2) neural network forecast
神经网络预测
1.
An artificial neural network forecast model for shaft lining non-mining fracture;
煤矿立井井筒非采动破裂的人工神经网络预测
3) neural network prediction
神经网络预测
1.
A real time intelligent control method including the advantage of artificial intelligence ,expert control,fuzzy control, neural network prediction and adaptive control was put forward in this paper aimed to design a integrated real time hierarchical intelligent control system.
本文提出一种实时智能控制方案 :融合人工智能、专家系统、模糊控制、神经网络预测和自适应控制的优点 ,设计成一个集成环境的实时递阶智能控制系统。
2.
methods from static,centralized dynamic,decentralized dynamic to behavior based were reviewed,their performances were analyzed and compared The new intelligent routing approach based on multi agent systems and neural network prediction was presented Simulation results demonstrated it s outstanding by virtue of its upstanding distribution and intelligenc
提出全新的基于多Agent系统和神经网络预测的智能路由策略。
3.
In the paper,on the bases of demerit-analysis of route-selecting methods being used in switch,a new routing approach based on neural network prediction was presented,including performance indicators,routing method,and recurrent neural n.
本文针对目前所使用的路由选择方法的不足 ,提出基于神经网络预测的新的路由选择方法 ,包括性能指标、选路思想和递归神经网络预测等 。
4) Predictive neural net
预测神经网络
1.
This paper adopt Fuzzy neural net(FNN) to deal with double hydraulic motors velocity feedback and Predictive neural net(PNN) for outer gimbal angle feedback,FNN controller simulate cerebra neural net(CNN) based on experiential control and PNN controller depend on self-study simulate CNN.
针对影响三轴电液仿真转台动、静态性能最大的同步驱动、摩擦和大惯量负载干扰三个问题,采用了模拟人脑基于经验控制的FNN(模糊神经网络)控制器和基于学习校正的PNN(预测神经网络)控制器分别对应转台内环(角速度环)和外环(角度环)反馈系统。
5) Neural network predictor
神经网络预测器
1.
The Fault Diagnose Based on Neural Network Predictor for Pressure Sensor in HTG System;
基于神经网络预测器的静压式油罐计量系统压力传感器的故障诊断
6) PMV index predicted by using ANN
PMV神经网络预测
补充资料：人工神经网络
| 人工神经网络 artificial neural network 一种模仿动物神经网络行为特征的分布式并行信息处理算法结构的动力学模型。它用接受多路输入刺激，按加权求和超过一定阈值时产生“兴奋”输出的部件来模仿动物神经元的工作方式，并通过这些神经元部件相互联接的结构和反映关联强度的权系数使其“集体行为”具有各种复杂的信息处理功能。特别是这种宏观上具有鲁棒、容错、抗干扰、适应性、自学习等灵活而强有力功能的形成不是由于元部件性能不断改进，而是通过复杂的互联关系得以实现，因而人工神经网络是一种联接机制模型，具有复杂系统的许多重要特征。人工神经网络适用于信号处理、数据压缩、模式识别 、机器人视觉、知识处理及其应用，预测、评价和决策问题 ，调度排序、路由规划等组合优化问题。在控制系统设计中它可用于模拟被控对象特性、搜索和学习控制规律、实现模糊和智能控制。 |
说明：补充资料仅用于学习参考，请勿用于其它任何用途。
参考词条