查询词典 neural network

The complex function between isochromatic fringe orders and RGB gray values of the image pixels is described by BP artificial neural network.

其特点是通过BP神经网络建立图像中像素点的R、G、B颜色值与条纹级数N之间的非线性关系；可以准确地得到3级以内等色线条纹级数。

Because color isochromatic fringes appear in the stress model based on a plane polariscope in white light, we studied the problems systematically by a digital camera as image inputting device, digital image processing technique and BP artificial neural network.

根据白光入射时应力模型在偏振仪光学系统中的等色线条纹是彩色的特点，本论文采用彩色数码相机作为数据采集与输入设备，结合彩色信息图像处理和BP神经网络等新技术，对上述两个难题进行了系统的研究，获得以下成果

On the basis of color imaging system, an automated photoelasticity in white light for determining isochromatics and isoclinics is presented It includes two techniques One is automation of the ordering of color isochromatics based on BP neural network The other is whole field digital determining of isoclinic angles by five step color phase shifting Many limitations and drawbacks, which affect the precision of measurement, were more eliminated and improved The validity of experimental results was ...

以彩色信息图象处理技术为基础，围绕光弹性实验数据自动采集这个主题，提出用BP神经网络自动确定等色线分数级条纹及其级数的颜色插值法，以及全场数字化确定等倾角的五步彩色相移法。典型实验表明，上述方法在提高光弹性数据采集自动化程度和减少各种误差因素影响等方面均有所改善；进而提高三维光弹性薄切片应力分析结果的精度，促进实验应力分析的工程应用，扩大光弹性法的应用范围。

Based on polynomial-interpolation and curve-fitting theory, this paper presents a special feed-forward neural network using Jacobi orthogonal polynomial activation-functions, which exploits a group of order-increased Jacobi orthogonal polynomial functions as the activation-function of hidden-layer neurons.

根据多项式插值与逼近理论，以一组零阀值特例 Jacobi 正交多项式（第二类 Chebyshev 正交多项式）作为隐层神经元的激励函数，构造一种基于 Jacobi 正交基的前向神经网络模型。

Recently, artificial intelligent technology, such as expert system, fuzzy control and neural network, is introduced to complex process control, which provides an effective method of the jigging automation. This article studies the strategy and realized method of jigging process automation with intelligent control theory.

首先对影响跳汰分选效果的主要因素做了深入分析，得出床层的密度分布与产品质量密切相关，其正态分布的标准离差可反映出床层中的错配物含量的结论，提出跳汰过程的自动控制应以优化分层状态为目标的控制策略。

In this paper, a neural network control system for rotary kiln based on features of combustion flame is proposed.

摘要提出了一种基于燃烧火焰图象特征的回转窑神经网络控制系统。

The character values of the wood disfigurement styles distinguishability based on connecting the wavelet multi- distinguishability with autocorrelation fractal dimention, uses four kinds disfigurements of knag 、 bark pocket 、 wormhole and molder as output of distinguishability typtles,uses L-M Calculation methods to train BP neural network.

本文以小波多分辨率下自相关分形维数作为木材缺陷类型识别的特征量，以夹皮、腐朽、节子、虫眼四种缺陷作为识别类型输出，选用L-M算法对BP神经网络进行训练。

Knap problem ; artificial neural network ; energy function ; combinatorial optimization

背包问题；神经网络；能量函数；组合优化

How to construct an excellent artificial neural network based on actual problems is a knotty problem for us.

如何根据问题建立一个好的神经网络是摆在我们面前最棘手的问题。

Characteristic data have been worked out, including the maximum Lyapunov index λ, fractional dimension D, lacunarity Λ and eight energies of various frequency bands. After being normalized, they can function as the characteristic vectors. Then, they are transmitted into an artificial neural network to perform pattern recognition.Starting from the mechanism of ultrasonic generating, initial ultrasonic pulses are calibrated. A stylish discharge source is directly coupled with the ultrasonic sensors, and work out actual discharge magnitude.

利用非线性和非平稳的方法对超声波信号进行了分析处理，对于局部放电模型得到的信号，计算了超声波信号的Lyapunov指数、分维数D、空缺率、小波包分解的8个频带能量，得到了11个特征数据，归一化处理后形成特征向量，由人工神经网络进行识别，实现了对局部放电典型模型的模式识别，显著提高了模式识别的正确率，并分析了传播途径对识别的影响。

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。