This paper proposed a new method of expanding the bandwidth of PUMA array. By attaching bottom-open vias below the coupling plate, lower operating frequency is available without increasing the profile. This design ult...
详细信息
Aerodynamic force prediction is an important application of deep learning in the field of fluid mechanics. In this paper, a light graph neural network model with residual connections named LRGCN is designed to speed t...
详细信息
In this paper, a millimeter-wave (mmW) wide band right-handed circularly polarized (RHCP) horn antenna is designed based on a polarizer with two 90 degree slots loaded on the inner wall of a circular waveguide. The an...
详细信息
Flow field prediction of variable geometry aims for the precise prediction of varying flow fields with complex geometric shapes and their variations. By combining a novel deep convolutional neural network (CNN) model ...
详细信息
With the advancement of remote sensing technology, video satellites have played an increasingly important role in both military and civilian domains, and they are widely used in areas such as military guidance, intell...
详细信息
In this paper, a millimeter wave (mmW) wide band right-handed circularly polarized (RHCP) horn antenna is designed with a polarizer in the form of a rectangular waveguide (RW). The antenna is fed by a standard RW WR-1...
详细信息
A method for designing the finite-time prescribed performance controller with RBFNN(Radial Basis Function Networks) is proposed for the HFV(Hypersonic Flight Vehicle) longitudinal attitude systems with parameters unce...
详细信息
ISBN:
(数字)9789887581536
ISBN:
(纸本)9781665482561
A method for designing the finite-time prescribed performance controller with RBFNN(Radial Basis Function Networks) is proposed for the HFV(Hypersonic Flight Vehicle) longitudinal attitude systems with parameters uncertainties and time-varying ***,the appointed-time prescribed performance functions for outer-loop and inner-loop are designed respectively,which aims to restrain the transient and steady-state performance of command tracking *** with the traditional prescribed performance function,the proposed method can guarantee that the errors convergence to the set stability precision at the appointed ***,the error-transform function is applied to transform the guidance command errors into un-limited boundary,which can ensure the error satisfy the constraint condition by means of controlling the transformed ***,the virtual control law of outer-loop subsystem and the actual control law of inner-loop subsystem are designed independently,and the lumped disturbances are estimated by the RBFNN,a novel finite-time tracking differentiator is applied to avoid the 'explosion of terms' problem in the control law design ***,comparative simulations with parametric uncertainties and time-varying disturbance are performed to demonstrate that the proposed method in this paper can effectively satisfy the prescribed performance constraints.
There are many adjustable parameters in the control method of predictive sliding mode control(PSMC) law and linear extended state observer(LESO) for hypersonic vehicle speed and altitude,and the adjustable parameters ...
详细信息
ISBN:
(数字)9789887581536
ISBN:
(纸本)9781665482561
There are many adjustable parameters in the control method of predictive sliding mode control(PSMC) law and linear extended state observer(LESO) for hypersonic vehicle speed and altitude,and the adjustable parameters influence each other on the control effect,and the speed and altitude channels of the aircraft are coupled with each other,so the controller parameters cannot be independently tuned.A method of automatically tuning controller parameters by using grey wolf optimization(GWO) algorithm is ***,the fitness function containing the desired control effect is designed,and then the appropriate number of search agent and iteration times are *** simulation results show that the control effect of the controller with GWO tuning parameters is obviously better than that of the controller with experience tuning parameters,and the expected control effect can be achieved under the condition of adding parameter deviation and actuator limitation.
A novel split ring (SR) wide-angle impedance matching (WAIM) printed on a double-layer PCB was designed to replace the dielectric slabs WAIM or frequency selective surface (FSS) WAIM with high profile. The proposed WA...
详细信息
Transfer learning(TL)utilizes data or knowledge from one or more source domains to facilitate learning in a target *** is particularly useful when the target domain has very few or no labeled data,due to annotation ex...
详细信息
Transfer learning(TL)utilizes data or knowledge from one or more source domains to facilitate learning in a target *** is particularly useful when the target domain has very few or no labeled data,due to annotation expense,privacy concerns,***,the effectiveness of TL is not always *** transfer(NT),i.e.,leveraging source domain data/knowledge undesirably reduces learning performance in the target domain,and has been a long-standing and challenging problem in *** approaches have been proposed in the literature to address this ***,there does not exist a systematic *** paper fills this gap,by first introducing the definition of NT and its causes,and reviewing over fifty representative approaches for overcoming NT,which fall into three categories:domain similarity estimation,safe transfer,and NT *** areas,including computer vision,bioinformatics,natural language processing,recommender systems,and robotics,that use NT mitigation strategies to facilitate positive transfers,are also ***,we give guidelines on NT task construction and baseline algorithms,benchmark existing TL and NT mitigation approaches on three NT-specific datasets,and point out challenges and future research *** ensure reproducibility,our code is publicized at https://***/chamwen/NT-Benchmark.
暂无评论