共查询到20条相似文献，搜索用时 171 毫秒
1.
A laser collimating system based on 2-D position sensitive detector (PSD) is presented in this paper. The working principle of PSD is depicted in detail. A calibration device was developed to check the nonlinearity errors of PSD and a multilayer feedforward neural network based on error back-propagation algorithm was used to compensate errors. With the aid of computer-based data acquisition system, an automatic dynamic measuring process was realized. A series of experiments, including comparison tests with laser interferometer, were done to evaluate the performance of the measuring system. The experimental results show that the spatial straightness errors of guide rails can be measured with high accuracy. The maximum differences between the device and laser interferometer are 0. 027 mm in Y direction, and 0. 053 mm in X direction in the measuring distance of 6 m. 相似文献
2.
In machining processes, errors of rough in dimension, shape and location lead to changes in processing quantity, and the material of a workpiece may not be uniform. For these reasons, cutting force changes in machining, making the machining system deformable. Consequently errors in workpieces may occur. This is called the error reflection phenomenon. Generally, such errors can be reduced through repeated processing while using appropriate processing quantity in each processing based on operator‘s experience.According to the theory of error reflection, the error reflection coefficient indicates the extent to which errors of rough influence errors of workpieces. It is related to several factors such as machining condition, hardness of the workpiece, etc. This non-linear relation cannot be worked out using any formula. RBF neural network can approximate a non-linear function within any precision and be trained fast. In this paper, non-linear mapping ability of a fuzzy-neural network is utilized to approximate the non-linear relation. After training of the network with swatch collection obtained in experiments, an appropriate output can be obtained when an input is given. In this way, one can get the required number of processing and the processing quantity each time from the machining condition. Angular rigidity of a machining system,hardness of workpiece, etc., can be input in a form of fuzzy values. Feasibility in solving error reflection and optimizing machining parameters with a RBF neural network is verified by a simulation test with MATLAB. 相似文献
3.
WANG Fang CHENG Shui-yuan LI Ming-jun FAN Qing CHEN Dong-sheng WANG Hai-yan ZHANG Wei 《重庆大学学报(英文版)》2010,9(3):117-123
We developed and tested an improved neural network to predict the average concentration of PM10 （particulate matter with diameter smaller than 10 μm） several hours in advance in summer in Beijing. A genetic algorithm optimization procedure for optimizing initial weights and thresholds of the neural network was also evaluated. This research was based upon the PM10 data from seven monitoring sites in Beijing urban region and meteorological observation data, which were recorded every 3 h during summer of 2002. Two neural network models were developed. Model I was built for predicting PM10 concentrations 3 h in advance while Model II for one day in advance. The predictions of both models were found to be consistent with observations. Percent errors in forecasting the numerical value were about 20%. This brings us to the conclusion that short-term fluctuations of PM10 concentrations in Beijing urban region in summer are to a large extent driven by meteorological conditions. Moreover, the predicted results of Model II were compared with the ones provided by the Models-3 Community Multiscale Air Quality （CMAQ） modeling system. The mean relative errors of both models were 0.21 and 0.26, respectively. The performance of the neural network model was similar to numerical models, when applied to short-time prediction of PM10 concentration. 相似文献
4.
Parameters optimization and nonlinearity analysis of grating eddy current displacement sensor using neural network and genetic algorithm 总被引：1，自引：0，他引：1
A grating eddy current displacement sensor （GECDS） can be used in a watertight electronic transducer to realize long range displacement or position measurement with high accuracy in difficult industry conditions. The parameters optimization of the sensor is essential for economic and efficient production. This paper proposes a method to combine an artificial neural network （ANN） and a genetic algorithm （GA） for the sensor parameters optimization. A neural network model is developed to map the complex relationship between design parameters and the nonlinearity error of the GECDS, and then a GA is used in the optimization process to determine the design parameter values, resulting in a desired minimal nonlinearity error of about 0.11%. The calculated nonlinearity error is 0.25%. These results show that the proposed method performs well for the parameters optimization of the GECDS. 相似文献
5.
This paper discusses dynamic characteristics of proton exchange membrane fuel cell (PEMFC) under rapid fluctuation of power demand. Wavelet neural network is adopted in the identification of the characteristic curve to predict the voltage. The system control scheme of the voltage and power is introduced. The corresponding schemes for voltage and power control are studied. MATLAB is used to simulate the control system. The results reveal that the adopted control schemes can produce expected effects. Corresponding anti-disturbance and robustness simulation are also carried out. The simulation results show that the implemented control schemes have better robustness and adaptability. 相似文献
6.
ZHAO Ying NAN Jun CUI Fu-yi GUO Liang 《浙江大学学报(A卷英文版)》2007,8(9):1482-1487
This paper deals with the study of a water quality forecast model through application of BP neural network technique and GUI (Graphical User Interfaces) function of MATLAB at Yuqiao reservoir in Tianjin. To overcome the shortcomings of traditional BP algorithm as being slow to converge and easy to reach extreme minimum value,the model adopts LM (Leven-berg-Marquardt) algorithm to achieve a higher speed and a lower error rate. When factors affecting the study object are identified,the reservoir's 2005 measured values are used as sample data to test the model. The number of neurons and the type of transfer functions in the hidden layer of the neural network are changed from time to time to achieve the best forecast results. Through simulation testing the model shows high efficiency in forecasting the water quality of the reservoir. 相似文献
7.
WU Xiao-juan ZHU Xin-jian CAO Guang-yi TU Heng-yong 《浙江大学学报(A卷英文版)》2007,8(9):1505-1509
The solid oxide fuel cell (SOFC) is a nonlinear system that is hard to model by conventional methods. So far,most existing models are based on conversion laws,which are too complicated to be applied to design a control system. To facilitate a valid control strategy design,this paper tries to avoid the internal complexities and presents a modelling study of SOFC per-formance by using a radial basis function (RBF) neural network based on a genetic algorithm (GA). During the process of mod-elling,the GA aims to optimize the parameters of RBF neural networks and the optimum values are regarded as the initial values of the RBF neural network parameters. The validity and accuracy of modelling are tested by simulations,whose results reveal that it is feasible to establish the model of SOFC stack by using RBF neural networks identification based on the GA. Furthermore,it is possible to design an online controller of a SOFC stack based on this GA-RBF neural network identification model. 相似文献
8.
This paper proposes a distributed second-order consensus time synchronization, which incorporates the second-order consensus algorithm into wireless sensor networks. Since local clocks may have different skews and offsets, the algorithm is designed to include offset compensation and skew compensation. The local clocks are not directly modified, thus the virtual clocks are built according to the local clocks via the compensation parameters. Each node achieves a virtual consensus clock by periodically updated compensation parameters. Finally, the effectiveness of the proposed algorithm is verified through a number of simulations in a mesh network. It is proved that the proposed algorithm has the advantage of being distributed, asymptotic convergence, and robust to new node joining. 相似文献
9.
Based on the operation data from a certain wastewater treatment plant(WWTP) in northeast China,the models of back propagation neural network ( BP NN ) and radial basis function neural network ( RBF NN ) have been designed respectively and the ability of convergence and generalization has been analyzed separately.As for BP NN, the effects of numbers of layers and nodes have been studied ; as for RBF NN, the influences of the number of nodes and the RBF‘s width have been studied. It is concluded that BP NN has converged much slowly in comparison with RBF NN. The conclusion that the RBF NN is suitable for modeling activated sludge system has been drawn. An automatically optimum design program for RBF NN has been developed, through which the RBF NN model of traditional activated sludge system has been established. 相似文献
10.
Based on minimum output energy,an improved blind multiuser detection algorithm is proposed by the use of Hopfield neural network.Compared with traditional algorithms,the proposed algorithm does not need the circuit for constraints.The resources are greatly saved and the complexity is reduced as well.The simulation results show that the performance of the improved algorithm is similar to that of the optimal multiuser detection algorithm which is not suitable for the mobile station.Compared with the traditional gradient blind multiuser detection algorithm,the convergence speed of the improved algorithm is quickened. 相似文献
11.
FENG Yan CHEN Yi-min School of Computer Engineering Science Shanghai University Shanghai P.R. China 《上海大学学报(英文版)》2006,(5)
1IntroductionAugmented reality(AR)is a newtechnique based onvirtual reality,which has attracted much attention inrecent years.AR is used to describe a system thatenhances the real world by superi mposing computer-generated information on top of it.It supp… 相似文献
12.
反向传播算法（BackPropagation）是一种有监督神经网络学习算法,但原始算法收敛速率慢,训练过程易陷入局部极小值,精度不高等问题．文中提出了一种加权和引入参数改进的神经网络BP算法,某种程度上克服了以上缺点．对文中的改进算法用VC平台编程,并利用真实数据,对大学生就业能力进行了预测．实验表明,改进算法有效,也为高校解决大学生就业能力提供了决策支持． 相似文献
13.
给出了两种神经网络设计方法,通过用这两种方法解决同一个问题,从而说明了BP算法相对于RBF算法比较粗糙,误差也比较大;而RBF算法训练简洁且学习收敛速度快,能够逼近任意非线性函数． 相似文献
14.
介绍BP神经网络的结构及相关算法,并通过实验比较不同情况下对BP神经网络的收敛速度与分类精度的影响。实验表明,合适的参数设置能提高BP神经网络算法的分类精度。 相似文献
15.
The fuzzy NN predictive control algorithm introduced in this paper uses fuzzy neural network to model the nonlinear MIMO process.
Its training method that integrates LS and BP algorithm brings quick convergence. GPC algorithm is used as the predictive
component. The fuzzy neural network has six layers, including input layer, output layer and four hidden layers. An application
to a MIMO nonlinear process (green liquor system of the recovery system in a pulp factory shows that this algorithm has better
performance than normal PID algrithm.
Project (No. 20010539) supported by Education Office of Zhejiang Province. 相似文献
16.
讨论BP神经网络的原理及其缺陷和改进方法.在MATLAB环境下,对含噪声文字符进行识别训练.仿真结果表明,网络收敛速度快,识别分类效果好. 相似文献
17.
针对BP算法在测向定位中收敛速度慢、易陷入局部极小等缺点,将模拟退火方法应用到BP神经网络中,同时结合变步长方法,利用隐层节点的动态合并与删除策略,在满足定位精度的同时使网络结构最小化,使用三层前馈网络建立了三站测向定位模型。通过仿真实验,新方法在收敛速度和有效性方面都远高于BP算法。 相似文献
18.
颜红梅 《重庆大学学报(英文版)》2003,2(1)
1. Introduction Statistics has consistently shown that heart disease is one of the leading causes of death all over the world [1]. Every year, millions of people suffer from various types of heart diseases, among which coronary heart disease, rheumatic valvular heart disease, hypertension, chronic cor pulmonale and congenital heart disease are the commonest. Significant life saving can be achieved if an accurate diagnosis decision, which is the prerequisite of a proper and timely treatment, ca… 相似文献
19.
BP算法是人工神经网络研究的一个常用方法，但从本质上说是属于局部寻优法，容易陷入局部极小点，且存在着学习速度与精度之间的矛盾；遗传算法是一种全局优化算法，具有并行计算能力．本文采用遗传算法来训练前向神经网络，建立一个基于遗传算法和BP算法的神经网络预测模型．试验结果表明它是一个成功较高的预测模型． 相似文献
20.
冀钰 《金华职业技术学院学报》2008,8(4):11-14
为了克服BP算法收敛速度慢、易陷入局部极小点的不足,提出将蚁群算法用于模拟电路故障诊断的神经网络模型学习算法。通过对实际模拟电路的仿真测试,表明该模型能有效地提高包括容差在内的多故障的模拟电路的故障诊断准确率和诊断速度,取得了令人满意的应用效果。 相似文献