微带径向短截线基于知识的人工神经网络模型

微带径向短截线具有比直微带短截线在更宽的频率范围内实现低阻抗值的优点。本文采用基于知识的人工神经网络模型模拟微带径向短截线的特性,利用已经具有的先验知识减小神经网络输入输出映射关系的复杂程度有效减少了训练样本的数量,本文建立的人工神经网络模型不仅保贸了全波有限元法的准确性,而且具有快速简便的优点。     

宽带W波段低噪声放大器的设计与制作

基于未来低功耗毫米波接收前端的应用,采用InP HEMT工艺实现了一种W波段宽带低噪声放大器.该放大器采用边缘耦合线用于级间的隔离,扇形短截线用于RF旁路,偏置网络采用薄膜电阻和扇形短截线以保持放大器的稳定性.采用3 mm噪声测试系统对单片进行在片测试.测试结果显示在80～102 GHz,噪声系数小于5 dB,相关增益大于19 dB.五级电路的栅、漏分别连在一起方便使用,芯片面积3.6 mm×1.7 mm,功耗30 mW.     

基于PSO-RBF神经网络的模拟电路故障诊断研究

针对模拟电路故障诊断的难点和传统诊断方法的不足之处,提出了一种基于PSO算法优化的RBF神经网络模拟电路故障诊断方法。为了约简网络结构从而提高诊断效率,采用主成分分析方法对故障特征进行有效提取。针对RBF网络传统训练算法中隐层节点中心及基函数宽度选取困难问题,提出采用PSO算法来优化训练RBF网络,以提高网络的训练速度和泛化性能。最后,通过电路仿真对所提方法的有效性进行了验证。     

Detection of basal cell carcinoma using electrical impedance and neural networks

Variations in electrical impedance over frequency might be used to distinguish basal cell carcinoma (BCC) from benign skin lesions, although the patterns that separate the two are nonobvious. Artificial neural networks (ANNs) may be good pattern classifiers for this application. A preliminary study to show the potential of neural networks to distinguish benign from malignant skin lesions using electrical impedance is presented. Electrical impedance was measured in vivo from 1 kHz to 1 MHz at five virtual depths on 18 BCC and 16 benign or premalignant lesions. A feed-forward neural network was trained using back propagation to classify these lesions. Two methods of preprocessing were used to account for the impedance of normal skin and the size of the lesion, one based on estimating the impedance of the lesion relative to adjacent normal skin and one based on estimating the impedance of the lesion independent of size or surrounding normal skin. Neural networks were able to classify measurements in a test set with 100% accuracy for the first preprocessing technique and 85% accuracy for the second. These results indicate electrical impedance may be a promising clinical diagnostic tool for basal cell carcinoma or other forms of skin cancer.     

Neural Models for the Resonant Frequency of Electrically Thin and Thick Circular Microstrip Antennas and the Characteristic Parameters of Asymmetric Coplanar Waveguides Backed with a Conductor

Neural models for computing the resonant frequency of electrically thin and thick circular microstrip antennas, based on the multilayered perceptrons and the radial basis function networks, are presented. Five learning algorithms, delta-bar-delta, extended delta-bar-delta, quick-propagation, directed random search and genetic algorithms, are used to train the multilayered perceptrons. The radial basis function network is trained according to its learning strategy. The resonant frequency results of neural models are in very good agreement with the experimental results available in the literature. In this paper, the characteristic impedance and the effective permittivity of the asymmetric coplanar waveguide backed with a conductor are also computed by using only one neural model trained by the backpropagation with momentum and the extended delta-bar-delta algorithms. When the performances of neural models are compared with each other, the best results for test are obtained from the multilayered perceptrons trained by the extended delta-bar-delta algorithm.     

基于神经网络的微波电路建模与优化

本文讨论用神经网络对微波电路进行建模、优化。借助电磁声理论计算或基于实际测量,可得到微波电路的输入、输出样本数据,从而可训练神经网络,在兼顾它的推广性能的基础上,对微波电路建模。进一步,通过优化神经网络对应参数,可优化微波电路。文章用ＲＢＦ（Ｒａｄｉａｌ Ｂａｓｉｓ Ｆｕｎｃｔｉｏｎ）神经网络对微带变阻器建模、优化,以此为例,进行了较为详细的阐述。     

DIPNET: A General Distributed Parameter Network Analysis Program

The DIPNETcomputer program makes practical the simple and rapid solution of elaborate microwave networks on a time-sharing computer. Given a file of input data describing a DIstributed Parameter NET-work of electrical sections, the program finds the complex voltage and current phasors along the network over a prescribed range of frequencies. Sections may consist of a variety of transmission lines, lumped constants, sources, and active devices. Network configurations may include chains, side stubs, and two-path sections. The network size is practically unlimited, and may easily comprise hundreds of sections. Output data at selected points along the network may include phasors, their absolute magnitude and phase shift, and power flow. Normalization to designated phasors is provided for by the program. The output data may also include input resistance, reactance, impedance, and the admittance counterparts. Repeated sequences may be handled automatically. Network parameters may also be modified automatically, both those which depend on frequency and frequency-independent parameters.     

带有直流偏置的毫米波单刀双掷开关仿真与设计

采用阶跃阻抗传输线和扇形微带短截线,实现了单刀双掷开关的直流偏置,使直流支路与毫米波支路之间的隔离度大于30dB,带宽超过25%,在中心频率30GHz附近回波损耗大于40dB。采用这种直流偏置电路和PIN梁式引线二极管,基于LTCC工艺对单刀双掷开关串联结构进行仿真。设计结果表明在28.5～31.5GHz频率范围内,串联开关的插入损耗小于1.5dB,回波损耗大于15dB,隔离度大于20dB。     

Design of Novel Ultra-Wideband Bandpass Filter with High Selectivity and Wide Stop Band and Optimizing it with Neuro-Genetic Method

This paper develops a novel ultra-wideband bandpass filter with high selectivity, deep stop band and compact size. By linking a broadband bandstop filter at two sides with two feed lines via interdigital coupled lines with enhanced coupling degree, an initial ultra-wideband bandpass filter is created. In this filter, all undesired pass bands are rejected by broadband bandstop filter embedded in middle of ultra-wideband filter. Then, stepped impedance open stubs are used for realizing transmission zeros in pass band edges to increase selectivity. Finally, a neuro-genetic method is applied for optimizing of proposed ultra-wideband bandpass filter. For this task, first a nonlinear relation is established between the input (layout parameters) and output (electrical responses) data by using neural network. Then, genetic algorithm is used in conjunction with neural network model for optimizing the ultra-wideband bandpass filter parameters. The designed filter was fabricated and measured that showed good characteristics including deep stop band and very high pass band selectivity.     

Direction of arrival estimation based on phase differences usingneural fuzzy network

A new high-resolution direction of arrival (DOA) estimation technique using a neural fuzzy network based on phase difference (PD) is proposed. The conventional DOA estimation method such as MUSIC and MLE, are computationally intensive and difficult to implement in real time. To attack these problems, neural networks have become popular for DOA estimation. However, the normal neural networks such as the multilayer perceptron (MLP) and radial basis function network (RBFN) usually produce the extra problems of low convergence speed and/or large network size (i.e., the number of network parameters is large). Also, the may to decide the network structure is heuristic. To overcome these defects and take use of neural learning ability, a powerful self-constructing neural fuzzy inference network (SONFIN) is used to develop a new DOA estimation algorithm. By feeding the PDs of the received radar-array signals, the trained SONFIN can give high-resolution DOA estimation. The proposed scheme is thus called PD-SONFIN. This new algorithm avoids the need of empirically determining the network size and parameters in normal neural networks due to the powerful on-line structure and parameter learning ability of SONFIN. The PD-SONFIN can always find itself an economical network size in the fast learning process. Our simulation results show that the performance of the new algorithm is superior to the RBFN in terms of convergence accuracy, estimation accuracy, sensitivity to noise, and network size     

基于卷积神经网络的红外光谱建模分析综述

红外光谱技术存在着数据预处理复杂、预测精度不高,且难以处理大量非线性数据的问题,适于用卷积神经网络进行处理.本文首先分析了卷积神经网络应用在红外光谱上的优点,并对卷积神经网络结构组成进行简单的概述.然后针对卷积神经网络在光谱分析建模中的输入数据维度问题进行详细阐述;针对模型设计中卷积核参数的影响、多任务处理模型以及训练...     

基于递阶粒子群优化径向基函数人工神经网络的光性能监控

为解决差错反向传输神经网络在透明可重构光网络光性能监测中精度不足的问题,提出一种基于优化的径向基函数人工神经网络的光性能监测方案。在该方案中,以信号眼图参数为网络输入,以光信噪比、色散和偏振模色散为网络输出;采用二进制与十进制相结合编码的递阶粒子群方法,用适应度函数引导粒子向小规模和小误差方向运动,进行神经网络的结构与参数自适应优化;分别以不同光信噪比,不同色散和偏振模色散水平仿真信道中传输速率为40 Gb/s差分相移键控仿真信号,进行网络训练和测试,并将测试结果与相同情形下基于差错反向传输法神经网络的光性能监测结果进行比较。结果表明,所提方案在保有人工神经网络方案优点的基础上,有着更好的监测精度。     

A General Neural Network Model for Estimating Telecommunications Network Reliability

This paper puts forth a new encoding method for using neural network models to estimate the reliability of telecommunications networks with identical link reliabilities. Neural estimation is computationally speedy, and can be used during network design optimization by an iterative algorithm such as tabu search, or simulated annealing. Two significant drawbacks of previous approaches to using neural networks to model system reliability are the long vector length of the inputs required to represent the network link architecture, and the specificity of the neural network model to a certain system size. Our encoding method overcomes both of these drawbacks with a compact, general set of inputs that adequately describe the likely network reliability. We computationally demonstrate both the precision of the neural network estimate of reliability, and the ability of the neural network model to generalize to a variety of network sizes, including application to three actual large scale communications networks.      

Direction finding in phased arrays with a neural network beamformer

Adaptive neural network processing of phased-array antenna received signals promises to decrease antenna manufacturing and maintenance costs while increasing mission uptime and performance between repair actions. We introduce one such neural network which performs aspects of digital beamforming with imperfectly manufactured, degraded, or failed antenna components. This paper presents measured results achieved with an adaptive radial basis function (ARBF) artificial neural network architecture which learned the single source direction finding (DF) function of an eight-element X-band array having multiple, unknown failures and degradations. We compare the single source DF performance of this ARBF neural network, whose internal weights are computed using a modified gradient descent algorithm, with another radial basis function network, Linnet, whose weights are calculated using linear algebra. Both networks are compared to a traditional DF approach using monopulse     

STABILITY CONTROL AND ANALYSIS OF ASYMMETRIC CONTINUOUS NEURAL NETWORKS

A new method for analyzing dynamics of continuous neural networks is proposed,and the necessary convergence conditions for a class of associative networks are obtained. Basedon the stability criterion and the equations of equilibrium set of the network, synthesis of aclass of associative neural networks is given. The stability control model of asymmetric unstablenetworks is suggested, which is also a valid way for optimization and dynamic control of stableneural networks.     

Subgradient-Based Neural Networks for Nonsmooth Convex Optimization Problems

This paper develops a neural network for solving the general nonsmooth convex optimization problems. The proposed neural network is modeled by a differential inclusion. Compared with the existing neural networks for solving nonsmooth convex optimization problems, this neural network has a wider domain for implementation. Under a suitable assumption on the constraint set, it is proved that for a given nonsmooth convex optimization problem and sufficiently large penalty parameters, any trajectory of the neural network can reach the feasible region in finite time and stays there thereafter. Moreover, we can prove that the trajectory of the neural network constructed by a differential inclusion and with arbitrarily given initial value, converges to the set consisting of the equilibrium points of the neural network, whose elements are all the optimal solutions of the primal constrained optimization problem. In particular, we give the condition that the equilibrium point set of the neural network coincides with the optimal solution set of the primal constrained optimization problem and the condition ensuring convergence to the optimal solution set in finite time. Furthermore, illustrative examples show the correctness of the results in this paper, and the good performance of the proposed neural network.      

钛合金薄板激光焊接参数的多目标优化

激光焊接过程产生的焊斑熔深和热影响区宽度直接影响焊接质量。激光焊接过程复杂,影响因素众多,许多参数难以量化。本文以TC4钛合金薄板为实验样品进行脉冲激光焊接实验。利用两个径向基函数神经网络分别预测焊斑熔深和热影响区宽度。将上述两个径向基函数神经网络作为多目标优化算法的目标函数,以提高焊接熔深并减小热影响区宽度。通过模拟退火算法寻求多目标优化所得的非劣解集中的最优解。实验证明,该方法可有效平衡激光焊接过程的焊斑熔深和热影响区宽度。     

Introduction to the modified probabilistic neural network forgeneral signal processing applications

This paper introduces a practical and easy-to-understand network for signal processing called the modified probabilistic neural network (MPNN). It begins with a short introduction to the application of artificial neural networks to signal processing followed by a background and review of the MPNN theory. The MPNN is a regression technique similar to Specht's (1991) general regression neural network, which is based on a single radial basis function kernel whose bandwidth is related to the noise statistics. It has advantages in application to time and spatial series signal processing problems because it is constructed directly and simply from the training signal waveform characteristics or features. An illustrative example involving noisy Doppler-shifted swept frequency sonar signal detection compares the effectiveness of the first- and second-order Volterra, multilayer perceptron neural network, radial basis function neural network, general regression neural network and MPNN filters, demonstrating some features of the MPNN for practical design     

Analog VLSI neural networks: implementation issues and examples inoptimization and supervised learning

Time-critical neural network applications that require fully parallel hardware implementations for maximal throughput are considered. The rich array of technologies that are being pursued is surveyed, and the analog CMOS VLSI medium approach is focused on. This medium is messy in that limited dynamic range, offset voltages, and noise sources all reduce precision. The authors examine how neural networks can be directly implemented in analog VLSI, giving examples of approaches that have been pursued to date. Two important application areas are highlighted: optimization, because neural hardware may offer a speed advantage of orders of magnitude over other methods; and supervised learning, because of the widespread use and generality of gradient-descent learning algorithms as applied to feedforward networks     

一种基于小波变换和FIR神经网络的广域网网络流量预测模型

该文提出了一种基于小波变换和FIR神经网络的广域网网络流量预测模型,首先采用小波分解把网络流量数据分解成小波系数和尺度系数,即高频系数和低频系数,将这些不同频率成分的系数单支重构为高频流量分量和低频流量分量,利用FIR神经网络对这些分量分别进行预测,将合成之后的结果作为原始网络流量的预测。实验结果表明:采用该模型对实际的广域网网络流量数据进行预测,不仅可以得到较快的收敛效果,而且预测性能比现有的小波神经网络和FIR神经网络要好得多。