NEURAL NETWORKS PREDICTION FOR SEISMIC RESPONSE OF STRUCTURE UNDER THE LEVENBERG-MARQUARDT ALGORITHM

Objective To investigate the prediction effect of neural networks for seismic response of structure under the Levenberg Marquardt(LM) algorithm. Results Based on identification and prediction ability of neural networks for nonlinear systems, and combined with LM algorithm, a multi layer forward networks is adopted to predict the seismic responses of structure. The networks is trained in batch by the shaking table test data of three floor reinforced concrete structure firstly, then the seismic responses of structure are predicted under the unused excitation data, and the predict responses are compared with the experiment responses. The error curves between the prediction and the experimental results show the efficiency of the method. Conclusion LM algorithm has very good convergence rate, and the neural networks can predict the seismic response of the structure well.

Combinatorial Optimization Based Analog Circuit Fault Diagnosis with Back Propagation Neural Network

Electronic components' reliability has become the key of the complex system mission execution. Analog circuit is an important part of electronic components. Its fault diagnosis is far more challenging than that of digital circuit. Simulations and applications have shown that the methods based on BP neural network are effective in analog circuit fault diagnosis. Aiming at the tolerance of analog circuit,a combinatorial optimization diagnosis scheme was proposed with back propagation( BP) neural network( BPNN).The main contributions of this scheme included two parts:( 1) the random tolerance samples were added into the nominal training samples to establish new training samples,which were used to train the BP neural network based diagnosis model;( 2) the initial weights of the BP neural network were optimized by genetic algorithm( GA) to avoid local minima,and the BP neural network was tuned with Levenberg-Marquardt algorithm( LMA) in the local solution space to look for the optimum solution or approximate optimal solutions. The experimental results show preliminarily that the scheme substantially improves the whole learning process approximation and generalization ability,and effectively promotes analog circuit fault diagnosis performance based on BPNN.

Levenberg-Marquardt神经网络在煤矿作业人员人因可靠性评价中应用研究

依据人因可靠性原理、事故致因理论,结合煤矿生产系统的特点,提出了观测可靠度的概念,确立了一系列便于统计和赋值的人因可靠性评价指标.针对人因失误事件过程的动态性、复杂性以及数据的不完整性,利用BP神经网络对非线性动态系统的自学习性和自适应性的特点,建立了基于BP神经网络的煤矿作业人员人因可靠性评价模型.运用Levenberg-Marquardt算法改进的BP神经网络,克服了收敛速度慢,容易陷入局部极小点的缺点,提高了预测精度和稳定性.对于岗位工龄短或有效记录不足的煤矿作业人员,采用BP神经网络模型进行了人因可靠性评价.评价结果表明,基于BP神经网络的煤矿作业人员人因可靠性评价方法具有较好的适用性和可行性.

基于Levenberg-Marquardt算法和最小二乘方法的小波网络混合学习算法

本文针对小波网络现有学习算法的不足 ,把 L evenberg- Marquardt算法 (简称 L M算法 )和最小二乘算法有机地结合在一起 ,提出了一种新的小波网络混合学习算法 .在该混合算法中 L M算法用来训练小波网络的非线性参数 ,而最小二乘算法用来训练线性参数 .最后以辩识一个混沌系统为例进行了数值仿真 ,并与改进的 BP算法和单纯 L M算法进行了比较 。

基于Levenberg-Marquardt神经网络的复合材料力学性能预测

本文提出将基于Levenberg-Marquardt算法的前向多层神经网络用于预测复合材料的力学性能,该方法通过利用二阶导数信息,可以提高收敛速度和增强网络的泛化性能。以麦秆增强复合板材为例,建立成型温度、成型压力、纤维含量和保温时间四个影响因子到拉伸强度和冲击韧性的非线性映射。仿真结果表明,所建神经网络模型具有较好的学习和泛化能力,在预测力学性能中效果较好。最后利用该模型优化模压成型的工艺参数,找出最佳工艺参数的范围。

Levenberg-Marquardt算法入侵检测系统

本文针对传统BP神经网络算法学习速度慢、收敛性较差的问题,在Windows操作系统下,利用Levenberg-Marquardt算法进行改进,将优化后的LM算法运用到主机入侵检测中去,建立LMBP-HIDS入侵检测系统模型.实验结果表明,运用Levenberg-Marquardt优化算法进行主机入侵检测,改善了传统模型收敛速度慢、易陷入局部最小点、计算量大的缺点,可以较好地提高学习速率,缩短训练过程.

基于Levenberg-Marquardt神经网络的企业资信评估方法研究

企业资信评估问题是一个复杂的非线性问题,而神经网络技术可实现非线性关系的隐式表达。文章提出将基于Levenberg-Marquardt算法的多层前馈型神经网络用于资信评估,并通过MATLAB软件及其神经网络工具对其进行仿真计算。实验结果表明,企业资信神经网络评估模型收敛速度快,准确率较高,具有一定的实用价值。

基于Levenberg-Marquardt算法的胃脘痛BP神经网络辨证模型研究

目的:本文提出了一种基于Levenberg-Marquardt算法的用于胃脘痛的BP神经网络辨证模型,用于提高胃脘痛智能辨证的准确率。方法:以"中医数字化诊疗平台"的门诊临床电子病历数据作为数据集,采用Matlab作为模型仿真平台,运用Levenberg-Marquardt算法构建了胃脘痛中医智能辨证的双隐含层BP神经网络模型。结果:实验结果显示,网络模型预测"肝胃不和"和"胃阳虚"的证型准确率和诊断准确率非常高,都在95%以上。结论:该智能辨证模型能有效利用BP神经网络的自主学习能力,充分逼近中医辨证的真实面貌,表现出优秀的辨证预测能力。而且,每天在"中医数字化诊疗平台"中都有新的中医临床真实数据上传,若利用这些数据完善该智能辨证模型,有望推动中医智能辨证在中医临床辅助诊断中大规模应用。

基于Levenberg-Marquardt算法改进BP神经网络的卷烟销量预测模型研究

针对一般时间序列分析方法中预测方法的不足,采用改进的BP神经网络对卷烟销量进行预测。介绍说明改进的BP神经网络Levenberg-Marquardt算法原理,对卷烟销量数据进行归一化处理,建立卷烟销量神经网络预测模型,利用Matlab软件对数据进行训练、仿真。与实际销量进行对比分析,证明采用改进的BP神经网络预测结果准确。

Prediction of Properties in Thermomechanically Treated Cu-Cr-Zr Alloy by an Artificial Neural Network

A supervised artificial neural network (ANN) to model the nonlinear relationship between parameters of thermomechanical treatment processes with respect to hardness and conductivity properties was proposed for Cu-Cr-Zr alloy. The improved model was developed by the Levenberg-Marquardt training algorithm. A basic repository on the domain knowledge of thermomechanical treatment processes is established via sufficient data acquisition by the network. The results showed that the ANN system is an effective way and can be successfully used to predict and analyze the properties of Cu-Cr-Zr alloy.

一种LM-BP加速搜索的周跳探测与修复方法

针对传统三频周跳探测与修复方法中的不敏感、漏检以及效率较低等问题,提出一种基于莱文伯格-马夸特(LM)-反向传播(BP)神经网络加速搜索法的伪距相位组合与电离层残差组合联合周跳探测与修复方法:利用2个伪距相位组合以减少不敏感周跳数量,利用1个电离层残差组合以提高小周跳探测敏感度;在构成3个线性无关的组合观测值后,使用LM-BP加速搜索算法进行周跳探测与修复。实验结果表明,相对常规的伪距相位组合与电离层残差组合联合方法,该方法能够提高周跳探测与修复性能,可探测小至1个的周跳,探测与修复整体时效有较大提升。

An Improved Differential Evolution Trained Neural Network Scheme for Nonlinear System Identification

This paper presents an improved nonlinear system identification scheme using di？erential evolution （DE）, neural network （NN） and Levenberg Marquardt algorithm （LM）. With a view to achieve better convergence of NN weights optimization during the training, the DE and LM are used in a combined framework to train the NN. We present the convergence analysis of the DE and demonstrate the efficacy of the proposed improved system identification algorithm by exploiting the combined DE and LM training of the NN and suitably implementing it together with other system identification methods, namely NN and DE＋NN on a number of examples including a practical case study. The identification results obtained through a series of simulation studies of these methods on different nonlinear systems demonstrate that the proposed DE and LM trained NN approach to nonlinear system identification can yield better identification results in terms of time of convergence and less identification error.

Improved Neural Network Prediction on Electrochemistry Properties of AB_5-Based Alloy

A traditional neural network was improved in two ways. An improved algorithm is associated into the network in order to enhance the optimization rate and predictability of the network. Two different methods were supplied to improve the generalization of the network. With this improved neural network, the properties of the AB_5-based hydrogen-storage alloys, the initial discharge capacity and capacity retention ratios after charge-discharge cycles, were predicted. A better prediction result was obtained by using the network.

Fuzzy optimization neural network model based on LM algorithm

A new fuzzy optimization neural network model is proposed based on the Levenberg-Marquardt (LM) algorithm on account of the disadvantages of slow convergence of traditional fuzzy optimization neural network model. In this new model,the gradient descent algorithm is replaced by the LM algorithm to obtain the minimum of output errors during network training,which changes the weights adjusting equations of the network and increases the training speed. Moreover,to avoid the results yielding to local minimum,the transfer function is also revised to sigmoid function. A case study is utilized to validate this new model,and the results reveal that the new model fast training speed and better forecasting capability.

Calibration Method of Magnetometer Based on BP Neural Network

Due to the influence of processing technology and environmental factors, there are errors in attitude measurement with the three-axis magnetometer, and the change of parameters during the operation of the magnetometer in orbit will have a great impact on the measurement accuracy. This paper studies the calibration method of magnetometer based on BP neural network, which reduces the influence of model error on calibration accuracy. Firstly, the error model of the magnetometer and the structural characteristics of the BP neural network are analyzed. Secondly, the number of hidden layers and hidden nodes is optimized. To avoid the problem of slow convergence and low accuracy of basic BP algorithm, this paper uses the Levenberg Marquardt backpropagation training method to improve the training speed and prediction accuracy and realizes the on-orbit calibration of magnetometer through online training of the neural network. Finally, the effectiveness of the method is verified by numerical simulation. The results show that the neural network designed in this paper can effectively reduce the measurement error of magnetometer, while the online training can effectively reduce the error caused by the change of magnetometer parameters, and reduce the measurement error of magnetometer to less than 10 nT.

New Approaches for Image Compression Using Neural Network

An image consists of large data and requires more space in the memory. The large data results in more transmission time from transmitter to receiver. The time consumption can be reduced by using data compression techniques. In this technique, it is possible to eliminate the redundant data contained in an image. The compressed image requires less memory space and less time to transmit in the form of information from transmitter to receiver. Artificial neural net- work with feed forward back propagation technique can be used for image compression. In this paper, the Bipolar Coding Technique is proposed and implemented for image compression and obtained the better results as compared to Principal Component Analysis (PCA) technique. However, the LM algorithm is also proposed and implemented which can acts as a powerful technique for image compression. It is observed that the Bipolar Coding and LM algorithm suits the best for image compression and processing applications.

Adaptive Internal Model Control of a DC Motor Drive System Using Dynamic Neural Network

This work concerns the study of problems relating to the adaptive internal model control of DC motor in both cases conventional and neural. The most important aspects of design building blocks of adaptive internal model control are the choice of architectures, learning algorithms, and examples of learning. The choice of parametric adaptation algorithm for updating elements of the conventional adaptive internal model control shows limitations. To overcome these limitations, we chose the architectures of neural networks deduced from the conventional models and the Levenberg-marquardt during the adjustment of system parameters of the adaptive neural internal model control. The results of this latest control showed compensation for disturbance, good trajectory tracking performance and system stability.

LM-BP神经网络在大坝变形预测中的应用

为了对大坝进行切实有效的监控,需要建立一个良好的大坝预测模型。针对传统BP(Back-Propagation)神经网络存在的收敛速度慢和泛化能力弱等缺陷,利用LM-BP(Levenberg Marquardt Back Propagation)算法对大坝变形进行预测,并根据丹江口大坝1996和1997两年的变形观测数据,对大坝挠度预测结果进行分析。结果表明,所建立的LM-BP神经网络的预测精度和收敛速度明显提高。

基于LM-BP神经网络算法的模拟电路故障诊断

针对BP神经网络在模拟电路故障诊断中存在的网络学习收敛速度慢、不易获得全局最优解、诊断精度低以及网络结构不确定等缺点,采用遗传算法对BP神经网络结构、初始连接权值和阈值进行全局优选,并利用Levenberg-Marquardt算法训练BP网络以克服这些缺陷;选取ITC97中的Elliptical Filter电路作为测试电路,设置故障并进行诊断,仿真实验表明,该诊断方法能够有效诊断模拟电路中存在的故障,并且具有更高的诊断精度。

LM-BP神经网络在农业总产值预测的应用

农业生产总值是衡量一个地区农业发展水平的重要指标,农业生产总值受多方因素的影响,具有非线性的特征,为此,提出了LM-BP神经网络预测农业生产总值的模型及方法.以农作物播种面积、粮食产量、甘蔗产量、木薯产量、茶叶产量、肉类产量、水产品产量、松脂产量及油茶籽产量等与农业生产总值相关指标作为网络输入,通过广西2000 ～2012年农业生产总值数据仿真试验分析表明,LM-BP神经网络预测结果与实际值有较好的拟合度.