可重构功放的新颖NARX神经网络逆向建模研究

针对使用CAD软件设计射频微波电路繁琐且耗时长等缺点,提出一种新颖的带外部输入的非线性自回归(NARX)神经网络逆向建模方法。此方法采用具有激励函数的NARX 神经网络(DAFNN)为模型以提高网络的泛化能力,利用支持向量机(SVM)替代模型的前馈部分完成数据分类,解决设计中的多解问题。然后应用于可以覆盖多个频段的可重构功率放大器中,实验表明,该方法在精度方面分别优于直接逆向建模方法和自适应浊逆向建模方法99.86%和81.32%,计算速度方面优于直接逆向建模方法31.72%,可以降低射频微波可重构功率放大器的设计复杂度、缩短其设计时间。     

Double Gate MOSFET Modeling Based on Adaptive Neuro‐Fuzzy Inference System for Nanoscale Circuit Simulation

As the conventional silicon metal‐oxide‐semiconductor field‐effect transistor (MOSFET) approaches its scaling limits, quantum mechanical effects are expected to become more and more important. Accurate quantum transport simulators are required to explore the essential device physics as a design aid. However, because of the complexity of the analysis, it has been necessary to simulate the quantum mechanical model with high speed and accuracy. In this paper, the modeling of double gate MOSFET based on an adaptive neuro‐fuzzy inference system (ANFIS) is presented. The ANFIS model reduces the computational time while keeping the accuracy of physics‐based models, like non‐equilibrium Green's function formalism. Finally, we import the ANFIS model into the circuit simulator software as a subcircuit. The results show that the compact model based on ANFIS is an efficient tool for the simulation of nanoscale circuits.     

A Recurrent Fuzzy-Network-Based Inverse Modeling Method for a Temperature System Control

Temperature control by a Takagi-Sugeno-Kang (TSK)-type recurrent fuzzy network (TRFN) designed by modeling plant inverse is proposed in this paper. TRFN is a recurrent fuzzy network developed from a series of TSK-type fuzzy if--then rules, and is characterized by structure and parameter learning. In parameter learning, two types of learning algorithms, the Kalman filter and the gradient descent learning algorithms, are applied to consequent parameters depending on the learning situation. The TRFN has the following advantages when applied to temperature control problems: 1) high learning ability, which considerably reduces the controller training time; 2) no a priori knowledge of the plant order is required, which eases the design process; 3) good and robust control performance; 4) online learning ability, i.e., the TRFN can adapt itself to unpredictable plant changes. The TRFN-based direct inverse control configuration is applied to a real water bath temperature control plant, where various control conditions are experimented. The same experiments are also performed by proportional-integral (PI), fuzzy, and neural network controllers. From comparisons, the aforementioned advantages of a TRFN have been verified     

基于模糊变换的模糊系统和模糊推理建模法

首先针对双输入单输出模糊系统提出了一种模糊变换方法,指出这种模糊变换不仅与单输入和单输出模糊系统有密切的联系,而且利用这种模糊变换构造的模糊系统具有很好的泛逼近性.然后将这种模糊变换应用到模糊推理建模法中,导出了所研究的模糊系统的微分方程模型和状态空间模型,从而给出了一种新的模糊推理建模法.理论分析和仿真实验均表明:利用模糊变换构造的微分方程对所研究的模糊系统具有很好的泛逼近性.     

模糊控制在二级倒立摆系统中的应用

针对倒立摆系统的非线性、不稳定的控制问题,推导了二级倒立摆系统的数学模型和状态空间表达式,对倒立摆系统在平衡点附近进行了可控性分析,提出了一种基于模糊控制器进行控制的方法,建立了相应的控制规则。实验结果表明,该系统具有鲁棒性、稳定性好的特点。     

分布式系统模糊分类识别航迹关联算法

以模糊分类识别理论为基础,提出了一种分布式系统航迹关联算法。算法以各节点局部航迹为研究对象,确定航迹特性指标,建立航迹贴近度向量,根据最大隶属原则解决航迹关联问题。仿真表明,该算法比基于统计方法的加权航迹关联算法具有关联速度快、关联正确率高,且对密集目标环境适应性较强的优点。     

二级倒立摆的模糊控制

研究了二级倒立摆系统的模糊控制问题,提出了一种结构新颖的模糊控制律。通过对控制律的参数寻优和调整,实现了二级倒立摆的稳定控制。仿真研究表明：本文提出的模糊控制算法无论是动态指标还是稳态精度方面都有明显的优越性。     

一种用于非线性复杂系统辨识的自适应模糊神经网络

该文提出一种用于复杂的非线性未知系统辨识的混合神经网络模型自适应模糊神经网络(AFNN)。AFNN网络结构简洁,具有通用逼近的特性,能够克服由于突变点的存在而对系统辨识所带来的误差,提高整个系统的辨识精度。对空空导弹攻击区辨识的仿真结果验证了AFNN网络的有效性。     

基于MATLAB/SIMULINK直流电机调速系统模糊控制的建模与仿真

论述了一种基于MATLAB语言的直流电机模糊控制仿真系统，通过MATLAB语言中SIMULINK模块和模糊控制工具箱实现模糊控制仿真。     

双层铝互连倒梯形通孔刻蚀技术研究

针对双层布线中二铝在通孔处台阶覆盖率低的问题,通过优化光刻胶膜的厚度、硬烘温度,以及调整刻蚀气体流量、腔室压力及极板功率,开发出坡度为62.5°的倒梯形通孔;二铝在通孔处的台阶覆盖率大于90%。将该技术用于D/A转换器的研制,成品率得到明显提高。     

Identification of pneumatic artificial muscle manipulators by a MGA-based nonlinear NARX fuzzy model

This study investigates the technique of modeling and identification of a new dynamic NARX fuzzy model by means of genetic algorithms. In conventional identification techniques, there are difficulties such as poor knowledge of the process, inaccurate process or complexity of the resulting mathematical model. All these factors deteriorate the identification performance when dealing with dynamic nonlinear industrial processes. To overcome these difficulties, this paper proposes a novel approach by using a modified genetic algorithm (MGA) combined with the predictive capability of nonlinear ARX (NARX) model for generating the dynamic NARX Takagi–Sugeno (TS) fuzzy model. The MGA algorithm processes the experimental input–output training data from the real system and optimizes the NARX fuzzy model parameters. This is referred to as fuzzy identification, which automatically generates the appropriate fuzzy if-then rules to characterize the dynamic nonlinear features of the real plant. The prototype pneumatic artificial muscle (PAM) manipulator, being a typical nonlinear and time-varying system, is used as a test system for this novel approach. This result shows that, with this MGA-based modeling and identification, the novel NARX fuzzy model identification approach to the PAM manipulator achieved highly outstanding performance and high precision as well. The accuracy of the proposed MGA-based NARX fuzzy model proves excellent in comparison with the MGA-based TS fuzzy model and the conventional GA-based TS fuzzy model.     

基于NARX神经网络的组合导航系统设计

针对捷联组合导航系统在定位信号无法获取的情况下定位误差大和BP神经网络定位的波动问题提出了基于NARX神经网络的导航算法。该方法在输入端加入输出输入量的时间序列,在定位信号可以获取时间段内对神经网络进行训练,不可获取时使用NARX预测的数据对系统进行补偿,提高定位精度。实验结果表明在30s的失锁时间内NARX神经网络定位精度在3m以内,迭代次数小于15次且数据波动较小,可以准确的预测导航位置。     

Modeling and Stability Analysis for Non-linear Network Control System Based on T-S Fuzzy Model

Based on the T -S fuzzy model, this paper presents a new model of non -linear network control system with stochastic transfer delay. Sufficient criterion is proposed to guarantee globally asymptotically stability of this two - levels T - S fuzzy model. Also a T - S fuzzy observer of NCS is designed base on this two - levels T - S fuzzy model. All these results present a new approach for networked control system analysis and design.     

基于系统辨识的电路脉冲响应建模

为探索基于系统辨识的电磁脉冲效应仿真新方法,设计了以阶跃信号和方波脉冲信号为激励源、稳压电源系统为对象的脉冲注入实验,分别采用OE模型和NARX神经网络模型对该系统的脉冲能量耦合传递函数进行建模.结果表明,所建模型均能较好地预测出响应波形,且NARX模型预测能力强于OE模型,两者对阶跃、方波脉冲的预测精度分别达到93....     

Hybrid Control of a Mechatronic System: Fuzzy Logic and Grey System Modeling Approach

This paper presents a method of fuzzy control combined with grey system modeling approach of a mechatronic system to be used in driving a four-bar mechanism by a dc motor through a buck converter. The main contribution of this paper is that it predicts the future error values in terms of the previous error values using a grey estimator and determines the control action for the following step that depends on the predicted error value before it occurs. Despite the basic assumption that the angular velocity of the crank is constant in most of the mechanism analysis, this may not be valid when the mechanism is connected to an electric motor. In this paper, a complete state-space mathematical model of each part of the converter-motor-mechanism system is first developed and numerically simulated to demonstrate the crank angular speed fluctuations for the case of a constant voltage supply. Then, a fuzzy logic controller combined with grey system modeling approach is designed to regulate the crank angular speed of the mechanism and compared with a fuzzy controller used alone. Finally, results are obtained for each part of the system separately, then related parts are connected as cascade, and complete system control is tested for the proposed control approach. The connection between dc motor and four-bar mechanism has been considered as a dynamic load for the converter. Comparatively better results are obtained when the fuzzy controller is used together with grey system modeling approach. The results obtained from the proposed controller are not only superior in the rise time, speed fluctuations, and percent overshoot, but also much better in the controller output signal structure.     

敌我识别系统建模研究

无论在作战仿真还是模拟训练中,敌我识别系统都是大系统的重要组成部分.对敌我识别系统的模拟目前仅停留在根据应答机平台的红蓝方属性直接给出识别结果,而对多个应答机处于询问范围内一问多答、询问对象超出询问距离等特殊情况都没有考虑.针对敌我识别系统建模现有模型过于简单的问题,在敌我识别系统模型中增加了询问信号传播模型和应答信号传播模型,考虑了询问信号和应答信号在空间传播的真实过程,真实反映了敌我识别系统询问、应答、识别的整个工作过程.利用建立的模型,能够对一问多答、询问超出距离、应答超出距离等特殊情况进行反映,在作战仿真系统或模拟训练系统中逼真地复现敌我识别系统的工作过程.     

自动确定聚类个数的模糊聚类算法

本文通过集成多次FCM(Fuzzy C-Means)聚类结果以及采用软化分方式,提出一种新的自动确定聚类个数的模糊聚类算法.本算法首先利用不同的聚类数目对数据进行FCM聚类,然后充分利用多次FCM聚类得到的隶属度信息构建一个累积邻接矩阵,最后采用迭代方式对累积邻接矩阵进行图切分以获取最终聚类结果.大量的仿真实验表明,相对现有集成聚类方法,本文方法能够有效减少FCM的聚类次数,并且在图切分过程中的迭代次数为现有方法的1/2左右.     

双波长稳频CO_2激光模糊控制系统的建模与优化

报导一种模糊逻辑控制系统的建模与优化方法。以此方法设计的模糊逻辑控制器，用于双波长稳频ＣＯ２激光器的控制得到令人满意的结果。     

基于区间二型T S模糊系统的压电迟滞特性建模

为了辨识压电驱动器中固有的迟滞特性,提出了一种基于区间二型Takagi Sugeno(T S)模糊系统的建模方案。首先,引用垂直距离公式替换传统的误差计算公式,使聚类算法与所辨识的超平面结果直接相关联,并提出了改进的区间二型模糊C回归模型(FCRM)聚类算法用于模糊空间的划分,提高了区间划分精度。其次,针对超球型高斯隶属度函数与超平面型聚类算法结构不匹配的问题,引入了与超平面相匹配的超平面隶属度函数完成模糊前件参数的辨识,并利用最小二乘法完成模糊后件参数的辨识。最后,利用上述方案完成了压电驱动器迟滞特性的建模。实验结果证明该方案是有效的。     

基于组合SVR的非平稳时间序列的模糊建模方法

本文介绍一种对非平稳时间序列建模的新方法.参考Janos Abonyi提出的应用于时间序列的模糊分块算法,将该算法与改进的支持向量回归模型结合起来.首先,提出一种改进的支持向量回归的表达形式;然后,通过启发式的加权方法将模糊分块的信息与SVR结合起来;最后,提出一种基于组合SVR的建模方法.实验结果表明,本文提出的方法对于非平稳时间序列的建模具有较高的实用价值.