轮胎在侧向力、纵向力联合工况下的神经网络模型

建立了轮胎在侧向力、纵向力联合工况下的神经网络模型，分析了不同训练方法对模型精度的影响。通过对轮胎实测值与神经网络预测值的对比表明，轮胎神经网络模型的精度能满足工程要求，BP前馈神经网络可有效地应用于车辆轮胎特性的数学建模。     

人工神经网络在模具型腔加工走刀方式选择中的应用

建立基于人工神经网络的模具型腔粗加工走刀方式的选择模型,设计了学习样本.采用3层反向传播BP网络模拟模具型腔几何参数与数控加工走刀方式的非线性关系,应用训练好的BP网络为模具型腔选择合理的走刀方式.切削加工表明,应用人工神经网络选择走刀方式可以提高模具型腔的加工效率.     

油气田区承压含水层地下水污染机理及其脆弱性评价

根据研究区地质构造及水文地质概况,分析了研究区承压含水层地下水有机污染的机理,建立了针对该地区承压含水层地下水污染脆弱性评价指标体系,并应用神经网络技术作为评价体系中参数的赋权方法;由ANN与GIS耦合技术得到的研究区承压含水层地下水污染脆弱性区划图比较好地符合研究区的实际情况。     

基于神经网络模型的某大坝混凝土弹性模量时变规律反演分析

基于人工神经网络的非线性映射特性，在三维有限元计算的基础上，结合大坝原型观测资料，提出了大坝参数时变规律的反演方法。以某混凝土重力坝的原型观测资料为例，利用该方法反演得出了该坝坝体混凝土弹性模量的变化规律。结果表明该方法是切实可行的，可应用于分析评价大坝材料参数的变化。     

均匀沙床面动床阻力计算的人工神经网络模型

针对泥沙运动数据含有噪音且样本数据较多的特点,提出采用人工神经网络(ANN)BP模型批学习的训练方法可有效地缩短计算时间、提高训练精度。建立了由能坡、无因次单宽流量和无因次泥沙粒径等3个参数预测水深的结构为3-33-1的冲积河槽动床阻力BP模型。预测结果与实测资料比较表明这个人工神经网络模型的预测精度较高,同时这个模型与21个动床阻力公式的比较表明人工神经网络模型要比传统的回归模型精度高。     

BP神经网络在城市水环境承载力预测中的应用

将人工神经网络引入到水环境承载力预测的研究应用中,选取11项指标为模型输入项,把综合污染指数作为输出项,构建了BP神经网络评价模型,利用构建的模型预测评价丽水市内河水环境承载力状况,给出了该区在不同方案下的水环境承载力情况,并对预测结果进行了分析。采用的BP神经网络评价模型具有结构简单、建模方便等特点,通过训练能快速准确获得样本信息,评价结果能直观地反映评价地区的水环境承载状态。     

Optimal location of three heat sources on the wall of a square cavity using genetic algorithms integrated with artificial neural networks

In this work, optimization of location of heat sources in a square enclosure with natural convection is performed to maximize the global conductance in the enclosure. For this study we have taken a square enclosure with three adiabatic walls, one isothermal wall opposing the wall having three heat sources. Numerical simulations are done by changing positions of heat sources for different Rayleigh numbers using Fluent 6.3(2d, double precision). And for some configurations maximum temperature inside the enclosure is noted. Optimization is done using genetic algorithms (GA) combined with artificial neural networks (ANN). An ANN is trained using the above data obtained from numerical solutions. The trained ANN will be the simulation tool, whenever required by the GA for optimization. It is shown that at high Rayleigh number the spacing between the heat sources should be zero for optimum heat transfer. Variation in optimum solution for unequal heat fluxes are also studied.     

基于Web的智能CAPP系统的研究

从CAPP系统结构研究出发，利用特征技术，建立便于知识处理和规则学习的模糊神经网络工艺知识表达与生成模型，实现了CAPP系统结构的可迭加性和方法与数据的分离。应用特征技术表示产品的几何信息和工艺信息，实现了零件特征级工艺知识和工艺规程的组合与重用。在此基础上，采用异地分布式结构，便于网络模式下CAPP功能的实现，使CAPP能满足网络环境下快捷有效的信息传输和资源利用，是基于Web的CAPP系统有利于智能化与通用化实现的结构模式。给出了应用实例。     

Evaluation of suspended load transport rate using transport formulas and artificial neural network models （Case study： Chelchay Catchment）＊

Accurate estimation of sediment load or transport rate is very important to a wide range of water resources projects. This study was undertaken to determine the most appropriate model to predict suspended load in the Chelchay Watershed, northeast of Iran. In total, 59 data series were collected from four gravel bed-rivers and a sand bed river and two depth integrating suspended load samplers to evaluate nine suspended load formulas and feed forward backpropagation Artificial Neural Network (ANN) structures. Although the Chang formula with higher correlation coefficient (r = 0.69) and lower Root Mean Square Error (RMSE = 0.013) is the best suspended load predictor among the nine studied formulas, the ANN models significantly outperform traditional suspended load formulas and show their superior performance for all statistical parameters. Among different ANN structures two models including 4 inputs, 4 hidden and one output neurons, and 4 inputs, 4 and one hidden and one output neurons provide the best simulation with the RMSE values of 0.0009 and 0.001, respectively.