基于线性曲率校正技术的低电压带隙基准源设计

采用电流求和取代传统电压求和的方法设计了一款低基准电压输出的带隙基准电压源电路,同时提出一种线性化P-N结正向导通电压（VBE）的温度曲率校正技术,保证了基准电压的低温漂和高精度。整个电路采用TSMC0.6μmBCD工艺设计实现,芯片面积为0.2mm2。在Cadence环境下使用Spectre对电路进行了模拟仿真,仿真结果表明：该基准电路可在低至1.1V的电源电压下正常工作;在-20℃～120℃温度范围内,温度系数为9.1×10-6/℃,PSRR为-78dB。在典型的1.5V电源电压下,基准输出电压可调节范围为0.165～1.25V。     

一种基于前馈补偿技术的高性能CMOS运算放大器

基于传统CMOS折叠共源共栅运算放大器的分析和总结,应用前馈补偿技术,实现了一种高性能CMOS折叠共源共栅运算放大器,不仅保证了高开环增益,而且还大大减小了运放的输入失调电压。设计采用TSMC 0.35μm混合信号CMOS工艺实现,采用Hspice进行仿真,仿真结果表明运放的直流开环增益为95 dB,输入失调电压为0.023 mV,负载电容为2pF时的相位裕度为45.5°。     

一种基于逐维扩展的前向网络训练方法

前向网络的快速训练问题是前向网络研究的一个非常重要的课题。本文针对一类n-维超立方体的分类问题（当为二分类问题时，这实际上是一个n-维Boole函数的神经网络实现问题），提出了一种基于逐维扩展的前向网络快速训练方法，将一个n个输入的大网络的各权训练问题转化为小网络逐维递归的扩展部分的参数训练问题，提高了网络训练的速度，实验结果表明了这种训练方法的有效性和可行性。     

Evaluation of fully fuzzy matrix equations by fuzzy neural network

In this paper, a new hybrid method based on fuzzy neural network for approximate solution of fully fuzzy matrix equations of the form AX=D$\mathit{AX}=D$, where A and D are two fuzzy number matrices and the unknown matrix X is a fuzzy number matrix, is presented. Then, we propose some definitions which are fuzzy zero number, fuzzy one number and fuzzy identity matrix. Based on these definitions, direct computation of fuzzy inverse matrix is done using fuzzy matrix equations and fuzzy neural network. It is noted that the uniqueness of the calculated fuzzy inverse matrix is not guaranteed. Here a neural network is considered as a part of a large field called neural computing or soft computing. Moreover, in order to find the approximate solution of fuzzy matrix equations that supposedly has a unique fuzzy solution, a simple algorithm from the cost function of the fuzzy neural network is proposed. To illustrate the easy application of the proposed method, numerical examples are given and the obtained results are discussed.     

基于神经网络的GaAs微波及高速集成电路CAD技术

介绍了基于神经网络的 Ga As微波与高速电路 CAD方面的研究与开发工作 ,其中包括用神经网络进行器件与电路建模的原理与方法及这一模型在优化与统计分析中的应用。     

Nonlinear identification and optimal feedforward friction compensation for a motion platform

In this study, we present a method of nonlinear identification and optimal feedforward friction compensation for an industrial single degree of freedom motion platform. The platform has precise reference tracking requirements while suffering from nonlinear dynamic effects, such as friction and backlash in the driveline. To eliminate nonlinear dynamic effects and achieve precise reference tracking, we first identified the nonlinear dynamics of the platform using Higher Order Sinusoidal Input Describing Function (HOSIDF) based system identification. Next, we present optimal feedforward compensation design to improve reference tracking performance. We modeled the friction using the Stribeck model and identified its parameters through a procedure including a special reference signal and the Nelder–Mead algorithm. Our results show that the RMS trajectory tracking error decreased from 0.0431 deg/s to 0.0117 deg/s when the proposed nonlinear identification and friction compensation method is utilized.     

静态前馈型网络的监督学习方法研究进展

本文从四个方面综述近年来用于前馈型网络的监督学习方法,即:1.对经典反向传播法的改进和变型;2.用于训练多层感知器的其它学习方法;3.其它前馈型网络模型和监督学习模型;4.具有复杂结构的各种模型.     

The use of preview wind measurements for blade pitch control

Light detection and ranging systems are able to measure conditions at a distance in front of wind turbines and are therefore suited to providing preview information of wind disturbances before they impact the turbine blades. In this study, preview-based disturbance feedforward control is investigated for load mitigation. Performance is evaluated assuming highly idealized wind measurements that rotate with the blades and compared to performance using more realistic stationary measurements. The results obtained using idealized, “best case” measurements show that excellent performance gains are possible with reasonable pitch rates. However, the results using more realistic wind measurements show that without further optimization of the controller and/or better processing of measurements, errors in determining the shear local to each blade can remove any advantage obtained by using preview-based feedforward techniques.     

Extended and Unscented Kalman filtering based feedforward neural networks for time series prediction

With the ability to deal with high non-linearity, artificial neural networks (ANNs) and support vector machines (SVMs) have been widely studied and successfully applied to time series prediction. However, good fitting results of ANNs and SVMs to nonlinear models do not guarantee an equally good prediction performance. One main reason is that their dynamics and properties are changing with time, and another key problem is the inherent noise of the fitting data. Nonlinear filtering methods have some advantages such as handling additive noises and following the movement of a system when the underlying model is evolving through time. The present paper investigates time series prediction algorithms by using a combination of nonlinear filtering approaches and the feedforward neural network (FNN). The nonlinear filtering model is established by using the FNN’s weights to present state equation and the FNN’s output to present the observation equation, and the input vector to the FNN is composed of the predicted signal with given length, then the extended Kalman filtering (EKF) and Unscented Kalman filtering (UKF) are used to online train the FNN. Time series prediction results are presented by the predicted observation value of nonlinear filtering approaches. To evaluate the proposed methods, the developed techniques are applied to the predictions of one simulated Mackey-Glass chaotic time series and one real monthly mean water levels time series. Generally, the prediction accuracy of the UKF-based FNN is better than the EKF-based FNN when the model is highly nonlinear. However, comparing from prediction accuracy and computational effort based on the prediction model proposed in our study, we draw the conclusion that the EKF-based FNN is superior to the UKF-based FNN for the theoretical Mackey-Glass time series prediction and the real monthly mean water levels time series prediction.