查看更多>>摘要：Increasing attention has been attracted to the dynamic performance and safety of advanced performance predictive control systems of the next-generation aeroengine.The latest research demonstrates that Subspace-based Improved Model Predictive Control(SIMPC)can over-come the difficulty in solving the predictive model in MPC/NMPC applications.However,applying constant design parameters cannot maintain consistent control effects in all states.Meanwhile,the designed system relies too much on sensor-measured data,and thus it is difficult to thoroughly val-idate the safety of the system because of its high complexity.This means that any potential hard-ware/software faults will endanger the engine.Therefore,this paper first presents a novel nonlinear mapping relationship to adaptively tune the tracking weight online with the change of Power Lever Angle(PLA)and real-time relative tracking error.Thus,without introducing additional design parameters,an Adaptive Tracking Weight-based SIMPC(ATW-SIMPC)controller is designed to improve the control performance in all operating states effectively.Then,a Primary/Backup Hybrid Control(PBHC)strategy with the ATW-SIMPC controller as the primary system and the traditional speed(Nf)controller as the backup system is proposed to ensure safety.The designed affiliated switching controller and the real-time monitor therein can be used to realize reasonable and smooth switching between primary/backup systems,so as to avoid bump transition.The PBHC system switches to the Nf controller when the ATW-SIMPC controller is wrong because of potential hardware/software faults;otherwise,the ATW-SIMPC controller keeps acting on the engine.The main results prove that the ATW-SIMPC controller with the optimal nonlinear mapping relation-ship,compared with the existing SIMPC controller,uplifts the dynamic control performance by 32％and reduces overshoots to an allowable limit,resulting in a better control effect in full state.The comparison results consistently indicate that the PBHC can guarantee engine safety in occur-rence of hardware/software faults,such as sensor/onboard adaptive model faults.The approach proposed is applicable to the design of a model-based engine intelligent control system.
查看更多>>摘要：With rapid development of UAV technology,research on UAV image analysis has gained attention.As the existing techniques of UAV target localization often rely on additional equipment,a method of UAV target localization based on depth estimation has been proposed.However,the unique perspective of UAVs poses challenges such as the significant field of view variations and the presence of dynamic objects in the scene.As a result,the existing methods of depth estimation and scale recovery cannot be directly applied to UAV perspectives.Additionally,there is a scarcity of depth estimation datasets tailored for UAV perspectives,which makes supervised algorithms impractical.To address these issues,an outlier filter is introduced to enhance the applicability of depth estimation networks to target localization.A frame buffer method is proposed to achieve more accurate scale recovery,so as to handle complex scene textures in UAV images.The proposed method demonstrates a 14.29％improvement over the baseline.Compared with the average recovery results from UAV perspectives,the difference is only 0.88％,approaching the performance of scale recovery using ground truth labels.Furthermore,to overcome the limited availability of traditional UAV depth datasets,a method for generating depth labels from video sequences is proposed.Com-pared to state-of-the-art methods,the proposed approach achieves higher accuracy in depth estima-tion and stands for the first attempt at target localization using image sequences.Proposed algorithm and dataset are available at https://github.com/uav-tan/uav-object-localization.
查看更多>>摘要：Reinforcement Learning(RL)algorithms enhance intelligence of air combat Autono-mous Maneuver Decision(AMD)policy,but they may underperform in target combat environ-ments with disturbances.To enhance the robustness of the AMD strategy learned by RL,this study proposes a Tube-based Robust RL(TRRL)method.First,this study introduces a tube to describe reachable trajectories under disturbances,formulates a method for calculating tubes based on sum-of-squares programming,and proposes the TRRL algorithm that enhances robustness by utilizing tube size as a quantitative indicator.Second,this study introduces offline techniques for regressing the tube size function and establishing a tube library before policy learning,aiming to eliminate complex online tube solving and reduce the computational burden during training.Fur-thermore,an analysis of the tube library demonstrates that the mitigated AMD strategy achieves greater robustness,as smaller tube sizes correspond to more cautious actions.This finding high-lights that TRRL enhances robustness by promoting a conservative policy.To effectively balance aggressiveness and robustness,the proposed TRRL algorithm introduces a"laziness factor"as a weight of robustness.Finally,combat simulations in an environment with disturbances confirm that the AMD policy learned by the TRRL algorithm exhibits superior air combat performance com-pared to selected robust RL baselines.
查看更多>>摘要：Obtaining the accurate value estimation and reducing the estimation bias are the key issues in reinforcement learning.However,current methods that address the overestimation prob-lem tend to introduce underestimation,which face a challenge of precise decision-making in many fields.To address this issue,we conduct a theoretical analysis of the underestimation bias and pro-pose the minmax operation,which allow for flexible control of the estimation bias.Specifically,we select the maximum value of each action from multiple parallel state-action networks to create a new state-action value sequence.Then,a minimum value is selected to obtain more accurate value estimations.Moreover,based on the minmax operation,we propose two novel algorithms by com-bining Deep Q-Network(DQN)and Double DQN(DDQN),named minmax-DQN and minmax-DDQN.Meanwhile,we conduct theoretical analyses of the estimation bias and variance caused by our proposed minmax operation,which show that this operation significantly improves both under-estimation and overestimation biases and leads to the unbiased estimation.Furthermore,the vari-ance is also reduced,which is helpful to improve the network training stability.Finally,we conduct numerous comparative experiments in various environments,which empirically demonstrate the superiority of our method.
查看更多>>摘要：This study proposes an active surge control method based on deep reinforcement learn-ing to ensure the stability of compressors when adhering to the pressure rise command across the wide operating range of an aeroengine.Initially,the study establishes the compressor dynamic model with uncertainties,disturbances,and Close-Coupled Valve(CCV)actuator delay.Building upon this foundation,a Partially Observable Markov Decision Process(POMDP)is defined to facilitate active surge control.To address the issue of unobservability,a nonlinear state observer is designed using a finite-time high-order sliding mode.Furthermore,an Improved Soft Actor-Critic(ISAC)algorithm is developed,incorporating prioritized experience replay and adaptive tem-perature parameter techniques,to strike a balance between exploration and convergence during training.In addition,reasonable observation variables,error-segmented reward functions,and ran-dom initialization of model parameters are employed to enhance the robustness and generalization capability.Finally,to assess the effectiveness of the proposed method,numerical simulations are conducted,and it is compared with the fuzzy adaptive backstepping method and Second-Order Sliding Mode Control(SOSMC)method.The simulation results demonstrate that the deep rein-forcement learning based controller outperforms other methods in both tracking accuracy and robustness.Consequently,the proposed active surge controller can effectively ensure stable opera-tion of compressors in the high-pressure-ratio and high-efficiency region.
查看更多>>摘要：Identifying and segmenting spacecraft components is vital in many on-orbit space mis-sions,such as on-orbit maintenance and component recovery.Integrating depth maps with visual images has been proven effective in improving segmentation accuracy.However,existing methods ignore the noise and fallacy in collected depth maps,which interfere with the network to extract representative features,decreasing the final segmentation accuracy.To this end,this paper proposes a Filtering and Regret Network(FRNet)for spacecraft component segmentation.The FRNet incorporates filtering and regret mechanisms to suppress the abnormal depth response in shallow layers and selectively reuses the filtered cues in deep layers,avoiding the detrimental effects of low-quality depth information while preserving the semantic context inherent in depth maps.Fur-thermore,a two-stage feature fusion module is proposed,which involves information interaction and aggregation.This module effectively explores the feature correlation and unifies the multi-modal features into a comprehensive representation.Finally,a large-scale spacecraft component recognition dataset is constructed for training and evaluating spacecraft component segmentation algorithms.Experimental results demonstrate that the FRNet achieves a state-of-the-art perfor-mance with a mean Intersection Over Union(mIOU)of 84.13％and an average inference time of 133.2 ms when tested on an NVIDIA RTX 2080 SUPER GPU.
查看更多>>摘要：In this paper,we propose a cooperative guidance law aimed to achieve coordinated impact angles with limited observation on target information.The primary challenge lies in estab-lishing an appropriate communication graph among all missiles and devising an algorithm to esti-mate target acceleration information during engagements.To address this,we propose a specific communication topology and employ a numerical integration-based estimation method.Addition-ally,a distributed algorithm is introduced to facilitate consensus on target acceleration estimation.Building upon these foundations,we design an optimal-control-based distributed guidance law for each missile.Performance of the proposed guidance law is validated through numerical simulations.
查看更多>>摘要：Supersonic Tailless Aerial Vehicles(STAVs)will become an essential force in Penetrating Counter Air(PCA),but STAVs do not have the traditional horizontal and vertical tails,making pitch and yaw control difficult.The attack angle and the sideslip angle need to be limited to ensure that the engine inlet and the aerodynamic rudder at the rear of the vehicle can work properly,which is the so-called security constraints.In addition,the tracking error of the aerodynamic angle needs to be limited to achieve effective attitude control or high-accuracy tracking of trajectories,which is the so-called performance constraints.To this end,an attitude control method that meets the needs of PCA has been devised,based on constraint definition,coupled constraints handling,and control law design.Firstly,mathematical descriptions of the security constraints,performance constraints,and control constraints are given.Secondly,two treatment methods,coupled command filter and coupled funnel control are proposed for the aerodynamic angle coupled constraint problem.Finally,based on Nonlinear Dynamic Inverse(NDI)design,the coupled funnel controller is designed and validated by simulation for two typical mission scenarios,high-altitude penetration and low-altitude surprise defence.The proposed control method not only satisfies the security and performance constraints of STAV attitude control but also is highly robust.
查看更多>>摘要：In this advanced exploration,we focus on multiple parameters estimation in bistatic Multiple-Input Multiple-Output(MIMO)radar systems,a crucial technique for target localization and imaging.Our research innovatively addresses the joint estimation of the Direction of Departure(DOD),Direction of Arrival(DOA),and Doppler frequency for incoherent targets.We propose a novel approach that significantly reduces computational complexity by utilizing the Temporal-Spatial Nested Sampling Model(TSNSM).Our methodology begins with a multi-linear mapping mechanism to efficiently eliminate unnecessary virtual Degrees of Freedom(DOFs)and reorganize the remaining ones.We then employ the Toeplitz matrix triple iteration reconstruction method,sur-passing the traditional Temporal-Spatial Smoothing Window(TSSW)approach,to mitigate the single snapshot effect and reduce computational demands.We further refine the high-dimensional ESPRIT algorithm for joint estimation of DOD,DOA,and Doppler frequency,elim-inating the need for additional parameter pairing.Moreover,we meticulously derive the Cramér-Rao Bound(CRB)for the TSNSM.This signal model allows for a second expansion of DOFs in time and space domains,achieving high precision in target angle and Doppler frequency estima-tion with low computational complexity.Our adaptable algorithm is validated through simulations and is suitable for sparse array MIMO radars with various structures,ensuring higher precision in parameter estimation with less complexity burden.
查看更多>>摘要：Iso-scallop height machining means,when machining a freeform surface,the scallop height between any two neighboring tool paths on the surface will be a constant(i.e.,the given threshold),which is preferable among various freeform surface machining strategies due to its high machining efficiency as well as better machine tool's dynamics.However,all the existing iso-scallop height path planning methods pertain to only the ball-end or flat-end types of tools.In recent years,the non-spherical cutting tool has become more and more popular,especially for five-axis machin-ing of complex freeform surfaces,majorly owing to its non-constant curvature which can be utilized to adaptively fit the tool to the surface to both avoid the local gouging and enlarge the cutting width.However,there have been no reported works on iso-scallop height five-axis tool path gener-ation for a non-spherical tool,and,in this paper,we present one.Specifically,we first define and construct two fields on the surface to be machined-the collision-free tool orientation field(vector)and the iso-scallop height distance field(scalar).The iso-lines of the scalar field and their associated tool orientation field vectors then naturally serve as potential iso-scallop height five-axis tool paths,and we present a propagation-based algorithm to construct the desired tool path from the iso-lines.The computer simulation and physical cutting experiments confirm that everywhere on the surface,except maybe near the saddle curves of the scalar filed,the scallop height is exactly the given thresh-old.By adding the saddle curves as extra tool paths,the final machined surface then is assured of the required scallop height requirement.
NETL
NSTL
万方数据