查询词典 neural network

In this paper, a model of network reconfiguration based on CMAC neural network is proposed.The feeder reconfiguration for loss minimization in distribution systems is realized by changing the status of sectionalizing and tie switches. However, there are many switches in a distribution system.

在满足各种运行约束条件下，以网损最小为目标的配电网重构问题是个典型的非线性整数组合优化问题，由于开关很多，很难用常规的数学模型直接建立负荷与网损最小时的开关状态之间的关系。

Knowledge base, model base, arithmetic base and inference engine for explosion disaster prevention and emergency succour are built. Design and development idea for decision support system based on object-oriented idea are offered. Design of structure and main function modules of DSS for disaster prevention are given. Distributing DSS for disaster prevention and simulation of disaster in chemical process is realized by system integration of diagnosis module for accident mode, neural network module, disaster simulation and evaluation module, knowledge base and its management system、database and its management system, module base and its management system, support environment for software system, network and hardware.

提出了基于面向对象思想的决策支持系统设计与开发思路与策略，给出了防灾决策支持系统的结构设计以及数据库及管理系统、模型库及管理系统、知识库及推理机等主要功能模块的设计方法，并对事故模式诊断模块、神经网络模型、灾害模拟与评价模块、灾害救援预案模块、决策支持四库系统，以及软件系统支撑环境、通讯网络与硬件等进行了系统集成，实现了两层结构的分布式化工过程爆炸灾害模拟与评价及防灾决策支持系统软件系统。

Knowledge base, model base, arithmetic base and inference engine for explosion disaster prevention and emergency succour are built. Design and development idea for decision support system based on object-oriented idea are offered. Design of structure and main function modules of DSS for disaster prevention are given. Distributing DSS for disaster prevention and simulation of disaster in chemical process is realized by system integration of diagnosis module for accident mode, neural network module, disastersimulation and evaluation module, knowledge base and its management system、database and its management system, module base and its management system, support environment for software system, network and hardware.

提出了基于面向对象思想的决策支持系统设计与开发思路与策略，给出了防灾决策支持系统的结构设计以及数据库及管理系统、模型库及管理系统、知识库及推理机等主要功能模块的设计方法，并对事故模式诊断模块、神经网络模型、灾害模拟与评价模块、灾害救援预案模块、决策支持四库系统，以及软件系统支撑环境、通讯网络与硬件等进行了系统集成，实现了两层结构的分布式化工过程爆炸灾害模拟与评价及防灾决策支持系统软件系统。

Knowledge base, model base, arithmetic base and inference engine for explosion disaster prevention and emergency succour are built. Design and development idea for decision support system based on object-oriented idea are offered. Design of structure and main function modules of DSS for disaster prevention are given. Distributing DSS for disaster prevention and simulation of disaster in chemical process is realized by system integration of diagnosis module for accident mode, neural network module, disaster simulation and evaluation module, knowledge base and its management system、database and its management system, module base and its management system, support environment for software system, network and hardware.

提出了基于面向对象思想的决策支持系统设计与开发思路与策略，给出了防灾决策支持系统的结构设计以及数据库及管理系统、模型库及管理系统、知识库及推理机等主要功能模块的设计方法，并对事故模式诊断模块、神经网络模型、灾害模拟与评价模块、灾害救援预案模块、决策支持四库系统，以及软件系统支撑环境、通讯网络与硬件等进行了系统集成，实现了两层结构的分布式化工过程*灾害模拟与评价及防灾决策支持系统软件系统。

This paper presents a Double Kohonen Neural Network lased on the Self－Organize Feature Mapping theory to analyge chomosome automatiolly. The DKNN consists of two layers, each of which is a Kohonen network. The first layer maps a 2－d plane to a 2－d feature space to extract the high－resolution bands of chromosome and to compute the parameters of bands. The second layer maps the arrays of high dimension feature parameters to a 2－d plane to pair and classify the chromosomes automatically.

应用自组织特征映射神经网络原理与方法，建立了双层Kohonen神经网络，其第一层是从二维图象平面到二维特征平面的映射，用于染色体高分辨率带纹的提取和带纹参数的计算，第二层是高维特征参数阵列到二维聚类平面的映射，用于同源染色体的自动配对和分类。

The sample BRDF curves variating with the scatter angle under several incident angles are given, and some of the curves were selected and sent into the artificial neural network. The network was trained with the Bayesian regularizing method. The mapping relation model of BRDF with incident and scatter angles was obtained.

给出测量样品多个入射角度下的BRDF随散射角变化的曲线，从中选取部分曲线输入到神经网络，使用贝叶斯正则化方法训练网络，最终获取双向反射分布函数和入射角、散射角的映射关系模型。

A novel kind of Ordination-Fuzzy min-max neural network based on non-metric multidimensional scaling was proposed to solve the classification problems of unlabeled input pattern. Firstly, all the input patterns were sorted by MDS to get their similarity measures. Then these measures were used to supervise the following expansion and contraction stage of hyperboxes for classification. OFMM had improvements both in the validity of unlabelled patterns classification, and the network structure and training time.

该模型首先利用非刻度—多维度收缩法对输入的所有样本进行了排序，然后获得样本间的相似性测度值，并利用该相似性测度值指导随后的分类器超盒扩张与压缩过程，从而使得该模型不仅提高了对未标记样本进行有效分类的性能，而且无论是在网络结构方面，还是在训练时间方面都有所改进。

On the basis of the algorithm of BP neural network,the network's excitation function has been improved, and an ANN-based Seismic Response recognising system for pile foundation bridge pier has been developed according to the characters of the seismic response of the pier.

在原BP神经网络基本算法的基础上，按研究桩基桥墩地震响应的特点，改进了网络的激励函数，开发了适用于桩基桥墩地震响应的神经网络辨识系统。

This paper describes a new method for constructing a rough neural network. In this network, rough neurons lie in the hidden-layer, and they consist of three parts which generated by two hyperplanes that partition the universe.

本文根据支持向量机可以解决小样本学习问题的优势，再结合粗集理论对不确定性问题分析的特点，提出一种支持向量机的粗糙神经网络的构造方法。

The method of intelligent control based on neural network is applied in electrode current of arc furnace.The electrode current is analyzed and simulated by the BP and RBF models of neral network.

讨论了基于神经网络对电弧炉电极进行智能控制的方法，运用神经网络的BP、RBF以及双隐层BP模型，分别对电弧炉电极的单相电流及三相电流进行了分析和仿真。

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。