Structure selective updating for nonlinear models and radial basis function neural networks

Selective model structure and parameter updating algorithms are introduced for both the online estimation of NARMAX models and training of radial basis function neural networks. Techniques for on-line model modification, which depend on the vector-shift properties of regression variables in linear models, cannot be applied when the model is non-linear. In the present paper new methods for on-line model modification are developed. These methods are based on selectively updating the non-linear model structure and therefore lead to a reduction in computational cost. A real data set is used to demonstrate the performance of the new algorithms. © 1998 John Wiley & Sons, Ltd.     

基于最小径向基函数(MRBF)神经网络的非线性噪声对消

由于传统线性噪声对消器对非线性噪声不能很好的适应,本文改进传统线形噪声对消器的线形滤波器部分,用MRBF网络代替横向LMS结构,以适应非线形噪声存在的情况.使用改进的RBF网络结构MRBF[1],解决了隐单元数目确定的困难,学习算法采用更加稳定的扩展卡尔曼滤波方法(KEF),增强了RBF的实用性.本文提出的方法降低了运算复杂度,增强实时性.仿真结果表明该方法有良好的噪声对消性能.     

Accurate fault locator for EHV transmission lines based on radial basis function neural networks

This paper describes the design and implementation of an artificial neural networks-based fault locator for extra high voltage (EHV) transmission lines. This locator utilizes faulted voltage and current waveforms at one end of the line only. The radial basis function (RBF) networks are trained with data under a variety of fault conditions and used for fault type classification and fault location on the transmission line. The results obtained from testing of RBF networks with simulated fault data and recorded data from a 400 kV system clearly show that this technique is highly robust and very accurate. The technique takes into account all the practical limitations associated with a real system. Thereby making it possible to effectively implement an artificial intelligence (AI) based fault locator on a real system.     

A radial basis function neural network controller for UPFC

This paper presents the design of radial basis function neural network controllers (RBFNN) for UPFC to improve the transient stability performance of a power system. The RBFNN uses either a single neuron or multi-neuron architecture and the parameters are dynamically adjusted using an error surface derived from active or reactive power/voltage deviations at the UPFC injection bus. The performance of the new single neuron controller is evaluated using both single-machine infinite-bus and three-machine power systems subjected to various transient disturbances. In the case of three-machine 8-bus power system, the performance of the single neuron RBF controller is compared with a BP (backpropagation) algorithm based multi-layered ANN controller. Further it is seen that by using a multi-input multi-neuron RBF controller, instead of a single neuron one, the critical clearing time and damping performance are improved. The new RBFNN controller for UPFC exhibits a superior damping performance in comparison to the existing PI controllers. Its simple architecture reduces the computational burden thereby making it attractive for real-time implementation     

Control of robots using radial basis function neural networks with dead‐zone

In this paper, we examine the control of robot manipulators utilizing a Radial Basis Function (RBF) neural network. We are able to remove the typical requirement of Persistence of Excitation (PE) for the desired trajectory by introducing an error minimizing dead‐zone in the learning dynamics of the neural network. The dead‐zone freezes the evolution of the RBF weights when the performance error is within a bounded region about the origin. This guarantees that the weights do not go unbounded even if the PE condition is not imposed. Utilizing protection ellipsoids we derive conditions on the feedback gain matrices that guarantee that the origin of the closed loop system is semi‐globally uniformly bounded. Simulations are provided illustrating the techniques. Copyright © 2011 John Wiley & Sons, Ltd.     

中央制冷空调冷冻水系统模糊RBF控制研究

针对中央空调冷冻水系统回水温度快速准确调节问题,提出基于模糊径向基函数(radial basis function,RBF)网络的变流量回水温度智能控制方法。首先,对冷冻水系统旁通阀门的水量开度、泵组转速等输入量,按照模糊控制理论,进行模糊化与反模糊化处理,获得归一化的输入信息向量;然后,利用能够全局寻优的RBF网络进行温度预测,不断迭代预测产生理想的预测温度;最后,当期望温度与预测迭代的温度残差小于门限值时,停止迭代,输出并记录温度,完成冷冻水系统的非线性温度控制。仿真实验表明,相比于传统反向神经(back propagation,BP)网络控制,RBF控制方法迭代次数更少且精度更高,能够提高系统的整体性能。     

Application of minimal radial basis function neural network todistance protection

The paper presents a new approach for the protection of power transmission lines using a minimal radial basis function neural network (MRBFNN). This type of RBF neural network uses a sequential learning procedure to determine the optimum number of neurons in the hidden layer without resorting to trial and error. The input data to this network comprises fundamental peak values of relaying point voltage and current signals, the zero-sequence component of current and system operating frequency. These input variables are obtained by a Kalman filtering approach. Further, the parameters of the network are adjusted using a variant of extended Kalman filter known as locally iterated Kalman filter to produce better accuracy in the output for harmonics, DC offset and noise in the input data. The number of training patterns and the training time are drastically reduced and significant accuracy is achieved in different types of fault classification and location in transmission lines using computer simulated tests     

Effectiveness of artificial neural networks for first swingstability determination of practical systems

The paper presents an evaluation of the effectiveness of artificial neural networks for rapid determination of critical clearing times for practical networks with varying line outages and load patterns. Studies are reported on the performance of artificial neural networks which have been trained using previously proposed and new training items. It is concluded that artificial neural networks have difficulty in returning consistently accurate answers under varying network conditions     

Adaptive tuning of power system stabilizers using radial basis function networks

A novel approach for on-line adaptive tuning of power system stabilizer (PSS) parameters using radial basis function networks (RBFNs) is presented in this paper. The proposed RBFN is trained over a wide range of operating conditions and system parameter variations in order to re-tune PSS parameters on-line based on real-time measurements of machine loading conditions. The orthogonal least squares (OLS) learning algorithm is developed for designing an adequate and parsimonious RBFN model. The simulation results of the proposed radial basis function network based power system stabilizer (RBFN PSS) are compared to those of conventional stabilizers in case of a single machine infinite bus (SMIB) system as well as a multimachine power system (MMPS). The effect of system parameter variations on the proposed stabilizer performance is also examined. The results show the robustness of the proposed RBFN PSS and its ability to enhance system damping over a wide range of operating conditions and system parameter variations. The major features of the proposed RBFN PSS are that it is of decentralized nature and does not require on-line model identification for tuning process. These features make the proposed RBFN PSS easy to tune and install.     

基于径向基神经网络的可用输电能力概率分析

可用输电能力(ATC)是电力系统经济安全运行的一项重要指标.由于大量风电并网和用户用电行为的多样化,ATC的计算必须要考虑其带来的不确定源.而在对不确定源相关性的处理时,Nataf变换中标准正态分布域相关系数的求解尤为复杂,传统的基于辛普森数值积分和二分法的相关系数转换法耗时极其严重.在概率计算中,采用蒙特卡洛法基于最...     

基于权重自适应更新径向基函数神经网络的水下游动机械臂镇定控制

水下游动机械臂（underwater swimming manipulator, USM）是一种由水下蛇形机器人和矢量推进器组成的新型水下机器人。USM系统具有高度非线性、强耦合以及不确定性等特点,其动力学模型难以精确建立。因此,实现USM的高精度镇定控制存在挑战。针对这一问题,本文基于反馈线性化和自适应径向基函数神经网络（radial basis function neural network, RBFNN）,设计了一种动力学控制方案以实现USM的镇定控制。首先,介绍了USM平台结构,基于Lagrange方程给出了USM的动力学模型,并推导了USM的矢量推力系统模型。然后,设计了基于反馈线性化和RBFNN的动力学控制器,并通过反步法自适应更新RBFNN的权重。其中,权重自适应更新RBFNN用于实时估计系统未建模部分、参数误差以及外部扰动,从而对动力学控制器进行补偿。此外,为了将动力学控制器提供的广义力和力矩转换成各个执行器的控制输入,给出了推力分配策略。最后,进行了湖泊实验,分别对USM的I构型和C构型镇定控制,文章所提出的控制方案在两种构型下的稳态误差均小于0.08 m和10°,验证了所提出的USM六自由度镇定控制器的有效性。     

The Neurochip BCI: towards a neural prosthesis for upper limb function.

The Neurochip BCI is an autonomously operating interface between an implanted computer chip and recording and stimulating electrodes in the nervous system. By converting neural activity recorded in one brain area into electrical stimuli delivered to another site, the Neurochip BCI could form the basis for a simple, direct neural prosthetic. In tests with normal, unrestrained monkeys, the Neurochip continuously recorded activity of single neurons in primary motor cortex for several weeks at a time. Cortical activity was correlated with simultaneously-recorded electromyogram (EMG) activity from arm muscles during free behavior. In separate experiments with anesthetized monkeys, we found that microstimulation of the cervical spinal cord evoked movements of the arm and hand, often involving multiple muscles synergies. These observations suggest that spinal microstimulation controlled by cortical neurons could help compensate for damaged corticospinal projections.     

Accurate prediction of different forecast horizons wind speed using a recursive radial basis function neural network

Environmental considerations have prompted the use of renewable energy resources worldwide for reduction of greenhouse gas emissions. An accurate prediction of wind speed plays a major role in environmental planning, energy system balancing, wind farm operation and control, power system planning, scheduling, storage capacity optimization, and enhancing system reliability. This paper proposes an accurate prediction of wind speed based ona Recursive Radial Basis Function Neural Network (RRBFNN) possessing the three inputs of wind direction, temperature and wind speed to improve modern power system protection, control and management. Simulation results confirm that the proposed model improves the wind speed prediction accuracy with least error when compared with other existing prediction models.     

利用径向基函数神经网络处理水轮机综合特性曲线

介绍了利用径向基函数神经网络进行水轮机综合特性曲线数据处理的方法。这种方法无须建立具体的函数关系表达式,即可对已知离散数据进行拟合,并结合边界约束条件对未知区域内的数据进行预测,从而提高了水轮机综合特性曲线数据处理的工作效率和数据精度。     

基于多输出衰减径向基函数神经网络的电网故障诊断

为提高电网故障诊断神经网络模型的构建速度,提出了一种基于多输出衰减径向基函数（Multi-output Decay Radial Basis Function, MDRBF）神经网络的故障诊断方法。DRBF神经网络不需训练即能以任意精度一致逼近任意连续多变量函数。介绍了单输出DRBF（Single-output DRBF, SDRBF）神经网络,分析了其存在的不足,即只能处理单输出变量问题,不能直接应用于电网故障诊断。在此基础上,根据电网元件的故障特点,提出了将SDRBF神经网络演变为多输出DRBF（Mu     

Application of artificial neural networks for optimization ofelectrode contour

In this paper artificial neural networks (NN) with supervised learning are proposed for HV electrode optimization. To demonstrate the effectiveness of artificial NN in electric field problems, a simple cylindrical electrode system is designed first where the stresses can be computed analytically. It is found that once trained, the NN can give results with mean absolute error of ~1% when compared with analytically obtained results. In the next section of the paper, a multilayer feedforward NN with a back-propagation algorithm is designed for electrode contour optimization. The NN is first trained with the results of electric field computations for some predetermined contours of an axisymmetric electrode arrangement. Then the trained NN is used to give an optimized electrode contour in such a way that a desired stress distribution is obtained on the electrode surface. The results from the present study show that the trained NN can give optimized electrode contours to get a desired stress distribution on the electrode surface very efficiently and accurately     

A solution method of unit commitment by artificial neural networks

The authors explore the possibility of applying the Hopfield neural network to combinatorial optimization problems in power systems, in particular to unit commitment. A large number of inequality constraints included in unit commitment can be handled by dedicated neural networks. As an exact mapping of the problem onto the neural network is impossible with the state of the art, a two-step solution method was developed. First, generators to be stored up at each period are determined by the network, and then their outputs are adjusted by a conventional algorithm. The proposed neural network could solve a large-scale unit commitment problem with 30 generators over 24 periods, and results obtained were very encouraging     

一类非线性混沌系统的RBF神经网络控制

设计了一种基于径向基函数网络(RBFNs)的混沌非线性动力系统控制方法，将嵌入在混沌吸引子中不稳定周期轨道镇定到稳定不动点。用Logistic方程和Henon映射作数值仿真实验，证明了该方法的有效性。     

基于神经网络辨识的模糊预测函数控制

针对生产过程中存在的滞后性、时变性、不确定性和变工况等特点及预测函数控制中模型失配的影响的情况,提出了基于神经网络辨识参数、通过模糊推理对控制量进行补偿的解决方案。并将基于神经网络辨识的模糊补偿预测函数控制应用于锅炉燃烧控制系统,通过连续系统仿真,结果表明这种控制器具有较强的鲁棒性。     

Application of fuzzy neural networks and artificial intelligence for load forecasting

An integrated evolving fuzzy neural network and simulated annealing (AIFNN) for load forecasting method is presented in this paper. First we used fuzzy hyper-rectangular composite neural networks (FHRCNNs) for the initial load forecasting. Then we used evolutionary programming (EP) and simulated annealing (SA) to find the optimal solution of the parameters of FHRCNNs (including parameters such as synaptic weights, biases, membership functions, sensitivity factor in membership functions and adjustable synaptic weights). We knew that the EP has a good capability for searching for globe optimal value, but a poor capability for searching for the local optimal value. And, the SA only had a good capability for searching for a local optimal value. Therefore, we combined both methods to obtain both advantages, and so improve the shortcoming of the traditional ANN training where the weights and biases are always trapped into a local optimum. Finally, we use the AIFNN to see if we could improve the solution quality, and if we actually could reduce the error of load forecasting. The proposed AIFNN load forecasting scheme was tested using data obtained from a sample study including 1 year, 1 month and 24 h time periods. The result demonstrated the accuracy of the proposed load forecasting scheme.