查询词典 neural network

The neural network model based on Lagrange multiplier is used to solve the elasto-plastic mechanic finite element problems.

计算结果表明了该神经网络求解弹塑性力学有限元问题的可行性。

Heavy oil distillation column ; chaotic neural network ; Laguerre function ; predictive control ; adaptive control

重油分馏塔；混沌神经网络； Laguerre函数；预测控制；自适应控制

In the subjects given, learners operate an integrated simulator landing stage of flight data to meet the aircraft and instructors to give students hands-on consolidated results. And then for the visual route trilateral, quadrilateral, and five edge-to-landing phases, with 37 operators' experiments through interviews with senior instructors, the instructors selected seven simulator modules to assess and define the effectiveness of the actual operation of the parameters. Through the way of neural network learning , the establishment of the definition of parameters of simulator training with the students finished the cause and effect comprehensive results relationship, so this research create a set of objective assessment of the effectiveness of flight training simulation platform.

在给定同样操作课目之下，以学员操作落地阶段之模拟机综合飞行数据，配合学员实际操作飞机教官给予之综合成绩，再针对目视航线三边、四边及五边到著陆阶段，以37位操作者为实验，各选取七个模拟机数据，透过资深教官访谈，定义教官评量学员实际操作成效之参数，透过类神经网路的学习，建立模拟机定义参数与学员完训综合成绩的因果关系，如此即可建立一套可以客观评估飞航训练成效的研究模拟平台。

Aimed at the characteristic of multiple types of faults possibly happened in nuclear power plant, large scale of training sample, and requirement of quick and accurate diagnosing, after the analysis of large sample number generated by large fault type exceeds limitation of 64K paragraph in DOS and large number of local minmum in error surface, measurements of same format of data file, Win95/NT operating system platform, resetting weight learning rate, dynamic training set in quick learning algorithm and improvement on quick learning algorithm using homotopy method which can avoid local minmum points in error surface have been adopted to ensure quickly and effective process of the course of neural network's training and testing.

针对核动力装置可能发生的故障种类多，训练样本规模大，故障诊断需要快速准确的特点等，分析了样本多和故障种类多产生的训练样本量超出DOS段大小和网络误差曲面上局部极小值多的情况，采取了使用相同格式数据文件、Win95/NT操作系统平台，对快速学习算法采用重置神经网络权值学习率和动态训练集、并采用能够有效克服网络误差曲面上局部极小点的同伦方法对学习算法进行改进等措施保证神经网络训练测试过程的快速、有效地进行；针对装置发生的故障须快速、准确诊断的需要，分析了故障的产生对装置参数变化的影响及操纵员对故障诊断的基础，在核动力装置发生故障时参数曲线的变化量与正常运行时参数曲线的变化量存在明显差异的基础上，提出采用参数曲线的变化量作为神经网络的输入，并围绕参数变化量的方法采用二次曲线拟合滤波求变化量和阈值技术来保证神经网络得到精确的装置参数变化量，从而得到准确的诊断结果。

The substitution model of RBF neural network was made respectively by 3 different test functions. The error analyses indicate that the fractional steps experiment design method is very practical for the substitution model needed large scale test sample points.

对3个测试函数建立RBF神经网络替代模型，其误差分析表明，分步试验设计方法对于需要大规模试验样本点的替代模型是非常实用的。

By TM images the linear structures, water system, the outer edge of Tianchi Volcano trachite are extracted. By the sensitivity of SAR images to geomorphology, the distribution of parasitical volcano cone and lava fornix around Tianchi volcano are interpreted. With the aerial photos the parasitical lava of Qixiangzhan, Baiyun and Bingchang stage are filtered. At the same time by orthogonal cross-course wavelet transform, texture analysis is carried on to ERS-2 SAR images, and the texture characters are filtered. On the basis of the spectrum character of multi-band of TM images, multi-band algebraic grouping is made, and the factor of texture character factor and band grouping of TM images are input to BP neural network classification model. The good classified results are received.

利用TM图像对线性构造、水系、天池火山粗面岩锥体外边缘的提取；利用SAR图像对地形敏感特性，提取了天池火山周围寄生火山锥体及熔岩穹丘的分布；利用航片对天池火山口周围的气象站期、白云期、冰场期等寄生喷发物进行了提取：同时利用正交小波变换对ERS-2 SAR图像进行了纹理分析，提取了纹理特征：根据TM图像不同波段的光谱特征，进行了波段代数组合，并把纹理特征参数与TM图像的波段组合及DEM一起输入BP神经元网络分类器，取得了较好的分类效果。

And point out that laxation type and densification type of wavelet-neural network will play an important role in non-destructive testing of wood material.

并提出小波、人工神经网络以及松散型和紧致型小波神经网络将在木质材料的无损检测中起重要的作用。

Flatness ; pattern recognition ; Legendre orthodoxy polynomial ; genetic algorithm ; neural network ; LSM

板形；模式识别；勒让德多项式；遗传算法；神经网络；最小二乘法1

By using the air temperature measured by thermocouples and the glass temperature measured by infrared thermometer as the training sample, a model for prediction of the temperature parameters for the float glass in lehr was created based on the ameliorated BP neural network.

摘要利用热电偶测得的退火窑中空气温度和红外测温仪测得的玻璃表面温度作为训练样本，建立了基于BP神经网络的玻璃温度预测模型。

In order to control the flow separation by reducing the diffusion factor and enlarging the diameter of inner circle, the meridian plane profile of the return channel was redesigned, which is achieved by substituting arbitrary curve for the circle with no change of the axial length of the stage. Bezier curve with eight parameters was chose to describe the shape of meridian plane profile, and the optimization of the meridian plane profile was implemented combining back-propagation neural network with genetic algorithm.

改进的主要思路是减小弯道前半部分通道的扩压度，并同时加大弯道出口内侧的转弯半径，主要做法是在不增加整级轴向尺寸的前提下，用任意曲线取代传统弯道的同心圆环结构，给定弯道回流器子午型线的外侧型线，采用Bezier曲线对内侧型线的2段曲线进行参数化描述，利用遗传算法和反向传播(back-propagation，BP)神经网络相结合的方法对内侧型线进行优化，得到新的弯道回流器子午型线。

The split between the two groups can hardly be papered over.

这两个团体间的分歧难以掩饰。

This approach not only encourages a greater number of responses, but minimizes the likelihood of stale groupthink.

这种做法不仅鼓励了更多的反应，而且减少跟风的可能性。