The RBF Network with the Green function as the active function is a universal approximator in that it can approximate arbitrarily well any multivariate continuous function. It has the potential of dealing with the nonlinear relationship and can forecast the calorific value of coal quickly and exactly.

Such a four-layer FNN constitutes a universal approximator of fuzzy valued function. That is, each continuous fuzzy valued function defined on any compact set of Euclidean space can be approximated by the FNN to any degree of accuracy.

该类网络构成了模糊值函数的一类泛逼近器，即在欧氏空间的任何紧集上，任意连续模糊值函数能被这类FNN逼近到任意精度。

Considering there are uncertainties in the system's model, fuzzy logic is adopted as an approximator to identify the uncertainties. Using Lyapunov law, we derive the sliding-mode control law and the related parameters adaptive law of fuzzy approximator.

同时考虑到系统模型中存在的不确定项，利用模糊逻辑的逼近功能进行估计，文中采用Lyapunov方法求取了控制器的控制律以及模糊逼近的有关参数的自适应律。

Although for financial time series forecasting methods, as a result of neural network function as a universal approximator of arbitrary precision can be any non-linear function approximation and dynamic system, is a highly non-linear a powerful tool for object modeling.

虽然用于金融时间序列的预测方法很多，但由于神经网络作为一种通用函数逼近器可以以任意精度近似任意的非线性函数和动态系统，是高度非线性对象建模的有力工具。

Learning feed-forward control is a form ( ofeedback-) Error-Learning control, i.e. the control system consists of a feedback controller, and a ( feed-forward) part which is implemented as a function approximator.

学习前馈控制是一种反馈误差学习的控制形式，其包含反馈控制器和采用函数逼近器的前馈控制器两部分。

At last, the authors use RBF neural network as function approximator to build large-signal model of RF-power component and verify that the model based in RBF neural network can accurately simulate the behavior of RF-power component.

最后，以RBF神经网络作为函数逼近器对射频功率器件建立了大信号特征模型，并进行了模型检验，证明了基于RBF网络的建模方法具有较高的精度。

The novel approach has been successfully applied to the construction of the fuzzy model for a nonlinear function approximator and the design of the fuzzy model for a product quality estimator of jet fuel oil in an oil refining plant.

该迭代优化方法已成功地应用于非线性函数逼近和航空煤油干点估计器的模糊模型构造。

Secondly, using the Takagi-Sugeno ( T-S) fuzzy systems as the approximator, the model reference decentralized adaptive control problem for a class of MIMO nonlinear systems with high-order interconnections is systematically studied.

其次，利用Takagi-Sugeno（T-S）模糊系统作为估计器，系统研究了一类具有高阶耦合的MIMO非线性系统的模型参考分散自适应控制问题。

The second is a novel modeling strategy that combines an artificial neural network ( ANN) as an approximator of the growth rate with prior knowledge represented by the mass balance of sucrose crystal.

第二种方法是一种新颖的建模策略，它把晶体生长率作为非线性逼近器的人工神经网络（ANN）与由蔗糖晶体质量平衡所表述的先前既定的知识相结合。

An adaptive fuzzy control system is composed of a structural identification system and a controller system, and introduced for the ER damper-rotor vibration system due to the function approximator property of fuzzy logical system.

本文利用模糊逻辑系统能够逼近非线性函数的特性，设计了电流变阻尼器－转子振动系统自适应模糊控制方案。

A straightforward way to dispel the curse of dimensionality in large stochastic control problems is to replace the lookup table with a generalized function approximator such as state aggregation.

在大规模随机控制问题中，值函数逼近是一种克服维数灾的方法。

Only one fuzzy logic system is employed as approximator to compensate all the unknown items, and at the same time, adaptive technology is adopted on line to identify the unknown parameter.

在控制器设计过程中，仅采用一个模糊逻辑系统作为逼近器，使得所有的未知项得到补偿，同时采用自适应技术在线辨识未知参数和逼近误差上界。

The inputs of the fault approximator are the estimated states. And the outputs estimated from the fault model can be used for fault alarm or for fault tolerant control.

故障估计器的输入为系统的状态估计，所估计出的故障既可用作故障容错控制，也可用作报警。

Neural netWork can be used for automatic generation of fuzzy rules because neural network as a function approximator can realize the data fitting among a pair of inputs and their expected outputs.

对于人工神经网可应用于模糊规则自动生成，这是因为人工神经网可用作近似化工具实现这一系列输入与期望输出之间的数据拟合。

Considering discrete and successive state space separately, a entropy based reinforcement learning algorithm and an auto-generating neural network function approximator method for reinforcement learning are researched.

分别针对离散化的状态空间和连续状态空间的压缩问题，提出了基于信息熵的强化学习算法和基于自主生成神经网络函数逼近器的强化学习算法。

In order to further discuss the identification of fault after the detection, a nonlinear online neural network approximator is used to provide an estimate of the fault.

为了进一步实现故障特性的辨识与跟踪，讨论了一种利用神经网络对非线性故障模式进行在线逼近的鲁棒故障诊断方法。

This paper presents that FCP network model and improved T-S model used in the disquisition are universal approximator, with the latter proved.

本文指出文中用到的FCP网络模型和改进T-S模型为通用逼近器，同时给出后者的证明。

An B spline network is used as function approximator to observing thrust ripples to improve the compensation precision.

采用B样条神经网络作为函数逼近器来实现对由端部效应等引起推力波动的观测，以提高补偿的精度。

Based on a single approximator, an adaptive fuzzy decentralized dynamic sur-face controller is proposed.

提出了一种基于单逼近器的自适应模糊分散动态面控制方法。

Estimated states are input to the fault approximator whose outputs are estimated fault.

然后利用另一个自适应RBF神经网络作为故障估计器，其输入是系统的估计状态（而不是系统状态），其输出为系统所发生的故障模型。

Fuzzy System as Universal Approximator and Its Approximation Properties

作为通用逼近子的模糊系统及其逼近性质