Dynamic soaring,inspired by the wind-riding flight of birds such as albatrosses,is a biomimetic technique which leverages wind fields to enhance the endurance of unmanned aerial vehicles(UAVs).Achieving a precise soar...Dynamic soaring,inspired by the wind-riding flight of birds such as albatrosses,is a biomimetic technique which leverages wind fields to enhance the endurance of unmanned aerial vehicles(UAVs).Achieving a precise soaring trajectory is crucial for maximizing energy efficiency during flight.Existing nonlinear programming methods are heavily dependent on the choice of initial values which is hard to determine.Therefore,this paper introduces a deep reinforcement learning method based on a differentially flat model for dynamic soaring trajectory planning and optimization.Initially,the gliding trajectory is parameterized using Fourier basis functions,achieving a flexible trajectory representation with a minimal number of hyperparameters.Subsequently,the trajectory optimization problem is formulated as a dynamic interactive process of Markov decision-making.The hyperparameters of the trajectory are optimized using the Proximal Policy Optimization(PPO2)algorithm from deep reinforcement learning(DRL),reducing the strong reliance on initial value settings in the optimization process.Finally,a comparison between the proposed method and the nonlinear programming method reveals that the trajectory generated by the proposed approach is smoother while meeting the same performance requirements.Specifically,the proposed method achieves a 34%reduction in maximum thrust,a 39.4%decrease in maximum thrust difference,and a 33%reduction in maximum airspeed difference.展开更多
Trans-medium flight vehicles can combine high aerial maneuverability and underwater concealment ability,which have attracted much attention recently.As the most crucial procedure,the trajectory design generally determ...Trans-medium flight vehicles can combine high aerial maneuverability and underwater concealment ability,which have attracted much attention recently.As the most crucial procedure,the trajectory design generally determines the trans-medium flight vehicle performance.To quantitatively analyze the flight vehicle performance,an entire aerial-aquatic trajectory model is developed in this paper.Different from modeling a trajectory purely for the water entry process,the constructed entire trajectory model has integrated aerial,water entry,and underwater trajectories together,which can consider the influence of the connected trajectories.As for the aerial and underwater trajectories,explicit dynamic models are established to obtain the trajectory parameters.Due to the complicated fluid force during high-velocity water entry,a computational fluid dynamics model is investigated to analyze this phase.The compu-tational domain size is adaptively refined according to the final aerial trajectory state,where the redundant computational domain is removed.An entire trajectory optimization problem is then formulated to maximize the total flight range via tuning the joint states of different trajectories.Simultaneously,several constraints,i.e.,the max impact load,trajectory height,etc.,are involved in the optimization problem.Rather than directly optimizing by a heuristic algorithm,a multi-surrogate cooperative sampling-based optimization method is proposed to alleviate the computational complexity of the entire trajectory optimization problem.In this method,various surrogates coopera-tively generate infill sample points,thereby preventing the poor approximation.After optimization,the total flight range can be improved by 20%,while all the constraints are satisfied.The result demonstrates the effectiveness and practicability of the developed model and optimization framework.展开更多
This paper addresses the time-varying formation-containment(FC) problem for nonholonomic multi-agent systems with a desired trajectory constraint, where only the leaders can acquire information about the desired traje...This paper addresses the time-varying formation-containment(FC) problem for nonholonomic multi-agent systems with a desired trajectory constraint, where only the leaders can acquire information about the desired trajectory. Input the fixed time-varying formation template to the leader and start executing, this process also needs to track the desired trajectory, and the follower needs to converge to the convex hull that the leader crosses. Firstly, the dynamic models of nonholonomic systems are linearized to second-order dynamics. Then, based on the desired trajectory and formation template, the FC control protocols are proposed. Sufficient conditions to achieve FC are introduced and an algorithm is proposed to resolve the control parameters by solving an algebraic Riccati equation. The system is demonstrated to achieve FC, with the average position and velocity of the leaders converging asymptotically to the desired trajectory. Finally, the theoretical achievements are verified in simulations by a multi-agent system composed of virtual human individuals.展开更多
Recently, high-precision trajectory prediction of ballistic missiles in the boost phase has become a research hotspot. This paper proposes a trajectory prediction algorithm driven by data and knowledge(DKTP) to solve ...Recently, high-precision trajectory prediction of ballistic missiles in the boost phase has become a research hotspot. This paper proposes a trajectory prediction algorithm driven by data and knowledge(DKTP) to solve this problem. Firstly, the complex dynamics characteristics of ballistic missile in the boost phase are analyzed in detail. Secondly, combining the missile dynamics model with the target gravity turning model, a knowledge-driven target three-dimensional turning(T3) model is derived. Then, the BP neural network is used to train the boost phase trajectory database in typical scenarios to obtain a datadriven state parameter mapping(SPM) model. On this basis, an online trajectory prediction framework driven by data and knowledge is established. Based on the SPM model, the three-dimensional turning coefficients of the target are predicted by using the current state of the target, and the state of the target at the next moment is obtained by combining the T3 model. Finally, simulation verification is carried out under various conditions. The simulation results show that the DKTP algorithm combines the advantages of data-driven and knowledge-driven, improves the interpretability of the algorithm, reduces the uncertainty, which can achieve high-precision trajectory prediction of ballistic missile in the boost phase.展开更多
Hypersonic Glide Vehicles(HGVs)are advanced aircraft that can achieve extremely high speeds(generally over 5 Mach)and maneuverability within the Earth's atmosphere.HGV trajectory prediction is crucial for effectiv...Hypersonic Glide Vehicles(HGVs)are advanced aircraft that can achieve extremely high speeds(generally over 5 Mach)and maneuverability within the Earth's atmosphere.HGV trajectory prediction is crucial for effective defense planning and interception strategies.In recent years,HGV trajectory prediction methods based on deep learning have the great potential to significantly enhance prediction accuracy and efficiency.However,it's still challenging to strike a balance between improving prediction performance and reducing computation costs of the deep learning trajectory prediction models.To solve this problem,we propose a new deep learning framework(FECA-LSMN)for efficient HGV trajectory prediction.The model first uses a Frequency Enhanced Channel Attention(FECA)module to facilitate the fusion of different HGV trajectory features,and then subsequently employs a Light Sampling-oriented Multi-Layer Perceptron Network(LSMN)based on simple MLP-based structures to extract long/shortterm HGV trajectory features for accurate trajectory prediction.Also,we employ a new data normalization method called reversible instance normalization(RevIN)to enhance the prediction accuracy and training stability of the network.Compared to other popular trajectory prediction models based on LSTM,GRU and Transformer,our FECA-LSMN model achieves leading or comparable performance in terms of RMSE,MAE and MAPE metrics while demonstrating notably faster computation time.The ablation experiments show that the incorporation of the FECA module significantly improves the prediction performance of the network.The RevIN data normalization technique outperforms traditional min-max normalization as well.展开更多
Compared with single-domain unmanned swarms,cross-domain unmanned swarms continue to face new challenges in terms of platform performance and constraints.In this paper,a joint unmanned swarm target assignment and miss...Compared with single-domain unmanned swarms,cross-domain unmanned swarms continue to face new challenges in terms of platform performance and constraints.In this paper,a joint unmanned swarm target assignment and mission trajectory planning method is proposed to meet the requirements of cross-domain unmanned swarm mission planning.Firstly,the different performances of cross-domain heterogeneous platforms and mission requirements of targets are characterised by using a collection of operational resources.Secondly,an algorithmic framework for joint target assignment and mission trajectory planning is proposed,in which the initial planning of the trajectory is performed in the target assignment phase,while the trajectory is further optimised afterwards.Next,the estimation of the distribution algorithms is combined with the genetic algorithm to solve the objective function.Finally,the algorithm is numerically simulated by specific cases.Simulation results indicate that the proposed algorithm can perform effective task assignment and trajectory planning for cross-domain unmanned swarms.Furthermore,the solution performance of the hybrid estimation of distribution algorithm(EDA)-genetic algorithm(GA)algorithm is better than that of GA and EDA.展开更多
The longitudinal dispersion of the projectile in shooting tests of two-dimensional trajectory corrections fused with fixed canards is extremely large that it sometimes exceeds the correction ability of the correction ...The longitudinal dispersion of the projectile in shooting tests of two-dimensional trajectory corrections fused with fixed canards is extremely large that it sometimes exceeds the correction ability of the correction fuse actuator.The impact point easily deviates from the target,and thus the correction result cannot be readily evaluated.However,the cost of shooting tests is considerably high to conduct many tests for data collection.To address this issue,this study proposes an aiming method for shooting tests based on small sample size.The proposed method uses the Bootstrap method to expand the test data;repeatedly iterates and corrects the position of the simulated theoretical impact points through an improved compatibility test method;and dynamically adjusts the weight of the prior distribution of simulation results based on Kullback-Leibler divergence,which to some extent avoids the real data being"submerged"by the simulation data and achieves the fusion Bayesian estimation of the dispersion center.The experimental results show that when the simulation accuracy is sufficiently high,the proposed method yields a smaller mean-square deviation in estimating the dispersion center and higher shooting accuracy than those of the three comparison methods,which is more conducive to reflecting the effect of the control algorithm and facilitating test personnel to iterate their proposed structures and algorithms.;in addition,this study provides a knowledge base for further comprehensive studies in the future.展开更多
Natural events have had a significant impact on overall flight activity,and the aviation industry plays a vital role in helping society cope with the impact of these events.As one of the most impactful weather typhoon...Natural events have had a significant impact on overall flight activity,and the aviation industry plays a vital role in helping society cope with the impact of these events.As one of the most impactful weather typhoon seasons appears and continues,airlines operating in threatened areas and passengers having travel plans during this time period will pay close attention to the development of tropical storms.This paper proposes a deep multimodal fusion and multitasking trajectory prediction model that can improve the reliability of typhoon trajectory prediction and reduce the quantity of flight scheduling cancellation.The deep multimodal fusion module is formed by deep fusion of the feature output by multiple submodal fusion modules,and the multitask generation module uses longitude and latitude as two related tasks for simultaneous prediction.With more dependable data accuracy,problems can be analysed rapidly and more efficiently,enabling better decision-making with a proactive versus reactive posture.When multiple modalities coexist,features can be extracted from them simultaneously to supplement each other’s information.An actual case study,the typhoon Lichma that swept China in 2019,has demonstrated that the algorithm can effectively reduce the number of unnecessary flight cancellations compared to existing flight scheduling and assist the new generation of flight scheduling systems under extreme weather.展开更多
巷道断面成形是煤矿掘进过程中的重要工序,但目前的巷道断面成形作业多为人工控制掘进机进行往复式截割,制约了煤矿掘进工作面的智能化发展。为此,针对断面成形轨迹规划未考虑煤岩特征、优化目标单一的问题,提出了一种基于改进灰狼优化(...巷道断面成形是煤矿掘进过程中的重要工序,但目前的巷道断面成形作业多为人工控制掘进机进行往复式截割,制约了煤矿掘进工作面的智能化发展。为此,针对断面成形轨迹规划未考虑煤岩特征、优化目标单一的问题,提出了一种基于改进灰狼优化(grey wolf optimizer, GWO)算法的掘进机断面成形轨迹规划方法。首先,根据夹矸位置将待截割断面环境分为4种情况,对相应断面进行栅格化处理并建立栅格地图,同时采用二值膨胀法对不规则夹矸进行膨胀化处理。然后,对GWO算法进行了改进,以提升其寻优性能和收敛速度。接着,开展了仿真实验,利用改进GWO算法实现了4种环境下掘进机断面成形轨迹的规划。最后,利用掘进机样机开展了断面截割实验。仿真结果表明:相较于传统的GWO算法,改进GWO算法的收敛速度更快且收敛精度更高;在4种断面环境下,基于改进GWO算法规划的断面成形轨迹长度最短,欠挖面积最小,转向次数最少,更容易实现高精度、高效率的轨迹跟踪控制,保证了巷道断面的成形质量。实验结果表明,基于改进GWO算法规划的断面成形轨迹既能提高掘进机的截割效率,又能满足巷道断面成形的质量要求。研究结果可为煤矿井下智能掘进技术的发展提供新的思路和方法。展开更多
为了更好探测识别与跟踪空飘球,考虑到空飘球运动与环境风的高度相关性,综合应用雷达探测定位、风场反演技术提出一种预测空飘球轨迹并判断其载荷的方法。基于当下主流的速度平面处理方法提出双体积单元风场反演方案。方案中,通过建立...为了更好探测识别与跟踪空飘球,考虑到空飘球运动与环境风的高度相关性,综合应用雷达探测定位、风场反演技术提出一种预测空飘球轨迹并判断其载荷的方法。基于当下主流的速度平面处理方法提出双体积单元风场反演方案。方案中,通过建立空飘球流体力学分析下的动力学模型实现空飘球在空轨迹的预测;引入轨迹惯性度(degree of inertia,DOI)和质阻比计算空飘球空载状态下理论轨迹与实际轨迹的差异,分析其自身空飘属性与携带载荷状况。通过仿真实验验证所提方法,结果表明所提风场反演方法各方向风场反演平均绝对误差在0.1以下,轨迹预测误差小于0.162,且在随机观测误差下展现了较好的鲁棒性;通过DOI值能有效判断空飘球带载有无的情况且判断结果受风场观测误差影响较小,相较于空载状态,载荷质量增加1%时DOI值增加16倍,并能较好表现空飘球与载荷之间的质量分布关系,且当载荷质量占比7%以上时DOI判据更为有效;同时通过DOI值能用于判断空飘球是否具备自主动力,根据仿真结果可以认为DOI值大于202,表明空飘球可能具备自主动力。展开更多
基金support received by the National Natural Science Foundation of China(Grant Nos.52372398&62003272).
文摘Dynamic soaring,inspired by the wind-riding flight of birds such as albatrosses,is a biomimetic technique which leverages wind fields to enhance the endurance of unmanned aerial vehicles(UAVs).Achieving a precise soaring trajectory is crucial for maximizing energy efficiency during flight.Existing nonlinear programming methods are heavily dependent on the choice of initial values which is hard to determine.Therefore,this paper introduces a deep reinforcement learning method based on a differentially flat model for dynamic soaring trajectory planning and optimization.Initially,the gliding trajectory is parameterized using Fourier basis functions,achieving a flexible trajectory representation with a minimal number of hyperparameters.Subsequently,the trajectory optimization problem is formulated as a dynamic interactive process of Markov decision-making.The hyperparameters of the trajectory are optimized using the Proximal Policy Optimization(PPO2)algorithm from deep reinforcement learning(DRL),reducing the strong reliance on initial value settings in the optimization process.Finally,a comparison between the proposed method and the nonlinear programming method reveals that the trajectory generated by the proposed approach is smoother while meeting the same performance requirements.Specifically,the proposed method achieves a 34%reduction in maximum thrust,a 39.4%decrease in maximum thrust difference,and a 33%reduction in maximum airspeed difference.
基金supported by the National Natural Science Foundation of China(Grant Nos.52425211,52272360,and 52472394)Chongqing Natural Science Foundation(CSTB2023NSCQ-MSX0300)。
文摘Trans-medium flight vehicles can combine high aerial maneuverability and underwater concealment ability,which have attracted much attention recently.As the most crucial procedure,the trajectory design generally determines the trans-medium flight vehicle performance.To quantitatively analyze the flight vehicle performance,an entire aerial-aquatic trajectory model is developed in this paper.Different from modeling a trajectory purely for the water entry process,the constructed entire trajectory model has integrated aerial,water entry,and underwater trajectories together,which can consider the influence of the connected trajectories.As for the aerial and underwater trajectories,explicit dynamic models are established to obtain the trajectory parameters.Due to the complicated fluid force during high-velocity water entry,a computational fluid dynamics model is investigated to analyze this phase.The compu-tational domain size is adaptively refined according to the final aerial trajectory state,where the redundant computational domain is removed.An entire trajectory optimization problem is then formulated to maximize the total flight range via tuning the joint states of different trajectories.Simultaneously,several constraints,i.e.,the max impact load,trajectory height,etc.,are involved in the optimization problem.Rather than directly optimizing by a heuristic algorithm,a multi-surrogate cooperative sampling-based optimization method is proposed to alleviate the computational complexity of the entire trajectory optimization problem.In this method,various surrogates coopera-tively generate infill sample points,thereby preventing the poor approximation.After optimization,the total flight range can be improved by 20%,while all the constraints are satisfied.The result demonstrates the effectiveness and practicability of the developed model and optimization framework.
文摘This paper addresses the time-varying formation-containment(FC) problem for nonholonomic multi-agent systems with a desired trajectory constraint, where only the leaders can acquire information about the desired trajectory. Input the fixed time-varying formation template to the leader and start executing, this process also needs to track the desired trajectory, and the follower needs to converge to the convex hull that the leader crosses. Firstly, the dynamic models of nonholonomic systems are linearized to second-order dynamics. Then, based on the desired trajectory and formation template, the FC control protocols are proposed. Sufficient conditions to achieve FC are introduced and an algorithm is proposed to resolve the control parameters by solving an algebraic Riccati equation. The system is demonstrated to achieve FC, with the average position and velocity of the leaders converging asymptotically to the desired trajectory. Finally, the theoretical achievements are verified in simulations by a multi-agent system composed of virtual human individuals.
基金the National Natural Science Foundation of China (Grants No. 12072090 and No.12302056) to provide fund for conducting experiments。
文摘Recently, high-precision trajectory prediction of ballistic missiles in the boost phase has become a research hotspot. This paper proposes a trajectory prediction algorithm driven by data and knowledge(DKTP) to solve this problem. Firstly, the complex dynamics characteristics of ballistic missile in the boost phase are analyzed in detail. Secondly, combining the missile dynamics model with the target gravity turning model, a knowledge-driven target three-dimensional turning(T3) model is derived. Then, the BP neural network is used to train the boost phase trajectory database in typical scenarios to obtain a datadriven state parameter mapping(SPM) model. On this basis, an online trajectory prediction framework driven by data and knowledge is established. Based on the SPM model, the three-dimensional turning coefficients of the target are predicted by using the current state of the target, and the state of the target at the next moment is obtained by combining the T3 model. Finally, simulation verification is carried out under various conditions. The simulation results show that the DKTP algorithm combines the advantages of data-driven and knowledge-driven, improves the interpretability of the algorithm, reduces the uncertainty, which can achieve high-precision trajectory prediction of ballistic missile in the boost phase.
文摘Hypersonic Glide Vehicles(HGVs)are advanced aircraft that can achieve extremely high speeds(generally over 5 Mach)and maneuverability within the Earth's atmosphere.HGV trajectory prediction is crucial for effective defense planning and interception strategies.In recent years,HGV trajectory prediction methods based on deep learning have the great potential to significantly enhance prediction accuracy and efficiency.However,it's still challenging to strike a balance between improving prediction performance and reducing computation costs of the deep learning trajectory prediction models.To solve this problem,we propose a new deep learning framework(FECA-LSMN)for efficient HGV trajectory prediction.The model first uses a Frequency Enhanced Channel Attention(FECA)module to facilitate the fusion of different HGV trajectory features,and then subsequently employs a Light Sampling-oriented Multi-Layer Perceptron Network(LSMN)based on simple MLP-based structures to extract long/shortterm HGV trajectory features for accurate trajectory prediction.Also,we employ a new data normalization method called reversible instance normalization(RevIN)to enhance the prediction accuracy and training stability of the network.Compared to other popular trajectory prediction models based on LSTM,GRU and Transformer,our FECA-LSMN model achieves leading or comparable performance in terms of RMSE,MAE and MAPE metrics while demonstrating notably faster computation time.The ablation experiments show that the incorporation of the FECA module significantly improves the prediction performance of the network.The RevIN data normalization technique outperforms traditional min-max normalization as well.
文摘Compared with single-domain unmanned swarms,cross-domain unmanned swarms continue to face new challenges in terms of platform performance and constraints.In this paper,a joint unmanned swarm target assignment and mission trajectory planning method is proposed to meet the requirements of cross-domain unmanned swarm mission planning.Firstly,the different performances of cross-domain heterogeneous platforms and mission requirements of targets are characterised by using a collection of operational resources.Secondly,an algorithmic framework for joint target assignment and mission trajectory planning is proposed,in which the initial planning of the trajectory is performed in the target assignment phase,while the trajectory is further optimised afterwards.Next,the estimation of the distribution algorithms is combined with the genetic algorithm to solve the objective function.Finally,the algorithm is numerically simulated by specific cases.Simulation results indicate that the proposed algorithm can perform effective task assignment and trajectory planning for cross-domain unmanned swarms.Furthermore,the solution performance of the hybrid estimation of distribution algorithm(EDA)-genetic algorithm(GA)algorithm is better than that of GA and EDA.
基金the National Natural Science Foundation of China(Grant No.61973033)Preliminary Research of Equipment(Grant No.9090102010305)for funding the experiments。
文摘The longitudinal dispersion of the projectile in shooting tests of two-dimensional trajectory corrections fused with fixed canards is extremely large that it sometimes exceeds the correction ability of the correction fuse actuator.The impact point easily deviates from the target,and thus the correction result cannot be readily evaluated.However,the cost of shooting tests is considerably high to conduct many tests for data collection.To address this issue,this study proposes an aiming method for shooting tests based on small sample size.The proposed method uses the Bootstrap method to expand the test data;repeatedly iterates and corrects the position of the simulated theoretical impact points through an improved compatibility test method;and dynamically adjusts the weight of the prior distribution of simulation results based on Kullback-Leibler divergence,which to some extent avoids the real data being"submerged"by the simulation data and achieves the fusion Bayesian estimation of the dispersion center.The experimental results show that when the simulation accuracy is sufficiently high,the proposed method yields a smaller mean-square deviation in estimating the dispersion center and higher shooting accuracy than those of the three comparison methods,which is more conducive to reflecting the effect of the control algorithm and facilitating test personnel to iterate their proposed structures and algorithms.;in addition,this study provides a knowledge base for further comprehensive studies in the future.
基金supported by the National Natural Science Foundation of China(62073330)。
文摘Natural events have had a significant impact on overall flight activity,and the aviation industry plays a vital role in helping society cope with the impact of these events.As one of the most impactful weather typhoon seasons appears and continues,airlines operating in threatened areas and passengers having travel plans during this time period will pay close attention to the development of tropical storms.This paper proposes a deep multimodal fusion and multitasking trajectory prediction model that can improve the reliability of typhoon trajectory prediction and reduce the quantity of flight scheduling cancellation.The deep multimodal fusion module is formed by deep fusion of the feature output by multiple submodal fusion modules,and the multitask generation module uses longitude and latitude as two related tasks for simultaneous prediction.With more dependable data accuracy,problems can be analysed rapidly and more efficiently,enabling better decision-making with a proactive versus reactive posture.When multiple modalities coexist,features can be extracted from them simultaneously to supplement each other’s information.An actual case study,the typhoon Lichma that swept China in 2019,has demonstrated that the algorithm can effectively reduce the number of unnecessary flight cancellations compared to existing flight scheduling and assist the new generation of flight scheduling systems under extreme weather.
文摘巷道断面成形是煤矿掘进过程中的重要工序,但目前的巷道断面成形作业多为人工控制掘进机进行往复式截割,制约了煤矿掘进工作面的智能化发展。为此,针对断面成形轨迹规划未考虑煤岩特征、优化目标单一的问题,提出了一种基于改进灰狼优化(grey wolf optimizer, GWO)算法的掘进机断面成形轨迹规划方法。首先,根据夹矸位置将待截割断面环境分为4种情况,对相应断面进行栅格化处理并建立栅格地图,同时采用二值膨胀法对不规则夹矸进行膨胀化处理。然后,对GWO算法进行了改进,以提升其寻优性能和收敛速度。接着,开展了仿真实验,利用改进GWO算法实现了4种环境下掘进机断面成形轨迹的规划。最后,利用掘进机样机开展了断面截割实验。仿真结果表明:相较于传统的GWO算法,改进GWO算法的收敛速度更快且收敛精度更高;在4种断面环境下,基于改进GWO算法规划的断面成形轨迹长度最短,欠挖面积最小,转向次数最少,更容易实现高精度、高效率的轨迹跟踪控制,保证了巷道断面的成形质量。实验结果表明,基于改进GWO算法规划的断面成形轨迹既能提高掘进机的截割效率,又能满足巷道断面成形的质量要求。研究结果可为煤矿井下智能掘进技术的发展提供新的思路和方法。
文摘针对传统的神经网络模型因超参数众多,在实验中比对最优参数组合效率低下导致误差较大和反应速度慢的问题。本文提出一种基于北方苍鹰优化(Northern Goshawk Optimization,NGO)算法和双向门控循环单元神经网络(Bidirectional Gated Recurrent Unit, Bi-GRU)的船舶轨迹预测模型NGO-Bi-GRU(Northern Goshawk Optimization Bidirectional Gated Recurrent Unit)。利用NGO对Bi-GRU模型的学习率、隐藏节点和正则化系数进行寻优,然后将寻优得到的网络超参数代入Bi-GRU进行船舶轨迹预测。将该模型与长短时记忆神经网络(Long Short Term Memory, LSTM)和门控循环单元神经网络模型(Gated Recurrent Unit, GRU)以及使用该算法优化的长短期神经网络模型进行实验对比,将均方误差、均方根误差、平均绝对误差作为评价标准。结果表明,NGO-Bi-GRU模型在经度和纬度预测上误差较小、精确度较高且数值波动更加稳定。
文摘为了更好探测识别与跟踪空飘球,考虑到空飘球运动与环境风的高度相关性,综合应用雷达探测定位、风场反演技术提出一种预测空飘球轨迹并判断其载荷的方法。基于当下主流的速度平面处理方法提出双体积单元风场反演方案。方案中,通过建立空飘球流体力学分析下的动力学模型实现空飘球在空轨迹的预测;引入轨迹惯性度(degree of inertia,DOI)和质阻比计算空飘球空载状态下理论轨迹与实际轨迹的差异,分析其自身空飘属性与携带载荷状况。通过仿真实验验证所提方法,结果表明所提风场反演方法各方向风场反演平均绝对误差在0.1以下,轨迹预测误差小于0.162,且在随机观测误差下展现了较好的鲁棒性;通过DOI值能有效判断空飘球带载有无的情况且判断结果受风场观测误差影响较小,相较于空载状态,载荷质量增加1%时DOI值增加16倍,并能较好表现空飘球与载荷之间的质量分布关系,且当载荷质量占比7%以上时DOI判据更为有效;同时通过DOI值能用于判断空飘球是否具备自主动力,根据仿真结果可以认为DOI值大于202,表明空飘球可能具备自主动力。
