搜索资源列表
asdf
- 本文提出一种粗糙集理论和动态前馈神经网络相结合的神经网络构造方法。充分发挥了粗糙集理论和神经网络的优势，弥补了各自的缺点。并应用于实际工业过程，在乙烯装置裂解炉燃料气热值控制中取得了良好的应用效果。-This paper presents a rough set theory and dynamic feedforward neural networks combined neural network constructed. Give full play to the rough set th
Power-Apparatus
- 关于TCR+FC型SVC的研究文献，这篇文章考查了晶闸管控制的并联补偿器的理论基础。不平衡负荷补偿和电压稳定的条件是建立在对称分量的应用上的。适用于前馈控制（电脑的）的数学关系是根据。这里对前馈和反馈的实用方法进行了讨论。-This paper examines the theoretical foundations of thyristorcontrolled shunt compensation. Conditions for unbalanced load compensation and
compensation-of-dead-time
- 交流伺服系统中的死区效应分析与补偿分析了逆变器的死区效应产生的原因及其对交流伺服系统控制性能产生的影响,指出死区补偿的关键 在于电流相位的获取,为了克服实际系统中电流零点的模糊性,提出了一种基于两相静止坐标系下的前馈死 区补偿方法. 该方法通过对三相输出电流一个周期内补偿电压进行傅里叶变换,发现仅需补偿1 ,5 ,7 次谐波 分量即可消除死区效应. 仿真和试验结果验证了这种方法的正确性和可行性.-AC servo system analysis and compensation of
ccdd
- 前馈调节与反馈调节相比较,其中的一个差异是:系统质量对对象特性参数或调节器参数的变化的敏感程度前者强于后者。-Feedforward adjustment and feedback regulation comparison, one of the differences are: the change of the system the quality of the object characteristic parameters or the regulator parameter and
A-hybrid
- 针对传统的ＢＰ或ＧＡ对模糊神经网络的识别应用存在收敛容易陷入局部极小 识别率低下等问题 提出一 种基于ＢＦＧＳ的混合遗传算法 其基本思想为 首先构造一种前馈型模糊神经网络结构 然后用遗传算法进化若干代 后 当目标函数的梯度或者范数小于预先设定值 则改用ＢＦＧＳ算法进行优化识别 仿真实验表明 对比ＧＡ该算法 收敛速度较快 识别精度提高了约７％ 能够较好地应用于一类模糊神经网络的识别-In traditional BP or GA to identify the application
position-control-algorithm
- 在运动控制中反馈和前馈补偿的位置控制算法的研究，以及软件实现。-n motion control feedback and feedforward compensation position control algorithm and software implementation.
-feedforward-technology-
- 射频功率放大器前馈线性化技术研究-RF power amplifier feedforward technology research
434
- 基于多层前向网络的诊断模型在设备 故障诊断领域应用比较广泛。 但在多层前向网络的 设计和训练问题上, 单隐层的隐层单元数选取一直非常困难, 一般采用试凑 法, 既费时又 不一定保证收敛。-Diagnostic model based on multilayer feedforward networks in the field of equipment fault diagnosis used widely. But before multilayer design and training
I-ELM
- Universal Approximation Using Incremental Constructive Feedforward Networks With Random Hidden Nodes
神经网络极速学习方法研究
- 单隐藏层前馈神经网络(Single-hidden Layer Feedforward Neural Network, SLFN)已经在模式识别、自动控制及数据挖掘等领域取得了广泛的应用，但传统学习方法的速度远远不能满足实际的需要，成为制约其发展的主要瓶颈。产生这种情况的两个主要原因是：（1）传统的误差反向传播方法(back propagation，BP)主要基于梯度下降的思想，需要多次迭代；（2）网络的所有参数都需要在训练过程中迭代确定。因此算法的计算量和搜索空间很大。针对以上问题，借鉴ELM的
ruoci-2
- 关于弱磁控制的文献，超前叫控制，电压前馈等等，希望对正在研究PMSM控制的你，有帮助-About flux-weakening control literature, advanced call control, voltage feedforward, etc., and I hope you are studying PMSM control, help
bpwt
- 神经网络算法和小波分解与重构，BP（Back Propagation）网络，是一种按误差逆传播算法训练的多层前馈网络-Neural network algorithm and wavelet decomposition and reconstruction, BP (Propagation Back) network, is a kind of multilayer feedforward network trained by the error back propagation algorit
06118316
- Pipelined Radix- Feedforward FFT Architectures
1-s2.0-S0022460X11004858-main
- Multi-input multi-output feedforward control of multi-harmonic gearbox vibrations using parallel adaptive notch filters in the principal component space
05420961
- In this paper it is presented a detailed descr iption of the analog implementation of the control for a DC-AC converter composed by a DC-DC Zeta converter and a low frequency inverter. Using only analog components, it was developed the MPPT t
266-Abdusalam
- Control of Hybrid Active Filter Without Phase Locked Loop in the Feedback et Feedforward Loops
offer-pid
- MATLAB实现前馈补偿PID程序 能够实现反馈PID 这个程序可以使用-MATLAB realize PID feedforward compensation program
The-Systematic-Trajectory-Search-Algorithm-for-Fe
- In this paper we present the systematic trajectory search algorithm (STSA) which first globally explores the solution space then makes thorough local searches in promising areas. The STSA has been tested on training feedforward neural network
Novel-Neuronal-Activation
- Feedforward neural network structures have extensively been considered in the literature. In a significant volume of research and development studies hyperbolic tangent type of a neuronal nonlinearity has been utilized. This paper dwells on the w
Deep Learning
- deep learning 书籍，此书包括机器学习基础，深度前馈网络，卷积网络，蒙特卡洛方法等的详细介绍(Deep learning books, which include a detailed introduction to machine learning, deep feedforward networks, convolution networks, Monte Carlo methods, and so on)