首页 | 本学科首页   官方微博 | 高级检索  
相似文献
 共查询到20条相似文献,搜索用时 46 毫秒
1.
An intelligent power factor correction approach based on artificial neural networks (ANN) is introduced. Four learning algorithms, backpropagation (BP), delta-bar-delta (DBD), extended delta-bar-delta (EDBD) and directed random search (DRS), were used to train the ANNs. The best test results obtained from the ANN compensators trained with the four learning algorithms were first achieved. The parameters belonging to each neural compensator obtained from an off-line training were then inserted into a microcontroller for on-line usage. The results have shown that the selected intelligent compensators developed in this work might overcome the problems occurred in the literature providing accurate, simple and low-cost solution for compensation.  相似文献   

2.
This paper describes many of the generic factors which influence the computational demands of continually online-trained backpropagation artificial neural networks (ANNs) used to identify and control fast processes. The limitations of even parallel hardware in meeting these demands is discussed. An adaptive online-trained ANN induction motor stator current controller is considered as a typical fast process. Various modifications are made to the ANN structure to lower computational demands and increase ANN parallelism. The effects of these modifications on the overall controller stability and performance are illustrated by means of simulation results  相似文献   

3.
An adaptive loss evaluation algorithm for power transmission systems is proposed in this paper. The algorithm is based on training of artificial neural networks (ANNs) using backpropagation. Due to the capability of parallel information processing of the ANNs, the proposed method is fast and yet accurate. Active and reactive powers of generators and loads, as well as the magnitudes of voltages at voltage-controlled buses are chosen as inputs to the ANN. System losses are chosen as the outputs. Training data are obtained by load flow studies, assuming that the state variables of the power system to be studied take the values uniformly distributed in the ranges of their lower and upper limits. Load flow studies for different system topologies are carried out and the results are compiled to form the training set. Numerical results are presented in the paper to demonstrate the effectiveness of the proposed algorithm in terms of accuracy and speed. It is concluded that the trained ANN can be utilized for both off-line simulation studies and on-line calculation of demand and energy losses. High performance has been achieved through complex mappings, modeled by the ANN, between system losses and system topologies, operating conditions and load variations  相似文献   

4.
This paper presents a prototype hardware implementation of a continually online trained artificial neural network (ANN) to adaptively identify the electrical dynamics of an induction machine and control its stator currents from a pulsewidth modulated voltage-source inverter. A single-transputer-based hardware platform is described, and the effects of computational speed limitations on the controller bandwidth are discussed. Captured results are compared with simulation results to practically verify the success of the adaptive neural network identification and control scheme  相似文献   

5.
This paper presents the implementation of an artificial-neural-network (ANN)-based real-time adaptive controller for accurate speed control of an interior permanent-magnet synchronous motor (IPMSM) under system uncertainties. A field-oriented IPMSM model is used to decouple the flux and torque components of the motor dynamics. The initial estimation of coefficients of the proposed ANN speed controller is obtained by offline training method. Online training has been carried out to update the ANN under continuous mode of operation. Dynamic backpropagation with the Levenburg-Marquardt algorithm is utilized for online training purposes. The controller is implemented in real time using a digital-signal-processor-based hardware environment to prove the feasibility of the proposed method. The simulation and experimental results reveal that the control architecture adapts and generalizes its learning to a wide range of operating conditions and provides promising results under parameter variations and load changes.  相似文献   

6.
针对MIMO非线性强耦合的两电机变频调速系统,在基于神经网络逆系统离线训练的基础上提出了在线调整的策略,通过静态神经网络加积分器来构造两电机变频调速系统的逆模型,在实际运行中不断地修正神经网络权值,更精确地逼近其逆系统,实现MIMO系统的线性化与解耦.仿真和实验结果表明,系统具有优良的动静态解耦性能和较强的抗负载扰动的能力.  相似文献   

7.
Chromosome classification using backpropagation neural networks   总被引:2,自引:0,他引:2  
The feasibility of an artificial neural network as a chromosome classifier was examined in this study, using the relative length, the centromeric index, and the density distribution of G-banded chromosome as feature vectors. The two-layer neural network trained with the error backpropagation training algorithm showed good potential in classification of Giemsa-banded human chromosomes. The minimum classification error was obtained with the configuration that had 27 input nodes and 24 PEs in the hidden layer. However, this study also showed some problems. Only two experiments, which had 25 and 50 density distribution samples, respectively, were carried out, due to the long computation time of the backpropagation neural network. Also, the centromere finding algorithm used in this study could not apply to telocentric chromosomes (group D and group G) because of their very small short arms; their centromere locations were determined manually. The algorithm must be modified so that it can be applied to all types of chromosomes to reduce the preprocessing time. Better training algorithms to reduce training time are needed. The error backpropagation training algorithm requires very long training times. Next, finding the optimal number of input nodes that gives the minimum classification error requires a trial and error experiment. Finally, other chromosome features that reduce the classification error need to be examined  相似文献   

8.
9.
ANN分类能力的ANN保护方法需要大量故障样本,但由于完整的故障样本的获取不易,提出了基于人工神经网络(ANN)函数逼近能力的ANN母线保护方法。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。母线保护的物理对象是一个输入输出关系确定的函数对象,可用一个ANN模型去替代,或用一个ANN数学模型去逼近母线保护物理对象的输入输出之间的函数关系。通过这个在无故障运行时学习训练出来的母线保护对象的ANN数学模型,就能判断区分母线保护对象的区内和区外故障。  相似文献   

10.
组合式非周期缺陷接地结构(CNPDGS)是由光子带隙结构(PBG)发展而来的,它具有结构简单、电路尺寸小、插入损耗小、设计参数少等优点。本文采用RBF神经网络建立了CNPDGS的神经网络模型。神经网络训练成功后,在其学习范围内,该模型能立刻给出任意尺寸结构的准确可靠的传输系数(S21)。结果证明神经网络建模的方法具有快速、准确、可靠等优点,具有很高的实用价值。  相似文献   

11.
This paper illustrates a new application of artificial neural network (ANN) observers in identifying and estimating synchronous generator dynamic parameters via time-domain, on-line disturbance measurements. To prepare the training database for an ANN observer, the transient behaviours of synchronous generators have been determined through off-line simulations of a generator operating in a one-machine-infinite-bus environment. The Levenberg–Marquardt optimization utilising very fast back propagation algorithm has been adopted for training feed-forward neural networks. The inputs of ANNs are organized in coordination with the data from the observability analysis of synchronous generator parameters in its dynamic behaviour. A collection of ANNs with same inputs but different outputs is developed to determine a set of the parameters. The ANNs are utilized to estimate the above parameters by the measurements for every kind of fault separately. The robustness tests are executed by on-line measurements to identify the parameters. Simulation studies not only indicate that the observer is capable to identify the dynamic parameters of synchronous generator but also show that the tests which have given better results in identification of each dynamic parameter can be acquired.  相似文献   

12.
一种永磁同步电机解耦控制的新方法   总被引:1,自引:0,他引:1  
针对永磁同步电机这一多变量、非线性、强耦合的控制对象,提出了一种基于神经网络在线辨识的永磁同步电机逆系统解耦控制新方法。通过静态神经网络加积分器来构造永磁同步电机的逆系统,并在实际运行中不断地修正神经网络权值,使其更精确地逼近逆系统。将逆系统与永磁同步电机原系统复合成两个伪线性子系统,使永磁同步电机解耦成二阶线性转速子系统和一阶线性磁链子系统,在此基础上,运用线性系统理论进行综合。仿真试验表明这种控制策略能够实现永磁同步电机转速和定子磁链之间的动态解耦控制,并且系统具有良好的动静态性能。  相似文献   

13.
In this paper, an artificial neural network (ANN) based internal fault detector algorithm for generator protection is proposed. The detector uniquely responds to the winding earth and phase faults with remarkably high sensitivity. Discrimination of the fault type is provided via three trained ANNs having a six dimensional input vector. This input vector is obtained from the difference and average of the currents entering and leaving the generator windings. Training cases for the ANNs are generated via a simulation study of the generator internal faults using Electromagnetic Transient Program (EMTP). A genetic algorithm is employed to reduce training time. The proposed ANN algorithm is compared with a conventional differential algorithm. It is found to be superior regarding sensitivity and stability  相似文献   

14.
This paper presents a study of the feasibility of using artificial neural networks (ANNs) in transient stability assessment for power systems. In the study ANNs have been developed to synthesize the complex mapping that carries the power system operating variables and fault locations into the Critical Clearing Times. The training of the ANNs was achieved through the method of backpropagation. The critical fault clearing time values were obtained by the Extended Equal Area Criterion method and used for training. In this work, an attempt was made to avoid the restrictions on load and topology variations. The parameters of the ANNs consist of the generation and loading levels. None of these inputs require any computation. This feature is desirable for on-line transient stability assessment purposes.Training of the ANNs was achieved using a combined production learning phase. The training patterns were not limited to a given collection of samples. This scheme eliminates the problem that an ANN may be influenced by the regions of attraction of a specific category.  相似文献   

15.
This paper presents a novel approach to sensorless vector control of induction motor drives. The method is based on an adaptive flux observer in the rotorspeed reference frame in which an artificial neural network (ANN) is employed to modify the estimated rotor flux to improve the performance of speed estimation. The adopted ANN is a feed-forward neural network identified off-line. It uses the backpropagation learning process to update their weights. The data for training are obtained from a computer simulation and experimental data file of a vector control system. Then, the estimated rotor flux is used in the speed estimation that will feedback to the vector control system. The proposed method has the advantages of better accuracy at low speed range and speed following under heavy loads. Experimental results show the effectiveness of the proposed method.  相似文献   

16.
李香萍 《电子测量技术》2007,30(11):170-172
人工神经网络通过学习可以实现对输入向量的分类,也就是说,对于经过训练的神经网络,每输入一个矢量,人工神经网络输出一个该矢量所属类别的标号,神经网络的这种分类作用可以运用到说话人识别中.本文在介绍人工神经网络实现对输入向量分类原理的基础上,通过MATLAB实现了基于神经网络学习向量量化方法(LVQ)的说话人识别实验,取得了较为满意的结果.  相似文献   

17.
This paper addresses the problem of controlling the speed of a permanent-magnet stepper motor assumed to operate in a high-performance drives environment. An artificial neural network (ANN) control scheme which uses continual online random training (with no offline training) to simultaneously identify and adaptively control the speed of the stepper motor is proposed. The control scheme utilizes two three-layer feedforward ANNs: (1) a tracker identification neural network which captures the nonlinear dynamics of the motor over any arbitrary time interval in its range of operation; and (2) a controller neural network to provide the necessary control actions to achieve trajectory tracking of the motor speed. The inputs to the controller neural network are not constructed from the actual motor/load dynamics, but as a feedback signal, from the estimated state variables of the motor supplied by the neural identifier and the reference trajectory to be tracked by the actual speed. A full nonlinear model (with no simplifying assumptions) is used to model the motor dynamics, and to the best of the authors' knowledge this represents the first such attempt for this device. This paper also makes use of a very realistic and practical scheme to estimate and adaptively learn the noise content in the speed-load torque characteristic of the motor. Simulations reveal that the neural controller adapts and generalizes its learning rate to a wide variety of loads, in addition to providing the necessary abstraction when measurements are contaminated with noise  相似文献   

18.
基于BP人工神经网络的绝缘子泄漏电流预测   总被引:5,自引:1,他引:5  
外绝缘泄漏电流和绝缘子的污闪过程存在密切的对应关系,相对湿度是影响泄漏电流产生和发展的关键因素之一。首先对两种常用悬式绝缘子进行人工污秽试验,利用泄漏电流测量系统记录其在运行电压作用下、不同相对湿度时的泄漏电流波形并对此进行分析;采用BP人工神经网络的方法,建立了不同湿度下的泄漏电流最大值之间的对应关系;选择Levenberg-Marquardt快速学习算法对建立的BP神经网络进行训练。利用部分试验数据进行的验证以及采用不同方法获得的泄漏电流随相对湿度变化曲线均表明,使用该神经网络来建立不同表面受潮状态时泄漏电流最大值之间的关系是准确有效的。  相似文献   

19.
在分析交流异步电动机数学模型的基础上,利用直接多步预测控制方法,设计了一种动态神经网络电机速度控制器,其中神经网络采用扩展卡尔曼滤波方法在线训练。仿真结果表明,该控制器具有良好的动、静态特性,并且在电机参数和负载发生变化的情况下效果依然理想,为实际电机控制系统的设计和调试提供了新的思路。  相似文献   

20.
采用神经网络和专家系统的变电站故障诊断系统   总被引:7,自引:1,他引:7  
介绍了采用ANN和ES的变电站故障诊断系统,充分利用ES的推理能力和ANN的学习能力。系统首先采用ES对故障报警信息进行预处理,再用ANN方法确定故障情况,最后利用ES评价保护和开关的动作情况。ANN采用RBF网络,提高了训练速度和诊断能力;训练样本包括用ES自动生成基本故障样本,以及无确定规则的特殊样本,提高了系统管理样本的能力。本系统故障诊断快速,动作评价可靠,可减轻运行人员的工作量。  相似文献   

设为首页 | 免责声明 | 关于勤云 | 加入收藏

Copyright©北京勤云科技发展有限公司  京ICP备09084417号