In the end, wavelet neural network after being trained is used to approximation of function to performance good approximation of function.
最后用训练后得到的小波神经网络用于函数近似,体现小波神经网络良好的近似功能。
This article indicates the principle for ANN bus protection based on function approximation ability, analyzes the functional relation of bus-bar object and builds the ANN model of bus-bar protection.
叙述了基于ANN函数逼近能力的母线保护原理,分析了母线保护物理对象的函数关系,构建了母线保护的人工神经网络模型。
At paraxial approximation the maximum of the matching function is increasing with increased divergence Angle. For different brightness of pumping light, the optimum value of the Angle is obtained.
发现在旁轴近似下,匹配函数的最大值随泵浦光发散角的增大而增大,在考虑到像散的影响后,得到泵浦光发散角的参考值。
The optimal approximation functions, of a continuous function which are constituted of the linear combination of series of Chebychev polynome have the characteristics of uniform approximation.
应用第一多项式系列的线性组合构成的某连续函数的最佳逼近函数,具有一致逼近的性质。
Study on approximation ability of nonlinear function.
模糊系统对非线性函数逼近能力的研究。
As one of the most important capability of ANN, function approximation ability can be used to design ANN model, which can characterize certain physics object.
函数逼近能力是ANN具有的重要性能之一,依据ANN具有的函数逼近能力,可用ANN模型去替代一个确定的物理对象。
Function approximation is one of the most important ability of ANN, a function object can be replaced by an ANN model with function approximation ability.
函数逼近能力是ANN具有的重要性能之一,依据ANN具有的函数逼近能力,可用ANN模型去替代一个确定的物理对象。
The RBF network function approximation theory and method are introduced, and the method of nonlinear error correction of sensor is presented based on generalized regression neural network(GRNN).
介绍了径向基函数网络的函数逼近原理和方法,提出了一种基于广义回归神经网络(GRNN)的传感器非线性误差校正方法。
The theoretical basis of ANN is function approximation, it USES a two - level feedforward neural network to approach arbitrary function to realize better power flow control.
径向基函数神经网络的理论基础是函数逼近,用一个两层的前向网络去逼近任意函数,以更好地进行潮流控制。
It is to select product samples, then to use methods of function approximation and set up model.
首先选取产品样本,然后采用函数逼近方法建立评价模型。
So there has been a great deal of interest in applying model-free methods such as fuzzy systems for nonlinear function approximation.
因此依然有很多场合需要使用无模型方法—如用模糊系统进行非线性函数逼近等。
This theorem simplifies greatly the analysis of the function approximation ability of FFMLNN because one needs only to study the one dimensional function approximation ability of FFMLNN.
也就是说我们只需研究其一维函数逼近能力,所得的结论完全适合于多维情形,该定理大大简化了前馈多层神经网络函数逼近问题的分析难度。
This method is also suited to design approximation function of passive filter.
这种方法同样适用无滤波器的近似函数设计。
Then the new step function space is introduced and stability problem for the finite difference scheme is discussed by means of variational approximation method.
然后引入新的步长函数空间,并在这个空间上,采用变分近似法讨论该格式的稳定性问题。
The equation of the molecular orientational distribution function was obtained by two-particle cluster approximation and solved by an iterative method.
在二粒子集团近似下导出了分子取向分布函数所满足的方程,并用迭代方法求解。
Based on the learning characteristic of neural network and the function approximation ability of the wavelet, a new self tuning control algorithm is presented.
依据小波的非线性逼近能力和神经网络的自学习特性,提出了一种基于小波神经网络模型的自校正控制算法。
In the present paper the convergence and validity of the results of boundary collocation procedure are studied by considering function approximation.
本文从函数逼近的观点研究了边界配置法解的有效性及收敛性。
The numerical example shows that increasing the item of radial basis function is not a right way to improve the accuracy of results, and more approximation functions should be employed in the DRBEM.
计算结果表明增加径向基函数的项数并不是改善结果的好办法,应该将更多的函数引入双互易边界元法中。
For each time increment, the approximation of each unknown nodal function can be solved with the matrix left division command in MATLAB.
在每一个时间步长,利用MATLAB提供的矩阵左除命令即可求出各个未知节点的函数近似值。
The paper emphasizes on the methods of polynomial surface approximation which is part of numerical approximations, and analyzes the precision of polynomial function model through the measured data.
着重介绍了数值逼近方法中的多项式曲面函数模型逼近法,并通过实测数据对多项式函数模型的精度进行分析。
Finally, the proposed method is applied to the problem of nonlinear function approximation.
最后将所提出的方法用于解决非线性函数的逼近问题。
The new method is based on combining perturbation method of eigen-problems with rational approximation of a vector-value function .
提出了一种新的结合特征灵敏度直接法和向量值函数有理逼近的结构动力重分析方法。
Then the Neural Network PID control is realised in the model. This method makes full use of nonlinear function approximation of the Neural Network.
这种方法充分利用了神经网络的非线性函数逼近能力,构造神经网络自整定PID控制器。
It used the moving least square approximation as a trial function, and used the weighted function of the moving least square approximation as a test function of the weighted residual method.
这种方法采用移动最小二乘函数来近似解变量,并且采用移动最小二乘近似函数的权函数作为加权残值法的权函数。
Then the new function space is introduced and the stability problem for the finite difference scheme is discussed by means of variational approximation method in this function space.
然后引入新的函数空间,并在这个空间上,采用变分近似法讨论了该格式的稳定性问题。
A method is proposed for the approximation and realization of the optimal transfer function of the receivers in full-response digital fiber-optic communication systems.
本文提出了全响应数字光纤通信接收机最佳传递函数的逼近和实现方法;
The adsorption properties of hydrogen on the supported-metal surfaces are investigated using the Green function method within the framework of tight-binding approximation.
应用格林函数方法在紧束缚近似下研究了氢在担载金属表面的吸附性质。
The results show that the eigen spectral functions declined with the increasing of order rapidly. The reconstruction of spectral density function shows that low order approximation is very efficient.
计算结果表明,冲击射流所形成的脉动壁压场可用正交分解进行描述,其特征谱函数随阶数的增加而迅速衰减,对谱密度函数进行低阶近似也非常有效。
The results show that the eigen spectral functions declined with the increasing of order rapidly. The reconstruction of spectral density function shows that low order approximation is very efficient.
计算结果表明,冲击射流所形成的脉动壁压场可用正交分解进行描述,其特征谱函数随阶数的增加而迅速衰减,对谱密度函数进行低阶近似也非常有效。
应用推荐