基于GRNN网络模型的土壤重金属空间分布的研究

以江苏省南通市为研究区,利用采样点实测数据,借助GRNN神经网络模型并结合3S技术对农田土壤重金属的空间动态分布进行了深入研究。结果表明,GRNN神经网络模型能够智能地学习各个采样点的空间位置与该点各重金属含量之间的映射关系,并能够稳健地对各个空间插值点处的土壤重金属含量进行预测;结果显示南通市农田土壤重金属污染总体较轻,但也存在局部地区的严重污染。在运用GRNN神经网络模型进行空间插值了解重金属空间动态分布的基础上,可以根据污染的状况确定农产品的生产布局和规划。     

Marcia K. Johnson: 2006 Award for Distinguished Scientific Contributions.

Presents the citation to Marcia K. Johnson, who received the Award for Distinguished Scientific Contributions "for raising and illuminating fundamental questions about the cognitive and neural processes that constitute the subjective experience of mental life." A brief profile and a selected bibliography, as well as Johnson's award address, entitled Memory and Reality (see record 2006-21079-028), accompany the citation. (PsycINFO Database Record (c) 2010 APA, all rights reserved)     

Application of stochastic filtering for lifetime prediction

This paper introduces a stochastic filtering modeling approach for predicting the remaining lifetime of a component based on information on the stochastic degradation process and uncertain condition monitoring measurements. The model is illustrated by a case study, where the degradation is assumed to be a simplified fatigue crack growth process. The model accounts for uncertainties in both degradation process and condition measurements in a sound way. If completed with information on costs of monitoring, failure and replacement, such model could be used in optimizing both the condition monitoring intervals and, e.g. the replacement time for the component.     

正则模糊神经网络对一类连续模糊值函数的普遍近似性

本文讨论了正则模糊神经网络于对定义于区间［０，Ｔ０］上连续可减模糊值函数的普遍近似性，在此基础上，证明了［０，Ｔ０］上取值为三角形模糊连续递增函数可用正则模糊神经网络逼近到任意精度。     

人工神经网络A／D变换器

本文对［５］的４位人工神经网络Ａ／Ｄ变换器进行了研究．指出按其方法推广实现多位Ａ／Ｄ时存在突触电阻大小以至无法实现且抗干扰能力也不好的问题并给出了解决办法．同时对如何改善神经元转移特性的硬限幅曲线作了简单讨论．     

Nonlinear black-box modeling in system identification: a unified overview

A nonlinear black-box structure for a dynamical system is a model structure that is prepared to describe virtually any nonlinear dynamics. There has been considerable recent interest in this area, with structures based on neural networks, radial basis networks, wavelet networks and hinging hyperplanes, as well as wavelet-transform-based methods and models based on fuzzy sets and fuzzy rules. This paper describes all these approaches in a common framework, from a user's perspective. It focuses on what are the common features in the different approaches, the choices that have to be made and what considerations are relevant for a successful system-identification application of these techniques. It is pointed out that the nonlinear structures can be seen as a concatenation of a mapping form observed data to a regression vector and a nonlinear mapping from the regressor space to the output space. These mappings are discussed separately. The latter mapping is usually formed as a basis function expansion. The basis functions are typically formed from one simple scalar function, which is modified in terms of scale and location. The expansion from the scalar argument to the regressor space is achieved by a radial- or a ridge-type approach. Basic techniques for estimating the parameters in the structures are criterion minimization, as well as two-step procedures, where first the relevant basis functions are determined, using data, and then a linear least-squares step to determine the coordinates of the function approximation. A particular problem is to deal with the large number of potentially necessary parameters. This is handled by making the number of ‘used’ parameters considerably less than the number of ‘offered’ parameters, by regularization, shrinking, pruning or regressor selection.     

Modelling of induced aeration in turbine aerators by use of radial basis function neural networks

Gas induction in agitated vessels with turbine impellers can be modelled accurately by means of radial basis function neural nets. The results obtained with the radial basis neural net were significantly better than those obtained by multivariate regression models or standard back propagation neural nets. Moreover, by using the radial basis function neural net model, it was possible to conduct a sensitivity analysis of the variables affecting aeration. Increased medium density showed a strong adverse effect, while variation of the viscosity can cause an increase or a decrease in the rate of aeration, depending on the prevailing process conditions.     

神经网络在电路诊断中的应用

目的：阐述了目前电路基于数据库技术和人工智能专家系统及神经网络原理的故障诊断系统。方法：将所记录的模糊症状输入到系统中，通过模糊运算后，运用神经网络学习算法来寻找故障类型。结果：介绍了人工神经网络技术在电路诊断中的应用，并给出系统故障诊断软件的设计，结论：所用专家系统和神经网络相结合的方法改进电子电路故障诊断是可行的。     

人工神经网络在激光加工温度场模拟中的应用

研究了人工神经网络在激光加工温度场模拟用的参数推算中的应用方法；并设计了相应的BP神经网络模型及软件；研究表明BP神经网络适用于对激光加工模拟的参数推算，其准确性优于回归分析法和函数插值法。