基于主成分分析与BP网络的锚杆支护方案优选

巷道特征与锚杆支护之间可以看作是一种非线性映射关系,用一般的数学方法难以表达巷道支护方案与其影响因素之间的非线性映射关系.神经网络已广泛应用于锚杆支护方案优选,并取得较好的效果.基于单一神经网络预测锚杆支护方案存在一些不足,构建了主成分分析与BP网络相结合的巷道锚杆支护方案优选模型.利用主成分分析对神经网络的输入数据进行预处理,使输入数据减少且不相关,加快网络的收敛速度,并且预测精度均在90%以上.研究结果表明:将主成分分析与BP神经网络结合优选巷道的锚杆支护方案,具有很高的预测精度;与单一BP神经网络相比,提高了预测精度．     

基于神经网络的动态测量误差分解研究

在讨论神经网络方法的基础上，尝试将其应用于动态测量误差分解理论。建立了一个简单的动态测试仿真系统，分别用小波变换方法和神经网络方法对系统输出的总误差进行分解，并对两种方法的处理结果作了比较，指出了神经网络方法在动态误差分解中的实用性和优越性。     

基于神经网络趋势分析

文章在分析研究了国内外现状的基础上 ,利用神经网络的非线性处理特性 ,提出了通过神经网络预测常见机械零件剩余寿命的方法 ,用实例验证了其有效性     

基于1DDCNN和PCA信息融合的滚动轴承FLHI智能提取方法

滚动轴承故障预测方法的核心在于健康指数(HI)的构建,绝大部分已经提出的HI都是基于专家经验人工构造的,且往往只能适用于部件某一特定退化阶段的趋势分析。为解决上述问题,结合振动信号的一维特性,提出一种基于一维深度卷积神经网络(1DDCNN)结合主成分分析(PCA)的滚动轴承全寿命健康指数(FLHI)智能提取法;利用1DDCNN对原始时域信号自适应提取特征,深度挖掘能够表征研究对象健康状态的退化特征矩阵,而后利用PCA法对提取的特征矩阵进行融合,从而实现研究对象的FLHI智能提取。滚动轴承试验振动信号实测结果表明,相较于传统健康指数,FLHI在趋势性、鲁棒性和单调性方面更具有优势。     

Application of principal component-artificial neural network models for simultaneous determination of phenolic compounds by a kinetic spectrophotometric method

A multicomponent analysis method based on principal component analysis-artificial neural network models (PC-ANN) is proposed for the determination of phenolic compounds. The method relies on the oxidative coupling of phenols (phenol, 2 chlorophenol, 3-chlorophenol and 4-chlorophenol) to N,N-diethyl-p-phenylenediamine in the presence of hexacyanoferrate(III). The reaction monitored at analytical wavelength 680 nm of the dye formed. Phenols can be determined individually over the concentration range 0.1-7.0 microg ml(-1). Differences in the kinetic behavior of the four species were exploited by using PC-ANN, to resolve mixtures of phenol. After reducing the number of kinetic data using principal component analysis, an artificial neural network consisting of three layers of nodes was trained by applying a back-propagation learning rule. The optimized ANN allows the simultaneous quantitation of four analytes in mixtures with relative standard errors of prediction in the region of 5% for four species. The results show that PC-ANN is an efficient method for prediction of the four analytes.     

Network-level accident-mapping: Distance based pattern matching using artificial neural network

The objective of an accident-mapping algorithm is to snap traffic accidents onto the correct road segments. Assigning accidents onto the correct segments facilitate to robustly carry out some key analyses in accident research including the identification of accident hot-spots, network-level risk mapping and segment-level accident risk modelling. Existing risk mapping algorithms have some severe limitations: (i) they are not easily ‘transferable’ as the algorithms are specific to given accident datasets; (ii) they do not perform well in all road-network environments such as in areas of dense road network; and (iii) the methods used do not perform well in addressing inaccuracies inherent in and type of road environment. The purpose of this paper is to develop a new accident mapping algorithm based on the common variables observed in most accident databases (e.g. road name and type, direction of vehicle movement before the accident and recorded accident location). The challenges here are to: (i) develop a method that takes into account uncertainties inherent to the recorded traffic accident data and the underlying digital road network data, (ii) accurately determine the type and proportion of inaccuracies, and (iii) develop a robust algorithm that can be adapted for any accident set and road network of varying complexity. In order to overcome these challenges, a distance based pattern-matching approach is used to identify the correct road segment. This is based on vectors containing feature values that are common in the accident data and the network data. Since each feature does not contribute equally towards the identification of the correct road segments, an ANN approach using the single-layer perceptron is used to assist in “learning” the relative importance of each feature in the distance calculation and hence the correct link identification. The performance of the developed algorithm was evaluated based on a reference accident dataset from the UK confirming that the accuracy is much better than other methods.     

Reliability analysis of structures using neural network method

In order to predict the failure probability of a complicated structure, the structural responses usually need to be estimated by a numerical procedure, such as finite element method. To reduce the computational effort required for reliability analysis, response surface method could be used. However the conventional response surface method is still time consuming especially when the number of random variables is large. In this paper, an artificial neural network (ANN)-based response surface method is proposed. In this method, the relation between the random variables (input) and structural responses is established using ANN models. ANN model is then connected to a reliability method, such as first order and second moment (FORM), or Monte Carlo simulation method (MCS), to predict the failure probability. The proposed method is applied to four examples to validate its accuracy and efficiency. The obtained results show that the ANN-based response surface method is more efficient and accurate than the conventional response surface method.     

A hybrid artificial neural network method with uniform design for structural optimization

This paper presents a new hybrid artificial neural network (ANN) method for structural optimization. The method involves the selection of training datasets for establishing an ANN model by uniform design method, approximation of the objective or constraint functions by the trained ANN model and yields solutions of structural optimization problems using the sequential quadratic programming method (SQP). In the proposed method, the use of the uniform design method can improve the quality of the selected training datasets, leading to a better performance of the ANN model. As a result, the ANN dramatically reduces the number of required trained datasets, and shows a good ability to approximate the objective or constraint functions and then provides an accurate estimation of the optimum solution. It is shown through three numerical examples that the proposed method provides accurate and computationally efficient estimates of the solutions of structural optimization problems.     

基于电容测量和PCA法的两相流相浓度检测方法

介绍利用电容层析成像系统阵列传感器结构和采样特点,引入主成分分析法(PCA)求取两相流相浓度的新方法.对大量测量值样本进行统计分析后,求出用测量值第一主成分求取相浓度的经验公式,仿真及静态实验表明:两者之间有着良好的对应关系,其测量结果不受两相流流型的影响,是一种有较好应用前景的测量方法.     

Formulation optimization technique based on artificial neural network in salbutamol sulfate osmotic pump tablets

The aim of this study was to develop a formulation optimization technique in which an artificial neural network (ANN) was incorporated; 30 kinds of salbutamol sulfate osmotic pump tablets were prepared, and their dissolution tests were performed. The amounts of hydroxypropyl methylcellulose (HPMC), polyethylene glycol 1500 (PEG1500) in the coating solution, and the coat weight were selected as the causal factors. Both the average drug release rate v for the first 8 hr and the correlation coefficient r of the accumulative amount of drug released andtime were obtained as release parameters to characterize the release profiles. A set of release parameters and causal factors was used as training data for the ANN, and another set of data was used as test data. Both sets of data were fed into a computer to train the ANN. The training process of theANN was completed until a satisfactory value of error function E for the test data was obtained. The optimal formulation produced by the technique gave the satisfactory release profile since the observed results coincided well with the predicted results. These findings demonstrate that an ANN is quite useful in the optimization of pharmaceutical formulations.     

主成分分析的入侵检测方法研究

直接将入侵检测算法应用在粗糙数据上,其入侵检测分析的效率非常低.为解决该问题,提出了一种基于主成分分析的入侵检测方法.该方法通过提取网络连接中的相关信息,对它进行解码,并将解码的网络连接记录与已知的网络连接记录数据进行比较,发现记录中的变化和连接记录分布的主成分,最后将机器学习方法和主成分分析方法结合实现入侵检测.实验结果表明该方法应用到各种不同KDD99入侵检测数据集中可以有效减少学习时间、降低各种数据集的表示空间,提高入侵检测效率.     

一种基于核主成分分析和组合分类器的虹膜识别方法

提出了一种新的虹膜特征提取与识别方法,该方法利用核主成分分析(KPCA)在高维空间具有较强的特征选择能力来提取虹膜图像的纹理特征。采用了一种距离度量和支持向量机相结合的两级分类方法,前级采用欧式距离来度量图像间的相似性,若符合条件,给出分类结果,否则拒绝,并转入后一级分类器——支持向量机分类,以减少进入支持向量机的样本数目,该组合分类方法充分利用了支持向量机识别率高和距离度量速度快的优点。实验结果表明,该方法提高了虹膜识别率,是一种有效的虹膜识别方法。     

基于BP人工神经网络的混凝土强度预测

混凝土强度是结构设计中控制的主要指标,其数值决定于水灰比、胶凝材料用量、矿物掺量、外加剂用量等多种因素,常规计算混凝土强度的公式因个人理解的不同而各异,一种仿生模型—人工神经网络则能很好地解决这个难题,文中尝试用人工神经网络对不同混凝土强度进行预测,结果表明此模型的可靠度很高,可以用以优化混凝土的试配,节约大量的时间、人力、物力和财力.     

Novel interpretable mechanism of neural networks based on network decoupling method

The lack of interpretability of the neural network algorithm has become the bottleneck of its wide application. We propose a general mathematical framework, which couples the complex structure of the system with the nonlinear activation function to explore the decoupled dimension reduction method of high-dimensional system and reveal the calculation mechanism of the neural network. We apply our framework to some network models and a real system of the whole neuron map of Caenorhabditis elegans. Result shows that a simple linear mapping relationship exists between network structure and network behavior in the neural network with high-dimensional and nonlinear characteristics. Our simulation and theoretical results fully demonstrate this interesting phenomenon. Our new interpretation mechanism provides not only the potential mathematical calculation principle of neural network but also an effective way to accurately match and predict human brain or animal activities, which can further expand and enrich the interpretable mechanism of artificial neural network in the future.     

基于人工神经网络的藏式结构有限元模型修正

针对典型藏式传统建筑年代久远、建造过程无设计图纸、存在太多不确定性,通过有限元数值分析所得结果与实验结果不能较好吻合问题,建立所测结构的有限元模型,并通过人工神经网络方法,以实测结构模态参数为目标对典型藏式结构的有限元模型中部分不确定因素—梁及雀替的等效变截面梁高、材料密度及弹性模量进行修正,得到更接近真实状态的有限元模型。该模型对该典型藏式结构的损伤识别、可靠度评估具有重要意义。     

Prediction of hopper discharge rate using combined discrete element method and artificial neural network

An Artificial Neural Network (ANN) was developed to predict the mass discharge rate from conical hoppers. By employing Discrete Element Method (DEM), numerically simulated flow rate data from different internal angles (20°–80°) hoppers were used to train the model. Multi-component particle systems (binary and ternary) were simulated and mass discharge rate was estimated by varying different parameters such as hopper internal angle, bulk density, mean diameter, coefficient of friction (particle-particle and particle-wall) and coefficient of restitution (particle-particle and particle-wall). The training of ANN was accomplished by feed forward back propagation algorithm. For validation of ANN model, the authors carried out 22 experimental tests on different mixtures (having different mean diameter) of spherical glass beads from different angle conical hoppers (60° and 80°). It was found that mass discharge rate predicted by the developed neural network model is in a good agreement with the experimental discharge rate. Percentage error predicted by ANN model was less than ±13%. Furthermore, the developed ANN model was also compared with existing correlations and showed a good agreement.     

Degrees of freedom for the residuals of a principal component analysis — A clarification

Various conflicting proposals for degrees of freedom associated with the residuals of a principal component analysis have been published in the chemometrics-oriented literature. Here, a detailed derivation is given of the ‘standard’ formula from statistics. This derivation intends to be more accessible to chemometricians than, for example, the impeccable, but condensed proof that was published by John Mandel in a relatively unknown paper (J. Res. Nat. Bur. Stand., 74B (1970) 149–154). The derivation is presented in the form of a two-stage recipe that also appears to apply to more complex multiway models like the ones considered by Ceulemans and Kiers (Br. J. Math. Stat. Psych., 59 (2006) 133–150).     

Hybrid artificial neural network based on BP-PLSR and its application in development of soft sensors

A novel hybrid artificial neural network (HANN) integrating error back propagation algorithm (BP) with partial least square regression (PLSR) was proposed to overcome two main flaws of artificial neural network (ANN), i.e. tendency to overfitting and difficulty to determine the optimal number of the hidden nodes. Firstly, single-hidden-layer network consisting of an input layer, a single hidden layer and an output layer is selected by HANN. The number of the hidden-layer neurons is determined according to the number of the modeling samples and the number of the neural network parameters. Secondly, BP is employed to train ANN, and then the hidden layer is applied to carry out the nonlinear transformation for independent variables. Thirdly, the inverse function of the output-layer node activation function is applied to calculate the expectation of the output-layer node input, and PLSR is employed to identify PLS components from the nonlinear transformed variables, remove the correlation among the nonlinear transformed variables and obtain the optimal relationship model of the nonlinear transformed variables with the expectation of the output-layer node input. Thus, the HANN model is developed. Further, HANN was employed to develop naphtha dry point soft sensor and the most important intermediate product concentration (i.e. 4-carboxybenzaldehyde concentration) soft sensor in p-xylene (PX) oxidation reaction due to the fact that there exist many factors having nonlinear effect on them and significant correlation among their factors. The results of two HANN applications show that HANN overcomes overfitting and has the robust character. And, the predicted squared relative errors of two optimal HANN models are all lower than those of two optimal ANN models and the mean predicted squared relative errors of HANN are lower than those of ANN in two applications.     

基于主成分分析的多光谱相机灵敏度优化

研究了基于主成分分析的多通道光谱图像获取硬件系统即多光谱相机的灵敏度优化问题。利用多维向量空间理论和主成分分析法,系统讨论了多光谱获取系统优化灵敏度的理论和方法。提出灵敏度优化向量的概念,将滤光片透过率优化和光源辐射谱优化两种方法统一起来。利用四种灵敏度优化向量进行了仿真试验,并给出了在主成分分析算法下的实验仿真结果。结论是：多光谱系统灵敏度优化向量的正交化设计是系统光谱图像获取的必要要求;窄带灵敏度中,交叠的灵敏度优化向量具有更好的光谱反射率信息获取能力;在有限数目的宽带滤色片中,挑选滤色片透过率向量可以得到较好的多光谱相机的灵敏度向量。