The resource-intensive,high-fidelity infrared signature simulations and Radar CrossSection(RCS)calculations limit the integrated optimization of Unmanned Combat Aerial Vehicles(UCAVs)in response to escalating threats ...The resource-intensive,high-fidelity infrared signature simulations and Radar CrossSection(RCS)calculations limit the integrated optimization of Unmanned Combat Aerial Vehicles(UCAVs)in response to escalating threats from joint detection systems.To this end,we present a sample-efficient framework to advance the optimization efficiency of UCAV's exhaust system,focusing on both the stealth characteristics evaluation and the optimization process.A novel multi-fidelity stealth assessment method,powered by multi-fidelity neural network and local perceptive fields,has been developed to fuse different fidelity information from infrared radiation signature and RCS values,respectively.Results demonstrate that the method can achieve relatively high accuracy based on a small set of high-fidelity data.Furthermore,this data fusion method is integrated into a multi-objective Bayesian optimization framework.Employing a Gaussian process regression model and the EHVI acquisition function,the framework effectively explores the stealth objective space,achieving a 15.21%hypervolume indicator increase with fewer optimization iterations compared to NSGA-Ⅱ.Results show that the optimized nozzle significantly reduces both the infrared signature and RCS compared to the baseline configuration.The proposed framework offers a practical and efficient approach for optimizing the integrated stealth performance of UCAVs.展开更多
By introducing a dimensionless parameter to couple the two objectives, weight and radar absorbing performance, into a single objective function, a multi-objective optimization procedure for the radar absorbing sandwic...By introducing a dimensionless parameter to couple the two objectives, weight and radar absorbing performance, into a single objective function, a multi-objective optimization procedure for the radar absorbing sandwich structure （RASS） with a cellular core is proposed. The optimization models considered are one-side clamped sandwich panels with four kinds of cores subject to uniformly distributed loads. The average specular reflectivity calculated with the transfer matrix method and the periodic moment method is utilized to characterize the radar absorbing performance, while the mechanical constraints include the facesheet yielding, core shearing, and facesheet wrinkling. The optimization analysis indicates that the sandwich structure with a two-dimensional （2D） composite lattice core filled with ultra-lightweight sponge may be a better candidate of lightweight RASS than those with cellular foam or hexagonal honeycomb cores. The 2D Kagome lattice is found to outperform the square lattice with respect to radar absorbing.展开更多
A novel modified optimization technique known as the multi-objective micro particle swarm optimization（MO-MicPSO） is proposed for polyphase coded signal design.The proposed MO-MicPSO requires only a small population...A novel modified optimization technique known as the multi-objective micro particle swarm optimization（MO-MicPSO） is proposed for polyphase coded signal design.The proposed MO-MicPSO requires only a small population size compared with the standard particle swarm optimization that uses a larger population size.This new method is guided by an elite archive to finish the multi-objective optimization.The orthogonal polyphase coded signal（OPCS） can fundamentally improve the multiple input multiple output（MIMO） radar system performance,with which the radar system has high resolution and abundant signal channels.Simulation results on the polyphase coded signal design show that the MO-MicPSO can perform quite well for this high-dimensional multi-objective optimized problem.Compared with particle swarm optimization or genetic algorithm,the proposed MO-MicPSO has a better optimized efficiency and less time consumption.展开更多
In order to improve detection and estimation performance of distributed OrthogonalFrequency-Division Multiplexing（OFDM） Multiple-Input Multiple-Output（MIMO） radar system in multi-target scene, we propose a novel a...In order to improve detection and estimation performance of distributed OrthogonalFrequency-Division Multiplexing（OFDM） Multiple-Input Multiple-Output（MIMO） radar system in multi-target scene, we propose a novel approach of Adaptive Waveform Design（AWD） based on a constrained Multi-Objective Optimization（MOO）. The sparse measurement model of this radar system is derived, and the method based on decomposed Dantzig selectors is applied for the sparse recovery according to the block structures of the sparse vector and the system matrix. An AWD approach is proposed, which optimizes two objective functions, namely minimizing the upper bound of the recovery error and maximizing the weakest-target return, by adjusting the complex weights of the emitting waveform amplitudes. Several numerical simulations are provided and their results show that the detection and estimation performance of the radar system is improved significantly when this MOO-based AWD approach is applied to the distributed OFDM MIMO radar system. Especially, we verify the effectiveness of our AWD approach when the available samples are reduced severally and the technique of compressed sensing is introduced.展开更多
Caused by the environment clutter,the radar false alarm plots are unavoidable.Suppressing false alarm points has always been a key issue in Radar plots procession.In this paper,a radar false alarm plots elimination me...Caused by the environment clutter,the radar false alarm plots are unavoidable.Suppressing false alarm points has always been a key issue in Radar plots procession.In this paper,a radar false alarm plots elimination method based on multi-feature extraction and classification is proposed to effectively eliminate false alarm plots.Firstly,the density based spatial clustering of applications with noise(DBSCAN)algorithm is used to cluster the radar echo data processed by constant false-alarm rate(CFAR).The multi-features including the scale features,time domain features and transform domain features are extracted.Secondly,a feature evaluation method combining pearson correlation coefficient(PCC)and entropy weight method(EWM)is proposed to evaluate interrelation among features,effective feature combination sets are selected as inputs of the classifier.Finally,False alarm plots classified as clutters are eliminated.The experimental results show that proposed method can eliminate about 90%false alarm plots with less target loss rate.展开更多
基金supported by the National Natural Science Foundation of China(No.12102356)。
文摘The resource-intensive,high-fidelity infrared signature simulations and Radar CrossSection(RCS)calculations limit the integrated optimization of Unmanned Combat Aerial Vehicles(UCAVs)in response to escalating threats from joint detection systems.To this end,we present a sample-efficient framework to advance the optimization efficiency of UCAV's exhaust system,focusing on both the stealth characteristics evaluation and the optimization process.A novel multi-fidelity stealth assessment method,powered by multi-fidelity neural network and local perceptive fields,has been developed to fuse different fidelity information from infrared radiation signature and RCS values,respectively.Results demonstrate that the method can achieve relatively high accuracy based on a small set of high-fidelity data.Furthermore,this data fusion method is integrated into a multi-objective Bayesian optimization framework.Employing a Gaussian process regression model and the EHVI acquisition function,the framework effectively explores the stealth objective space,achieving a 15.21%hypervolume indicator increase with fewer optimization iterations compared to NSGA-Ⅱ.Results show that the optimized nozzle significantly reduces both the infrared signature and RCS compared to the baseline configuration.The proposed framework offers a practical and efficient approach for optimizing the integrated stealth performance of UCAVs.
基金Project supported by the National Natural Science Foundation of China (Nos. 90816025, 10632060,and 10640150395)the National Basic Research Program of China (No. G2006CB601202)the Fund of State Key Laboratory of Explosion Science and Technology (No. KFJJ08-15)
文摘By introducing a dimensionless parameter to couple the two objectives, weight and radar absorbing performance, into a single objective function, a multi-objective optimization procedure for the radar absorbing sandwich structure （RASS） with a cellular core is proposed. The optimization models considered are one-side clamped sandwich panels with four kinds of cores subject to uniformly distributed loads. The average specular reflectivity calculated with the transfer matrix method and the periodic moment method is utilized to characterize the radar absorbing performance, while the mechanical constraints include the facesheet yielding, core shearing, and facesheet wrinkling. The optimization analysis indicates that the sandwich structure with a two-dimensional （2D） composite lattice core filled with ultra-lightweight sponge may be a better candidate of lightweight RASS than those with cellular foam or hexagonal honeycomb cores. The 2D Kagome lattice is found to outperform the square lattice with respect to radar absorbing.
基金supported by the National Natural Science Foundation of China (60601016)
文摘A novel modified optimization technique known as the multi-objective micro particle swarm optimization（MO-MicPSO） is proposed for polyphase coded signal design.The proposed MO-MicPSO requires only a small population size compared with the standard particle swarm optimization that uses a larger population size.This new method is guided by an elite archive to finish the multi-objective optimization.The orthogonal polyphase coded signal（OPCS） can fundamentally improve the multiple input multiple output（MIMO） radar system performance,with which the radar system has high resolution and abundant signal channels.Simulation results on the polyphase coded signal design show that the MO-MicPSO can perform quite well for this high-dimensional multi-objective optimized problem.Compared with particle swarm optimization or genetic algorithm,the proposed MO-MicPSO has a better optimized efficiency and less time consumption.
基金supported by the National Basic Research Program of China(No.613205212)
文摘In order to improve detection and estimation performance of distributed OrthogonalFrequency-Division Multiplexing（OFDM） Multiple-Input Multiple-Output（MIMO） radar system in multi-target scene, we propose a novel approach of Adaptive Waveform Design（AWD） based on a constrained Multi-Objective Optimization（MOO）. The sparse measurement model of this radar system is derived, and the method based on decomposed Dantzig selectors is applied for the sparse recovery according to the block structures of the sparse vector and the system matrix. An AWD approach is proposed, which optimizes two objective functions, namely minimizing the upper bound of the recovery error and maximizing the weakest-target return, by adjusting the complex weights of the emitting waveform amplitudes. Several numerical simulations are provided and their results show that the detection and estimation performance of the radar system is improved significantly when this MOO-based AWD approach is applied to the distributed OFDM MIMO radar system. Especially, we verify the effectiveness of our AWD approach when the available samples are reduced severally and the technique of compressed sensing is introduced.
文摘Caused by the environment clutter,the radar false alarm plots are unavoidable.Suppressing false alarm points has always been a key issue in Radar plots procession.In this paper,a radar false alarm plots elimination method based on multi-feature extraction and classification is proposed to effectively eliminate false alarm plots.Firstly,the density based spatial clustering of applications with noise(DBSCAN)algorithm is used to cluster the radar echo data processed by constant false-alarm rate(CFAR).The multi-features including the scale features,time domain features and transform domain features are extracted.Secondly,a feature evaluation method combining pearson correlation coefficient(PCC)and entropy weight method(EWM)is proposed to evaluate interrelation among features,effective feature combination sets are selected as inputs of the classifier.Finally,False alarm plots classified as clutters are eliminated.The experimental results show that proposed method can eliminate about 90%false alarm plots with less target loss rate.
