基于进化神经元算法的堡镇隧道软弱围岩施工弹塑性智能位移反分析

结合宜万铁路堡镇隧道的施工,将BP神经网络和遗传算法引入特长隧道软岩段的施工位移反分析,采用遗传算法自动搜索BP神经网络训练效果最优的参数,建立起反映围岩变形与岩体物理力学参数及初始地应力之间高度非线性、不确定的GA-BP智能模型,然后采用遗传算法在岩体物理力学参数和初始地应力取值范围内,搜索BP神经网络预测围岩变形与实测围岩变形最接近的参数组合,取得反演获得的岩体物理力学参数和初始地应力.从堡镇隧道应用结果来看,这种进化神经元算法反演结果可以满足隧道施工的需要,并为类似工程提供了借鉴.     

Operating Rule Classification System of Water Supply Reservoir Based on Learning Classifier System

An operating rule classification system based on lesrning classifier system (LCS), which learns through credit assignment (bucket brigade algorithm, BBA) and rule discovery (genetic algorithm, GA), is established to extract water-supply reservoir operating rules. The proposed system acquires an online identification rate of 95% for training samples and an offline rate of 85% for testing samples in a case study. The performances of the rule classification system are discussed from the rationality of the obtained rules, the impact of training samples on rule extraction, and a comparison between the rule classification system and the artificial neural network (ANN). The results indicate that the LCS is feasible and effective for the system to obtain the reservoir supply operating rules.     

NEURAL NETWORK TRAINING WITH PARALLEL PARTICLE SWARM OPTIMIZER

Feed forward neural net works such as multi-layer perceptron,radial basis function neural net-works,have been widely applied to classification,function approxi mation and data mining.Evolu-tionary computation has been explored to train neu-ral net works as a very promising and competitive al-ternative learning method,because it has potentialto produce global mini mum in the weight space.Recently,an emerging evolutionary computationtechnique,Particle Swar m Opti mization(PSO)be-comes a hot to…     

基于多智能体局部寻优的粒子群优化算法

为了提高粒子群算法的收敛速度和全局寻优能力,用多智能体遗传算法对粒子群算法当前搜索到的全局极值进行局部寻优．用搜索到的更好的解在下一次迭代中引导粒子进行搜索从而获得更快的收敛速度和更好的全局收敛性。对函数优化和神经网络训练的仿真实验表明．此算法能更快的收敛到全局最优解。     

L-M神经网络算法在汽轮发电机组故障诊断中的应用

针对汽轮发电机组的故障诊断,采用Levenberg-Marquardt算法建立多层前向人工神经网络,采用改进算法训练网络,克服了传统BP算法收敛速度慢,易陷入局部最小的缺陷.就BP网络的不足,提出了一种改进的BP神经网络模型,并使用L-M算法用于汽轮发电机组故障的诊断.经理论和实践证明:该方法有效地提高了故障诊断的精度和可靠度,为旋转机械故障诊断提供了有效方法.     

优化设计求解的遗传-神经网络新算法研究

提出并研究了一种优化设计求解的遗传神经网络新算法,该算法综合了遗传算法的全局性和神经网络的并行快速性等特点,可克服遗传算法最终进化至最优解较慢和神经网络易陷入局部解的缺陷,具有较好的全局性和收敛速度     

基于多层前馈神经网络的车牌提取方法

文中提出一种采用三层前馈神经网络提取车牌的方法。该方法是一种基于纹理分析的图像分割算法,适合于彩色及灰度图像。实验表明,该方法能准确地提取图像中的车牌。     

遗传算法优化的模糊神经网络在故障诊断中的应用

本文针对船舶柴油机故障诊断系统提出了一种基于遗传算法优化训练的模糊神经网络诊断方法,介绍了这种模糊神经网络故障诊断系统的结构及其参数形式,通过遗传优化算法对它的权值和阈值进行了学习优化训练。这种方法可以有效地避免通常所选BP算法训练易陷于局部极值的问题,最后将该遗传算法优化训练的模糊神经网络系统应用到船舶柴油机的故障诊断中,通过仿真研究,说明了该方法的有效性。     

A Novel Evolutionary Feedforward Neural Network with Artificial Immunology

A hybrid algorithm to design the multi-layer feedforward neural network was proposed. Evolutionary programming is used to design the network that makes the training process tending to global optima. Artificial im-munology combined with simulated annealing algorithm is used to specify the initial weight vectors, therefore im-proves the probabiligy of training algorithm to converge to global optima. The applications of the neural network in the modulation-style recognition of analog modulated rader signals demonstrate the good performance of the network.     

一种新的多模式对模糊联想记忆自适应学习规则

本文给出了模糊联想记忆神经网络联想输出误差函数的一种梯度计算方法,成功地把误差逆传播梯度下降搜索技术应用于该网络的训练中,提出一种新的多模式对模糊联想记忆的学习规则,计算机模拟表明该规则是十分有效的。     

铁路客流量预测分析与研究

铁路客流量预测与分析对铁路部门采取有效的应对措施具有十分重要的意义,分别应用基本的神经网络和遗传算法优化BP神经网络对客流量进行了预测,建立铁路客流量网络预测模型.分别利用以前客流量的数据对2011年和2012年的客流量做了预测验证,并对2013年的客流量做了预测,结果表明利用遗传算法优化BP神经网络得到的预测数据和实际的基本相符,该预测算法应用到客流量的预测中效果良好,具有很好的应用和推广的前景.     

基于遗传算法的神经网络在道路收费中的应用

道路拥挤收费被认为是城市交通管理和控制的一个有效方法,国内外不少学者提出了模型和相应的计算方法。文章根据弹性需求下的拥挤收费模型,利用BP神经网络算法模拟路段流量和路段收费之间的对应关系,并在神经网络的训练过程中引入遗传算法,加速神经网络的全局收敛。通过训练后的神经网络制定收费,可以使得各路段流量基本达到最优路段流量的要求,并通过实例证明了该算法的有效性。     

Adaptive Identification of Logging Lithology Based on VPSO-ENN Hybrid Algorithm

Particle swarm optimization (PSO) was modified by variation method of particle velocity, and a variation PSO (VPSO) algorithm was proposed to overcome the shortcomings of PSO, such as premature convergence and local optimization. The VPSO algorithm is combined with Elman neural network (ENN) to form a VPSO-ENN hybrid algorithm. Compared with the hybrid algorithm of genetic algorithm (GA) and BP neural network (GA-BP), VPSO-ENN has less adjustable parameters, faster convergence speed and higher identification precision in the numerical experiment. A system for identifying logging parameters was established based on VPSO-ENN. The results of an engineering case indicate that the intelligent identification system is effective in the lithology identification.     

Forming path optimization for press bending of aluminum alloy aircraft integral panel

Because of the light weight, high stiffness and high structural efficiency, aluminium alloy integral panels are widely used on modern aircrafts. Press bend forming has many advantages, and it becomes a significant technique in aircraft manufacturing field. In order to design the press bend forming path for aircraft integral panels, we propose a novel optimization method which integrates the finite element method (FEM) equivalent model based on our previous study, the artificial neural network response surface, and the genetic algorithm. First, a multi-step press bend forming FEM equivalent model is established, with which the FEM experiments designed with Taguchi method are performed. Then, the back-propagation (BP) neural network response surface is developed with the sample data from the FEM experiments. Further more, genetic algorithm (GA) is applied with the neural network response surface as the objective function. Finally, experimental and simulation verifications are carried out on a single stiffener specimen. The forming error of the panel formed with the optimal path is only 5.37% and the calculating efficiency has been improved by 90.64%. Therefore, this novel optimization method is quite efficient and indispensable for the press bend forming path designing.     

基于遗传算法与小波神经网络的客流预测研究

针对轨道交通短时客流具有动态性、非线性、不确定性的特点,提出一种基于遗传算法与小波神经网络的轨道交通短时客流预测方法.该方法利用具有全局搜索最优的遗传算法优化小波神经网络,有效的避免了神经网络易陷入局部最小值的缺陷.在分析轨道交通短时客流的特征上,利用实测数据对模型进行验证.结果表明,相比遗传算法优化的BP神经网络模型,单一的小波神经网络模型其预测精度更高,误差更小,能在实际中应用.     

基于遗传BP神经网络的城市物流需求量预测

结合遗传算法与BP神经网络算法预测城市物流需求量,通过算例对比证明了遗传BP神经网络算法在预测的精度与收敛速度上均优于单一算法.基于物流业的广泛性提出采用3种物流需求量作为网络的输出指标,提高了物流需求量预测的广度与可信度,并提出了一种连续预测未来数年物流需求量的方法以便于运用于实际决策之中.     

基于RBFNN的铁路混凝土桥梁构件状态评估

介绍了RBF神经网络模型的结构和训练算法,提出了既有铁路桥梁构件的综合状态评估模型,根据RBF神经网络的自适应性和学习能力,成功的将RBF神经网络应用于既有铁路桥梁构件综合状态评估中去,并给出了便于获取,且能全面准确反映桥梁实际工作状态的输入参数.以某铁路线的若干组实测数据对RBF神经网络进行训练和测试,系统输出与期望输出吻合较好,证明了RBF神经网络评估既有桥梁构件综合状态的准确性、有效性和稳定性.     

基于进化规划的BP神经网络学习

通过对将传统的BP算法和遗传算法应用到BP神经网络的学习的研究和分析,指出它们存在的缺陷。提出一个改进的进化规划算法,并将其应用于BP神经网络的权值优化。取XOR问题和4奇偶性问题的实验对传统的进化规划算法和改进的进化规划算法进行实验对比。实验结果表明,本文中提出的改进的进化规划算法优于前2个算法。     

基于头脑风暴优化的PCNN路面裂缝分割算法

为提升裂缝检测的分割精度和鲁棒性,基于头脑风暴优化（brainstorming optimization,BSO）和脉冲耦合神经网络（pulse coupled neural network,PCNN）,提出了一种路面裂缝图像分割算法（BSO-PCNN）. 该算法采用最大熵准则作为BSO算法的适应度函数,并依据适应度值决定参与次轮迭代的个体;BSO具有强收敛性,可快速确定最优个体解;结合图像特征,获得PCNN模型的最优参数,将其代入PCNN模型实现对裂缝图像的分割. 试验结果表明:算法可在20次迭代内取得不同类型路面裂缝图像的最大适应值,从而确定最佳分割参数;与Sobel边缘检测算法、PCNN图像分割算法、基于最大熵的遗传算法（genetic algorithm based on the maximun entropy of the histogram,GA-KSW）、基于遗传算法参数优化的PCNN分割算法（genetic algorithm based on the pulse coupled neural network,GA-PCNN）相比,BSO-PCNN算法取得了0.9924的区域一致性与0.0900的区域对比度.      

Feature Selection for SVM Classifiers Based on Discretization

The rough sets and Boolean reasoning based discretization approach （RSBRA） is not suitable for feature selection for machine learning algorithms such as neural network or SVM because the information loss due to discretization is large. A modified RSBRA for feature selection was proposed and evaluated with SVM classifiers. In the presented algorithm, the level of consistency, coined from the rough sets theory, is introduced to substitute the stop criterion of circulation of the RSBRA, which maintains the fidelity of the training set after discretization. The experimental results show the modified algorithm has better predictive accuracy and less training time than the original RSBRA.