unmanned Aerial Vehicle(UAV)swarm collabora-tive operations.With an continuous increase of UAVs'scale and the complexity and uncertainty of tasks,existing methods have poor performance in computing efficiency,robustness,and real-time allocation,and there is a lack of theoretical analysis on the convergence and optimality of the solution.This paper presents a novel intelligent framework for distributed decision-making based on the evolutionary game theory to address task allocation for a UAV swarm system in uncertain scenarios.A task allocation model is designed with the local utility of an individual and the global utility of the system.Then,the paper analytically derives a potential function in the networked evolutionary potential game and proves that the optimal solution of the task allocation problem is a pure strategy Nash equilibrium of a finite strategy game.Additionally,a PayOff-based Time-Variant Log-linear Learning Algorithm(POTVLLA)is proposed,which includes a novel learning strategy based on payoffs for an individual and a time-dependent Boltzmann parameter.The former aims to reduce the system's computational burden and enhance the individual's effectiveness,while the latter can ensure that the POTVLLA converges to the optimal Nash equilibrium with a probability of one.Numerical simulation results show that the approach is optimal,robust,scalable,and fast adaptable to environmental changes,even in some realistic situations where some UAVs or tasks are likely to be lost and increased,further validating the effectiveness and superiority of the proposed framework and algorithm.
查看更多>>摘要：Achieving higher accuracy positioning results in urban environments at a lower cost has been an important pursuit in areas such as autonomous driving and intelligent transportation.Low-cost Inertial Navigation System and Global Navigation Satellite System(INS/GNSS)integrated navigation systems have been an important means of fulfilling the above quest due to the comple-mentary error characteristics between INS and GNSS.The complex urban driving environment requires the system sufficiently adaptive to keep up with the time-varying measurement noise and sufficiently robust to cope with measurement outliers and prior uncertainties.However,many efforts lack a balance between adaptability and robustness.In this paper,a novel positioning method with both adaptability and robustness is proposed by coupling the Mahalanobis distance method,the Variational Bayesian method and the student's t-distribution in one process(M-VBt method).This method is robust against non-Gaussian noise and priori uncertainties,plus adaptive against measurement noise uncertainty and time-varying noise.The field test results show that the M-VBt method(especially the Mahalanobis distance part)has significantly improved the system performance in the complex urban driving environment.
查看更多>>摘要：Obtaining absolute pose based on pre-loaded satellite images is one of the important means of autonomous navigation for small Unmanned Aerial Vehicles(UAVs)in Global Naviga-tion Satellite System(GNSS)denied environments.Most of the previous works have tended to build Convolutional Neural Networks(CNNs)to extract features and then directly regress the pose,which will fail when solving the challenges caused by the huge viewpoint and size differences between"UAV-satellite"image pairs in real-world scenarios.Therefore,this paper proposes a probability distribution/regression integrated deep model with the attention-guided triple fusion mechanism,which estimates discrete distributions in pose space and three-dimensional vectors in translation space.In order to overcome the shortage of the relevant dataset,this paper simulates image datasets captured by UAVs with forward-facing cameras during target searching and auton-omous attacking.The effectiveness,superiority,and robustness of the proposed method are verified by simulated datasets and flight tests.
查看更多>>摘要：To solve the divergence problem and overcome the difficulty in guaranteeing filtering accuracy during estimation of the process noise covariance or the measurement noise covariance with traditional new information-based nonlinear filtering methods,we design a new method for estimating noise statistical characteristics of nonlinear systems based on the credibility Kalman Fil-ter(KF)theory considering noise correlation.This method first extends credibility to the Unscented Kalman Filter(UKF)and Extended Kalman Filter(EKF)based on the credibility theory.Further,an optimization model for nonlinear credibility under noise related conditions is established consid-ering noise correlation.A combination of filtering smoothing and credibility iteration formula is used to improve the real-time performance of the nonlinear adaptive credibility KF algorithm,fur-ther expanding its application scenarios,and the derivation process of the formula theory is pro-vided.Finally,the performance of the nonlinear credibility filtering algorithm is simulated and analyzed from multiple perspectives,and a comparative analysis conducted on specific experimental data.The simulation and experimental results show that the proposed credibility EKF and credi-bility UKF algorithms can estimate the noise covariance more accurately and effectively with lower average estimation time than traditional methods,indicating that the proposed algorithm has stable estimation performance and good real-time performance.
查看更多>>摘要：Current research on Digital Twin(DT)based Prognostics and Health Management(PHM)focuses on establishment of DT through integration of real-time data from various sources to facilitate comprehensive product monitoring and health management.However,there still exist gaps in the seamless integration of DT and PHM,as well as in the development of DT multi-field coupling modeling and its dynamic update mechanism.When the product experiences long-period degradation under load spectrum,it is challenging to describe the dynamic evolution of the health status and degradation progression accurately.In addition,DT update algorithms are difficult to be integrated simultaneously by current methods.This paper proposes an innovative dual loop DT based PHM framework,in which the first loop establishes the basic dynamic DT with multi-filed coupling,and the second loop implements the PHM and the abnormal detection to provide the interaction between the dual loops through updating mechanism.The proposed method pays atten-tion to the internal state changes with degradation and interactive mapping with dynamic param-eter updating.Furthermore,the Independence Principle for the abnormal detection is proposed to refine the theory of DT.Events at the first loop focus on accurate modeling of multi-field coupling,while the events at the second loop focus on real-time occurrence of anomalies and the product degradation trend.The interaction and collaboration between different loop models are also dis-cussed.Finally,the Permanent Magnet Synchronous Motor(PMSM)is used to verify the proposed method.The results show that the modeling method proposed can accurately track the lifecycle performance changes of the entity and carry out remaining life prediction and health management effectively.
查看更多>>摘要：This paper presents that a serpentine curve-based controller can solve locomotion con-trol problems for articulated space robots with extensive flight phases,such as obstacle avoidance during free floating or attitude adjustment before landing.The proposed algorithm achieves artic-ulated robots to use closed paths in the joint space to accomplish the above tasks.Flying snakes,which can shuttle through gaps and adjust their landing posture by swinging their body during glid-ing in jungle environments,inspired the design of two maneuvers.The first maneuver generates a rotation of the system by varying the moment of inertia between the joints of the robot,with the magnitude of the net rotation depending on the controller parameters.This maneuver can be repeated to allow the robot to reach arbitrary reorientation.The second maneuver involves periodic undulations,allowing the robot to avoid collisions when the trajectory of the global Center of Mass(CM)passes through the obstacle.Both maneuvers are based on the improved serpenoid curve,which can adapt to redundant systems consisting of different numbers of modules.Finally,the sim-ulation illustrates that combining the two maneuvers can help a free-floating chain-type robot tra-verse complex environments.Our proposed algorithm can be used with similar articulated robot models.
查看更多>>摘要：This paper presents a Shared Control Architecture(SCA)between a human pilot and a smart inceptor for nonlinear Pilot Induced Oscillations(PIOs),e.g.,category Ⅱ or Ⅲ PIOs.One innovation of this paper is that an intelligent shared control architecture is developed based on the intelligent active inceptor technique,i.e.,Smart Adaptive Flight Effective Cue(SAFE-Cue).A deep reinforcement learning approach namely Deep Deterministic Policy Gradient(DDPG)method is chosen to design a gain adaptation mechanism for the SAFE-Cue module.By doing this,the gains of the SAFE-Cue will be intelligently tuned once nonlinear PIOs triggered;meanwhile,the human pilot will receive a force cue from the SAFE-Cue,and will consequently adapting his/her control policy.The second innovation of this paper is that the reward function of the DDPG based gain adaptation approach is constructed according to flying qualities.Under the premise of consid-ering failure situation,task completion qualities and pilot workload are also taken into account.Finally,the proposed approach is validated using numerical simulation experiments with two types of scenarios:lower actuator rate limits and airframe damages.The Inceptor Peak Power-Phase(IPPP)metric is adopted to analyze the human-vehicle system simulation results.Results and anal-ysis show that the DDPG based sharing control approach can well address nonlinear PIO problems consisting of Categories Ⅱ and Ⅲ PIO events.
NETL
NSTL
万方数据