神经网络

A new case-matching algorithm, namely ANNI, is proposed in this paper. It uses artificial neural network to setup the mapping relationship, which is generally decided by human expert before and full of unreasonability in weight setting. The ANNI algorithm is proven to be very suitable for mapping between complex-related factor sets and can be applied in case-matching calculation.

首次提出基于BP神经网络的事例匹配度计算—ANNI方法，很好地解决了现有的事例匹配算法需要人为定义权值或匹配规则的缺陷，利用神经网络的自适应性可以有效地确定复杂相关因素集之间的相互映射关系权值矩阵，从而能够有效地应用于基于事例的推理方法中多因素的注塑成型特征集匹配度计算。

Wavelet neural network was trained with experimental data collected from a variety of literature and then was utilized to study influences of geometries of impeller and diffuser on rotating stall in vaneless diffuser, and the results were presented in graphs.

用来自不同文献的实验数据作为样本，对小波神经网络进行训练，并利用训练好的神经网络研究叶轮和扩压器几何尺寸对无叶扩压器失速的影响。

IEPA was combined with neural network by the new algorithm, multi-layer feed-forward neural network structure was replaced with RBF neural network structure, and back propagation algorithm was replaced with IEPA, then, expected side-lobe suppression quota was rapidly waisted.

该算法将进化规划算法和神经网络结合起来，用径向基RBF神经网络结构取代多层前馈网络MFNN（Multilayer Feedforward Neural Nerworks）结构，用改进进化规划取代反向传播算法BP，可以以较大概率快速的收敛到要求的旁瓣抑制指标。

It points out the current situation and existing problems of this method. This paper actualizes the integration of Expert System and Neural Network. It excellently utilizes the advantages of Expert System and BP Neural Network, and overcomes some of their disadvantages.Neural network expert system is designed based on neural network high identification ability and theory research.

本文介绍了专家系统应用于故障诊断的原理，详细阐述了专家系统的结构、各部分功能、工作流程等，并指出了该方法在故障诊断中的应用现状和存在的问题；实现了神经网络和专家系统的结合，很好地利用专家系统和BP神经网络的优点并且克服了它们的一些缺点。

The approximating capability and the generalization capability of the neural network is studied.

神经网络技术是智能控制理论的重要组成部分，当前神经网络在系统辨识与控制中的应用还存在许多问题。

To overcome the bad effect resulting from the nonlinearity time-variability and uncertainty on autopilot system performance during the motion process of aerodynamics missile, and to further improve the flight quality of missile, the autopilot system and used control method are researched. Firstly the integrant structure of system is discussed; then baaed un introducing the traditional PID method, controllers for missile attitude motion are designed respectively using fuzzy self-turning PID method and neural network self-adaptive PID method; at last a simulation experiment is finished. By comparing the simulation results that the designed controllers have good qualities is showed, and the feasibility and validity of applying fuzzy control and neural network into automatic control of aerodynamics missile is confirmed, and the base that other nonlinear control theory can be combined with the traditional control for missile to further improve the performance of missile control system is established.

为了克服飞航导弹运动过程中的非线性、时变性和不确定性对自动驾驶仪系统性能的不良影响，进一步提高导弹的飞行质量，对自动驾驶仪系统及其采用的控制方案进行了研究；首先对系统的整体结构进行了分析，然后在介绍经典PID方案的基础上，分别采用模糊自调整PID方案和神经网络自适应PID方案设计了导弹姿态运动控制器，最后进行了仿真实验；仿真结果的对比展示了所设计控制器良好的品质，验证了将模糊控制和神经网络应用于飞航导弹自动控制中的可行性和有效性，为其它非线性控制理论与导弹传统控制相结合以进一步提高导弹控制系统的性能奠定了基础。

On the basis of the training of network, the mathematics model on the relationship between double glow plasma carbonizing and prediction of properties is built.

将人工神经网络理论和算法应用于双辉离子渗碳的研究，在对人工神经网络训练的基础上，建立了双辉离子渗碳工艺与渗层性能预报的数学模型。

The detector first combines the technology of single chip with the technology of artificial neural network , colligates the strongpoint of single chip and artificial neural network , overcomes the difficulty of linearization between gas sensor output and gas concentration.

该仪器首次将单片机与人工神经网络相结合用于气体浓度检测，综合了单片机和人工神经网络的优点，克服了传统仪器气体传感器输出与气体浓度难以线性化等缺点。

Based on the analysis of available decoupling control method, a neural-based adaptive control algorithm is proposed in this paper.

本文在对现有线性定常多变量系统解耦控制算法及非线性系统的神经网络控制算法分析研究的基础上，提出了基于神经网络的自适应解耦控制算法。

In the aspect of auto diagnosing using neural network in NPP, a lot of fault diagnosing system has been excogitated in foreign country. This thesis is the first study of this aspect in our country.

在使用神经网络对装置进行故障自动诊断方面，国外已经研究了一些核动力装置神经网络故障诊断系统，国内尚未见到这方面的研究报导，本文是国内首次在这方面进行的研究。

We have no common name for a mime of Sophron or Xenarchus and a Socratic Conversation; and we should still be without one even if the imitation in the two instances were in trimeters or elegiacs or some other kind of verse--though it is the way with people to tack on 'poet' to the name of a metre, and talk of elegiac-poets and epic-poets, thinking that they call them poets not by reason of the imitative nature of their work, but indiscriminately by reason of the metre they write in.

索夫农 、森那库斯和苏格拉底式的对话采用的模仿没有一个公共的名称；三音步诗、挽歌体或其他类型的诗的模仿也没有——人们把&诗人&这一名词和格律名称结合到一起，称之为挽歌体诗人或者史诗诗人，他们被称为诗人，似乎只是因为遵守格律写作，而非他们作品的模仿本质。

The relationship between communicative competence and grammar teaching should be that of the ends and the means.

交际能力和语法的关系应该是目标与途径的关系。