神经控制

神经控制（Ⅱ）&神经元网络控制

Neurocontrol (ⅱ) Neural Network Control

基于DSP的轧机调速系统模糊神经控制

Fuzzy Neural Control Based on DSP Chip for Roller Speed Regulation Systems

结果显示在相同环境下，模糊神经控制系统的减摇效果要优于传统PID控制器，证明该控制系统具有可行性。

It is shown that fuzzy neural control system is better than the traditional rolling PID controller .

其次，介绍了模糊控制理论和神经控制理论，模糊控制理论主要论述了二维模糊控制器的设计过程以及模糊自适应PID控制器的原理，神经控制理论重点叙述了BP神经算法的学习过程。

The fuzzy control theory discusses the design process of the fuzzy controller and the principle of fuzzy adaptive PID controller .

具有在线训练功能的智能旋翼频域神经控制

Neural Control Method with On-Line Training in Frequency Domain for Smart Rotor

一种模糊神经控制系统及其应用

On a fuzzy neural control systems and its applications

高精度宽带钢冷轧机板形模糊神经控制的研究

Research on High Precision Flatness Fuzzy Neural Control for Wide Strip Steel Cold Mill

非线性结构振动的神经控制

Neuro - Control for Nonlinear Structural Vibration

挠性卫星姿态的模糊神经控制

Neuro-Fuzzy Control fo Flexible Satellite Attitude

直升机模糊神经控制模型

Helicopter fuzzy nerve control model

分别给出了模糊控制、专家控制和神经控制用于电机拖动系统的行之有效的结构形式。

We put forward effective Structure diagrams of motor drive systems using Fuzzy Control , Expert Control and Neural Conrol .

最终仿真结果还表明双侧模糊神经控制性能要比单侧模糊神经控制效果好。

Finally , The simulation results also show that the effect controlled by fuzzy neural-network both in rectifier and inverter is better than by one of them .

计算结果与实验测量的比较表明：正向动力学方法可将肢体运动状态、肌肉收缩力、神经控制信号等联系起来，求解人体步态的控制模式。

The results show that forward dynamics theory can model the limb movements , muscular forces and neural control signals to simulate the control of a natural gait .

目前智能控制基本形成了专家控制、模糊控制、神经控制、学习控制（包括迭代学习控制）及混合智能控制和智能控制的整体理论体系等几个较成熟的理论和方法。

At present , the well-known theories and methods of Intelligent control are : Expert control , Fuzzy Control , Neural Network Control , Learning Control ( including Iterative Learning Control ), Hybrid control and general theory of Intelligent Control System .

最后通过算例对三个控制算法进行结果分析，得出以下结论：在城市交通干线的协调控制中，递阶模糊神经控制算法优于递阶模糊控制算法，而递阶模糊控制算法又优于定时控制算法。

Finally , compare the three algorithms by examples and have a conclusion that hierarchical fuzzy neural control algorithms is better than hierarchical fuzzy control algorithms and hierarchical fuzzy control algorithms is better than the fixed coordination control algorithms in the urban traffic junction coordination control .

利用B样条神经网络控制聚合物相对分子质量分布新方法

Control of molecular weight distribution of polymerization via B-spline neural networks

基于H∞变结构的不确定机器人模糊神经网络控制

Fuzzy neural-network control based on H_ ∞ variable structure control for uncertain robot manipulators

基于不完全微分PID算法的神经网络控制

The Neural Network Control based on Incomplete Differential PID Algorithm

基于DSP的飞机全电刹车模糊神经网络控制系统

Aircraft Electric Braking System Using Fuzzy Neural Network Control Method Based on DSP

基于多步预测的PID型神经网络控制

A PID-like Neural Network Control Based on Multi-step Prediction

输入输出非对称多变量系统的PID神经网络控制

PID Neural Network Control for Unsymmetry Multivariable Systems

内燃机活塞裙面加工精度的BP神经网络控制技术研究

BP Neural Network Control Technique Study on Processing Accuracy of Internal Combustion Engine Piston Skirt

PID神经网络控制及其在山梨醇生产线上的应用研究

Application of PID Neural Networks Control Based on RBF Neural Networks Identification to the Sorbitol Product Line

用进化RBF神经网络控制二级倒立摆

Controlling a Double Inverted Pendulum Using Evolutionary Radial Basis Function Neural Network

基于DCS的神经网络控制的工程实现

Engineering Implement of Neural Networks Control Based on DCS

混沌系统的RBF神经网络控制设计

Design of RBF Neural Network Control for Chaotic System

基于CMAC神经网络控制的精密定位控制系统

Precise Positioning Control System Based on CMAC Neural Network Control

神经网络控制系统比传统的PID等控制方法，在大时变、强耦合、大滞后等非线性系统中控制效果有着明显的优势。

To some traditional PID methods , and Neuron Control system have some obvious predominance in some big temporal variation , close coupling , controller lag nonlinearity system .

Hammerstein系统自适应神经网络控制算法的收敛性分析

Convergence Analysis for Adaptive Neural Networks Control of Hammerstein System

目前提出的数字控制策略有数字PID控制、自适应控制、模糊控制、神经网络控制、极点配置法、无差拍控制、预测控制等，这些控制策略各有特点，但都有各自的局限性。

The proposed control strategies include digital PID control , adaptive control , fuzzy control , neural network control , pole place control , dead-beat control and predictive control .