In the paper , by using bp ( back propagation ) method of ann , we can get the relationship between grading , asphalt - aggregate ratio , bulk density , percentage of voids , test temperature and ds . at the same time , we can get the relationship between grading , asphalt - aggregate ratio , bulk density , percentage of voids , test temperature and viscoelastic parameter . at last , we can estimate the ds and draw the deformation curve 本文应用bp人工神经元网络，建立沥青混合料的矿料通过百分率、沥青用量、毛体积密度、空隙率、试验温度与沥青混合料粘弹性参数的关系，或建立沥青混合料的矿料通过百分率、沥青用量、毛体积密度、空隙率、试验温度与车辙试验动稳定度值的关系，从而预估车辙试验的动稳定度值和绘制车辙试验变形曲线。
First , this thesis reviewed the development and applications of anns , and it presented some typical anns which are widely used . especially , it analyzed multi - layer feed - forward neural networks ( fnns ) and their traditional learning algorithm , back propagation ( bp ) algorithm , because fnns are the most common used anns 本文首先介绍了神经网络理论的发展历史和应用领域，然后介绍了人工神经元网络的特点及目前应用比较广泛的几种典型的神经网络，并重点分析了当今最流行的bp网络的特性。
In this paper , the theory of artificial neural network is summarized ; the analyse on bp neural network model is put stress on . for the predominance of artificial neural network ' s dealing with non - linear complicated relation , the technology of artificial neural network is introduced into the evaluation of the highway bridge ' s carrying capacity ; and the preferences , the collection and disposal of stylebook , the structuring of bp neural network model are analyzed 文中对人工神经元网络理论进行了综述，重点对神经元网络的bp算法进行了分析，利用人工神经元网络处理非线性复杂关系的优势，将人工神经元网络技术引入到公路桥梁承载力评估中；并对其中的参数选择、样本收集与处理、构造bp网络模型等进行了分析。
After an evaluation and analysis of international strategy management theory and comprehensive advantage theory , and based on comprehensive advantage theories , this paper has made the following contribution : using a systematic analyzing method on the relative factors of comprehensive advantages of high - tech enterprises , it designs the principles and index system for the evaluation of comprehensive advantages of high - tech enterprises ; using radial basis function artificial neural network ; by inputting relative data of representative high - tech enterprise to a network test , it makes a demonstrative research on the comprehensive advantage evaluation of some high - tech enterprises ; and using fussy analytic hierarchy process to analyze the output , it brings forward the strategy analyzing and selecting methods based on the 本文在对现有国内外企业战略管理理论及综合优势理论研究成果综合评析的基础上，基于综合优势的理论思想，通过对高新技术企业综合优势的相关因素的系统分析，设计了高新技术企业综合优势评价的原则与指标体系，并运用径向基人工神经元网络( rbf - ann )方法，运用典型高新技术企业有关数据进行网络训练，从而提出了一种新的高新技术企业综合优势智能化分类方法。本文运用该智能化评价方法对部分高新技术企业进行了综合优势评价的实证研究，并结合模糊综合评价方法对评价结果进行分析，提出了基于高新技术企业综合优势发展状态进行战略分析与战略选择的有关方法，以指导我国高新技术企业充分利用企业内外部资源、条件和机遇，更好地形成和提高企业综合优势参与市场竞争。
The method of modeling forecasting molten steel based on artificial neural network and expert system was firstly put forward . furthermore , it is applied successfully to the electric furnace in the xingcheng special steel corporation and has an advantage of high veracity and easiness to be used on site 本文率先提出了基于人工神经元网络和专家系统的钢水温度预报建模方法，并成功地应用于江阴兴澄特殊钢有限公司的电炉，具有准确度高和易于现场在线应用的优点。
In this paper , the control system of industrial boiler widely used in industrial production was studied . aiming at the nonlinear object of industrial boiler with instability parameter and difficult building math model , combining fuzzy control theory and neural networks theory , a adaptive controller built with compensatory fuzzy neural networks to control industrial boiler is proposed 本文对于目前在工业生产中广泛应用的工业锅炉的控制系统进行了研究，针对工业锅炉这种具有非线性、参数不稳定、难以建立精确的数学模型的控制对象，结合模糊控制理论和人工神经元网络理论，提出用补偿模糊神经网络构造自适应控制器实现对工业锅炉的过程控制。
Ycm ann works under the principle of vcm , in which ann targets to adjust the faint knowledge of vcm and keeps the knowledge among the connections of ann crunodes in ftart arm network . the thesis has testified that vcm ann method is more precise than tf idf ig , can conquer part of what the latter can not deal with , and has less work to compute 我们通过实验证明了人工神经方法的计算精度比改进的信息增益方法高，能够有效地克服信息增益方法不能克服的精确性问题，计算的复杂性也比信息增益方法低，这说明人工神经元网络方法虽然捕捉的是模糊信息，却能够较为精确的捕捉到文档中词条项与文档的类别之间的模糊关系。
The main research fields are image processing , computer vision and pattern recognition , multi - media visual and audio information processing , virtual reality and its application , multi - media cooperative works system based on computer network , multi - media communication and multi - dimensional digital signal processing , information processing and artificial neural network , and digital information system 主要研究方向： "图像处理、计算机视觉与模式识别" 、 "多媒体视听信息处理与计算机图形学" 、 "虚拟现实及应用" 、 "基于计算机网络的多媒体协同工作系统" 、 "多媒体通信与多维数字信号处理" 、 "信息处理与人工神经元网络"及"数字信息系统" 。
The steps and goals to build ks are also presented . thirdly , after the theoretical analysis of kss , it concludes the goals and drivers and gives an illustration of two main patterns to create and accumulate knowledge : cross transition patterns of tacit and explicit knowledge , and architectural and component knowledge , then suggests that the push and pull interaction based on sense and respond pattern is the general pattern of kss . it designs a measurement index system for knowledge stock and develops a bp artificial neural network to stimulate the knowledge stock and its structure 再次，论文在追溯了企业知识专门化的理论渊源之后，总结了企业采纳知识专门化战略的目标和动因，论述了企业创造和积累知识的主要模式? ? “隐性? ?显性知识”和“构架? ?元素知识”的交互转化模式，提出了基于“感测与响应”的“推拉”互动模式是企业知识专门化战略的一般模式，设计了一套企业知识存量的评价指标体系，并构造bp人工神经元网络对企业知识存量进行了模拟，对其知识存量及结构进行了比较分析。
