In the design of conventional microwave devices, the parameters need to be continuously optimized to meet the desired targets, and the whole process is time-consuming and laborious. As a surrogate model, machine learning is an effective optimization method. However, in the modeling process, the highdimensional data processing and the complex nonlinear relationship between parameters is a problem to be solved. This paper proposes a deep learning model for designing UWB antennas, which determines the model structure of deep belief network (DBN) by particle swarm algorithm (PSO), and then combines DBN and extreme learning machine (ELM). The proposed model can obtain higher feature learning capability and nonlinear function approximation capability, and has been applied to the optimal design of the whole structure of the fractal antenna and the notch structure of the MIMO antenna, and its S-parameters are well fitted while meeting the requirements of the design targets. The DBN-ELM method obtains the good results when compared with common modeling methods using the same training samples (the root mean square error tested is 11.87% in the fractal antenna and 3.56% in the MIMO antenna). Overall, the proposed DBN-ELM model has higher predictive and generalization capabilities, which can also be used to model more complex antenna structures.
INDEX TERMSDeep belief network (DBN),Extreme learning machine (ELM),Particle swarm optimization (PSO),UWB antenna.
A miniaturized ultra-wideband multiple-input multiple-output (UWB MIMO) two-port antenna with high isolation based on FR4 is designed in this article. The size of the antenna is only 18 × 28 × 1.6 mm3. The MIMO antenna consists of two identical antenna elements symmetrically placed on the same dielectric substrate in opposite directions. By loading three crossed X-shaped stubs between two unconnected ground planes, high isolation and good impedance matching are achieved. The working frequency band measured by this UWB MIMO antenna is 1.9–14 GHz, and the isolation is kept above 20.2 dB in the whole analysis frequency band. Good radiation characteristics as well as envelope correlation coefficient (ECC, <0.09), mean effective gain (MEG), and channel capacity loss (CCL) in the passband meet the requirements of the application, which can be applied to the UWB wireless communication system. To verify the applicability of the proposed method for enhancing the isolation between antenna elements, the two-port antenna structure was extended to a four-port antenna structure. In the case of loading the X-shaped stubs to connect to the ground plane, the isolation of the antenna is maintained above 15.5 dB within 1.7–14 GHz.
'New' Class-E solutions are proposed by varying three different design parameters which are introduced in the voltage and current equations in order to extend the Class-E 'design space', of which the 'new' solutions can apply to optimal and suboptimal operation. The design procedure of suboptimal Class-E power amplifier (PA) is analysed in details and then a suboptimal Class-E PA based on GaN HEMT CGH40010F is designed to prove the correctness of the 'new' solutions. The measured maximum output power of 39.6 dB, power-added-efficiency of 74.7% and drain efficiency of 78.9% were obtained at 2.6 GHz with a 28 dBm input power. These measurement results show that a similar or better level of efficiency and output power that are reported for optimal Class-E PAs at lower frequencies using the same transistor, and the presented 'new' solutions extend the 'design space' of Class-E PA. This paper give engineers more degrees of freedom to design Class-E PA.
scite is a Brooklyn-based organization that helps researchers better discover and understand research articles through Smart Citations–citations that display the context of the citation and describe whether the article provides supporting or contrasting evidence. scite is used by students and researchers from around the world and is funded in part by the National Science Foundation and the National Institute on Drug Abuse of the National Institutes of Health.