基于粒子群-BP神经网络算法的电价预测

为了解决现有电价预测中BP神经网络法对初始权值敏感、易陷入局部最小值和收敛速度慢等问题,在神经网络训练中引入基于全局随机优化思想的粒子群优化(PSO)算法,先利用PSO优化BP神经网络的初始权值,然后采用神经网络完成给定精度的学习,建立了粒子群-BP神经网络模型.与传统BP神经网络、粒子群广义神经网络相比,该方法收敛速度快、所需历史数据少、预报精度高,可用于电力系统的短期电价预测.     

基于粗糙集和主成分分析结合的短期负荷预测

采用神经网络进行负荷预测,为了进一步减少输入变量的个数,减小网络结构,在基于粗糙集理论约简的基础上,采用能消除变量间相关性的主成分分析法对负荷影响因素约简,并且通过实例研究证明了此法的有效性。     

Application of generalized regression neural network on fast 3D reconstruction

Over the past decade,robots have been appearingin the operating rooms.With the robotic system assis-tance,operations have become lesser invasion.Roboticsurgery requires the use of computer imaging to diag-nose and perform the operation.A three dimension(3…     

Risk based security assessment of power system using generalized regression neural network with feature extraction

A comprehensive risk based security assessment which includes low voltage, line overload and voltage collapse was presented using a relatively new neural network technique called as the generalized regression neural network (GRNN) with incorporation of feature extraction method using principle component analysis. In the risk based security assessment formulation, the failure rate associated to weather condition of each line was used to compute the probability of line outage for a given weather condition and the extent of security violation was represented by a severity function. For low voltage and line overload, continuous severity function was considered due to its ability to zoom in into the effect of near violating contingency. New severity function for voltage collapse using the voltage collapse prediction index was proposed. To reduce the computational burden, a new contingency screening method was proposed using the risk factor so as to select the critical line outages. The risk based security assessment method using GRNN was implemented on a large scale 87-bus power system and the results show that the risk prediction results obtained using GRNN with the incorporation of principal component analysis give better performance in terms of accuracy.     

基于广义回归神经网络的微电路工艺设备表征

为了使用较少的工艺试验建立更高精度的模型描述微电路工艺的复杂性与非线性,将神经网络技术与统计试验设计相结合代替传统的统计方法应用于微电路热氧化工艺设备的表征．通过试验设计安排15轮试验,然后基于广义回归神经网络建立了以氧化膜厚以及均匀性为目标值的热氧化工艺模型,最后利用信噪比函数对模型的拟合以及预测能力进行了验证与比较分析．结果表明,该方法建立的模型可用于工艺表征与控制．所讨论的方法可用于其他微电路工艺设备的表征．     

基于MPCA-RBFNN的神经网络在中长期电力负荷预测中的应用

利用改进的主成分分析(MPCA)方法对径向基函数神经网络输入空间进行重构,在降低输入空间维数的同时克服了传统主成分分析法的缺点,缩小了网络的结构,达到了提高网络泛化能力的目的。通过某省实例验证了该方法的有效性。     

A new grey forecasting model based on BP neural network and Markov chain

A new grey forecasting model based on BP neural network and Markov chain was proposed. In order to combine the grey forecasting model with neural network, an important theorem that the grey differential equation is equivalent to the time response model, was proved by analyzing the features of grey forecasting model(GM(1,1)). Based on this, the differential equation parameters were included in the network when the BP neural network was constructed, and the neural network was trained by extracting samples from grey system’s known data. When BP network was converged, the whitened grey differential equation parameters were extracted and then the grey neural network forecasting model (GNNM(1,1)) was built. In order to reduce stochastic phenomenon in GNNM(1,1), the state transition probability between two states was defined and the Markov transition matrix was established by building the residual sequences between grey forecasting and actual value. Thus, the new grey forecasting model(MNNGM(1,1)) was proposed by combining Markov chain with GNNM(1,1). Based on the above discussion, three different approaches were put forward for forecasting China electricity demands. By comparing GM(1, 1) and GNNM(1,1) with the proposed model, the results indicate that the absolute mean error of MNNGM(1,1) is about 0.4 times of GNNM(1,1) and 0.2 times of GM(1,1), and the mean square error of MNNGM(1,1) is about 0.25 times of GNNM(1,1) and 0.1 times of GM(1,1).     

神经网络在股票价格预测中的应用

如何对股票价格进行预测是投资者所关注的话题，采用BP神经网络对股票价格进行预测，提出了将股票市场上所采用的技术指标作为神经网络输入变量，利用逐步回归方法筛选出影响股票价格涨跌的变量，从而建立起神经网络模型，研究结果表明，该方法具有一定的预测能力。     

基于神经网络的有效停车泊位预测方法研究

对基于神经网络的有效停车泊位预测方法进行研究,通过调查及采集商业中心区停车场停放车辆的实时数量信息,建立相应的神经网络模型,并运用MATLAB仿真分析软件实现实时有效停车泊位预测,最后对误差结果进行分析和解释。     

基于RBF神经网络的交通流预测

针对交通模型是一个非线性、不确定的复杂动力学系统,难以用精确模型来表达的问题,采用RBF神经网络建立交通流预测模型,具有较强的局部泛化能力,收敛速度快,克服了BP神经网络收敛速度慢、易陷入局部极小的缺点．实例仿真研究表明,该方法预测效果较好．     

基于主成分分析和支持向量机的道路网短时交通流量预测

将主成分分析和支持向量机回归相结合,进行道路网多断面的短时交通流量预测研究。首先,整理分析路网中多个断面交通流量数据进行主成分分析,得到主成分数据序列;其次,根据主成分数据序列建立训练集训练支持向量机,并利用遗传算法优化参数;最后,输入支持向量机所需数据,得到主成分预测结果,转化为断面交通流量数据,从而预测道路网短时交通流量。采用城市快速路多断面数据进行实例分析,结果表明,该模型比单一断面预测方法的效果更好。     

基于人工神经网络的鲁棒短期负荷预测方法

提出一种用神经网络设计提前一天的短期负荷预测系统的方法.在对神经网络进行训练前,先通过一种简单的方法对数据进行了预处理,以使设计的系统具有处理由于突发事件等因素引起负荷突然变化的能力.用山东省电网2003年的负荷数据进行试验,试验结果表明方法的适用性.     

基于小波神经网络的房地产价格指数预测研究

要对非线性趋势房地产价格指数进行预测,就必须利用模拟非线性的模型。应用BP神经网络来对房地产价格指数进行预测,精度和收敛的速度都不是很理想,这主要是因为BP神经网络本身存在着缺陷。为了克服BP神经网络的缺陷,本文将小波变换和BP神经网络结合起来,运用小波神经网络来对房地产价格指数进行预测,并与BP网络的预测结果进行了比较,最后发现用小波神经网络进行经济预测可以达到很好的效果。     

基于主成分分析的研究与开发活动绩效评价

地区持续、健康发展的主要推动力之一是研究与试验发展（R＆D）活动。研究证实：主成分分析方法作为一种多元统计方法适合对R＆D活动进行评价,其评价结果在很大程度上能避免人为因素影响,比较客观地反映实际情况,并为科技管理部门提供相应政策建议。搞好研究与试验发展活动的评价工作对促进一个地区的发展有很强的理论和现实意义。     

基于改进广义回归神经网络的网络安全态势预测

针对网络安全态势精确预测,提出一种基于改进广义回归神经网络的预测方法,以改善网络安全态势预测精度.利用滑动时间窗口方法将各个离散时间监测点的网络安全态势值构造成部分线性相关的多元回归数据序列,以其做为样本集输入到改进广义回归神经网络加以训练,进而得到网络安全态势预测模型.在改进广义回归神经网络训练过程中,利用粒子群算法...     

基于多尺度卷积神经网络的短期电力负荷预测

In order to improve the accuracy of short-term load forecasting of power system, a multi-scale information fusion convolutional neural network(MS-ConvNet)model based on deep learning technology was proposed. A full convolution network structure and causal logic constraints were introduced to enhance the expression of time series features; a multi-scale convolution was utilized to extract the relationship among time domain data of different lengths for obtaining more abundant series features; a residual network structure was designed to increase the network depth, which increased the acceptance domain of outputneurons and enhanced the prediction accuracy. The results show that the accuracy and stability of MS-ConvNet model is better than those of multi-layer perceptron machine, long-short term memory network and gated recurrent unit network, indicating that the as-proposed model has a good application prospect in power load forecasting.     

基于模糊集的电力系统神经网络负荷预报研究

提出了电力系统短期负荷预报基于模糊集的神经网络方法 .该方法计及了天气和日期特征量 ,具有训练时间短预测精度高的特点 .采用两种学习算法 ,依据模糊集概念用某地区电网实际数据建立样本集后 ,对ANN进行了训练 ,通过分析比较得出了优化模型 .计算事例表明用该方法是可行和有效的     

基于主成分分析的神经网络评价模型研究

根据供电企业的特点,建立了适用于评价供电企业营销效果的指标体系,综合运用主成分分析法和BP神经网络方法建立模型,对供电企业的营销效果进行了模拟综合评价。     

BP神经网络在回归分析中的应用研究

通过实例比较，分析了神经网络在回归分析和预测中的应用。与传统的回归方法相比在某些方面有一定的优势。     

Short-term load forecasting based on fuzzy neural network

The fuzzy neural network is applied to the short-term load forecasting. The fuzzy rules and fuzzy membership functions of the network are obtained through fuzzy neural network learming. Three inference algorithms, i.e. themultiplicative inference, the maximum inference and the minimum inference, are used for comparison. The learningalgorithms corresponding to the inference methods are derived from back-propagation algorithm. To validate the fuzzyneural network model, the network is used to Predict short-term load by compaing the network output against the realload data from a local power system supplying electricity to a large steel manufacturer. The experimental results aresatisfactory.