基于径向基神经网络的桥梁有限元模型修正

基于某预应力混凝土大跨刚构-连续梁桥的ANSYS有限元模型,提出一种基于径向基神经网络的有限元模型修正方法。该方法以不同设计参数条件下有限元模型模态分析频率作为输入向量,以对应的桥面单元、中墩、边墩的弹性模量、密度等设计参数修正值作为输出向量,利用径向基神经网络来逼近两者之间的非线性映射关系。结合该桥梁结构健康监测系统中加速度传感器监测的桥梁结构动力反应的加速度数据,利用神经网络的泛化特性,直接计算出有限元模型设计参数的修正值。研究结果表明:修正后的有限元模型能更真实地反映结构的物理状态,较好地反映该桥梁结构的真实动力特性。     

基于径向基函数神经网络模型的砂土液化概率判别方法

以国内外25次大地震中的344组场地液化实测资料为基础,通过径向基函数神经网络模型的训练和检验,分析了修正标准贯入击数N1与饱和砂土抗液化强度之间的非线性关系,建立了饱和砂土液化极限状态曲线或抗液化强度临界曲线经验公式。经统计分析,给出了液化和非液化的概率密度函数以及抗液化安全系数与液化概率之间的经验公式,最后导出了具有概率意义的饱和砂土抗液化强度经验公式。当液化概率水平为50%时,即等价于传统的确定性砂土液化判别,该方法预测液化和非液化的可靠性分别为90.4%和81.2%,具有较高的可靠性。本文提出的砂土液化概率判别方法,使工程场地的砂土液化概率判别如同确定性砂土液化判别一样简单、方便,从而使砂土液化概率判别方法用于工程实践和纳入有关规范成为可能。     

基于径向基函数神经网络的高层建筑结构选型

提出了应用径向基函数神经网络进行高层结构体系的选型,它充分运用了神经网络高度的非线性、高度的容错性和鲁棒性、自学习、实时处理等特点.研究表明,径向基函数神经网络运算速度较普通BP算法快103～104倍,并且精度高,可以高效、高质地进行高层建筑结构的选型.     

岩石本构关系的径向基函数神经网络快速逼近模型

建立了径向基函数神经网络快速逼近模型 ,基于具体条件下岩石力学实验数据 ,对相应岩石的本构关系进行逼近 ,实例分析表明 ,该模型不仅对具体应力 -应变关系能够很好逼近和预测 ,而且逼近速度快、稳定性好 ,对岩石力学快速、高效数值方法的进一步发展具有重要参考价值。     

An artificial neural network approach to inhomogeneous soil slope stability predictions based on limit analysis methods

The assessment of soil slope stability is an important task in geotechnical designs. This study uses finite element upper bound (UB) and lower bound (LB) limit analysis (LA) methods to investigate inhomogeneous soil slope stability on the basis of the conventional Mohr–Coulomb parameters. The obtained stability numbers are presented in inhomogeneous soil slope stability charts. In order to minimize manual reading errors when using the chart solutions, an artificial neural network (ANN) is employed to develop a stability assessment tool for the slopes investigated in this paper. The slope stability analysis using the ANN-based tool is convenient, and the predictions it provides are highly accurate.     

Structural reliability analysis for implicit performance functions using artificial neural network

The Monte-Carlo simulation (MCS), the first-order reliability methods (FORM) and the second-order reliability methods (SORM), are three reliability analysis methods that are commonly used for structural safety evaluation. The MCS requires the calculations of hundreds and thousands of performance function values. The FORM and SORM demand the values and partial derivatives of the performance function with respect to the design random variables. Such calculations could be time-consuming or cumbersome when the performance functions are implicit. Such implicit performance functions are normally encountered when the structural systems are complicated and numerical analysis such as finite element methods has to be adopted for the prediction.To address this issue, this paper presents three artificial neural network (ANN)-based reliability analysis methods, i.e. ANN-based MCS, ANN-based FORM, and ANN-based SORM. These methods employ multi-layer feedforward ANN technique to approximate the implicit performance functions. The ANN technique uses a small set of the actual values of the implicit performance functions. Such a small set of actual data is obtained via normal numerical analysis such as finite element methods for the complicated structural system. They are used to develop a trained ANN generalization algorithm. Then a large number of the values and partial derivatives of the implicit performance functions can be obtained for conventional reliability analysis using MCS, FORM or SORM. Examples are given in the paper to illustrate why and how the proposed ANN-based structural reliability analysis can be carried out. The results have shown the proposed approach is applicable to structural reliability analysis involving implicit performance functions. The present results are compared well with those obtained by the conventional reliability methods such as the direct Monte-Carlo simulation, the response surface method and the FORM method 2.     

基于径向基神经网络的深基坑非线性位移反分析

以支护结构-土非线性共同作用的土压力计算模型为基础,提出了非线性共同作用弹性地基反力法;然后将径向基神经网络引入深基坑位移反分析,研究了根据深基坑空间效应的表现形式及规律选取适当剖面进行位移反分析的原理与方法,编制了计算程序。它可以逐工况地对支护结构不同标高和平面位置处的实测位移进行反分析,从而使反演的土性参数包含了时空效应和非线性共同作用的影响。工程算例表明:围护墙位移的反演计算结果与实测值吻合良好。     

基于径向基网络和气象因子的森林火灾预测系统

根据森林火灾的历史资料,利用径向基函数网络的自学习、自适应能力,建立了基于径向基网络的森林火灾预测系统.针对气象条件对森林火灾发生的影响,提取了温度、相对湿度、风速、降水量几个特征参数作为样本,对网络进行了训练和测试.结果表明,该系统的预测精度高,对森林火灾预测技术的发展具有一定的推动作用,同时也为其他自然灾害的预测提供了参考.     

Prediction of blast-induced ground vibration using artificial neural network

An attempt has been made to evaluate and predict the blast-induced ground vibration and frequency by incorporating rock properties, blast design and explosive parameters using the artificial neural network (ANN) technique. A three-layer, feed-forward back-propagation neural network having 15 hidden neurons, 10 input parameters and two output parameters were trained using 154 experimental and monitored blast records from one of the major producing surface coal mines in India. Twenty new blast data sets were used for the validation and comparison of the peak particle velocity (PPV) and frequency by ANN and other predictors. To develop more confidence in the proposed method, same data sets have also been used for the prediction of PPV by commonly used vibration predictors as well as by multivariate regression analysis (MVRA). Results were compared based on correlation and mean absolute error (MAE) between monitored and predicted values of PPV and frequency.     

Innovative piled raft foundations design using artificial neural network

Studying the piled raft behavior has been the subject of many types of research in the field of geotechnical engineering. Several studies have been conducted to understand the behavior of these types of foundations, which are often used for uniform loading on the raft and piles with the same length, while generally the transition load from the upper structure to the foundation is non-uniform and the choice of uniform length for piles in the above model will not be optimally economic and practical. The most common method in identifying the behavior of piled rafts is the use of theoretical relationships and software analyses. More precise identification of this type of foundation behavior can be very difficult due to several influential parameters and interaction of set behavior, and it will be done by doing time-consuming computer analyses or costly full-scale physical modeling. In the meantime, the technique of artificial neural networks can be used to achieve this goal with minimum time consumption, in which data from physical and numerical modeling can be used for network learning. One of the advantages of this method is the speed and simplicity of using it. In this paper, a model is presented based on multi-layer perceptron artificial neural network. In this model pile diameter, pile length, and pile spacing is considered as an input parameter that can be used to estimate maximum settlement, maximum differential settlement, and maximum raft moment. By this model, we can create an extensive domain of results for optimum system selection in the desired piled raft foundation. Results of neural network indicate its proper ability in identifying the piled raft behavior. The presented procedure provides an interesting solution and economically enhancing the design of the piled raft foundation system. This innovative design method reduces the time spent on software analyses.     

Construction equipment productivity estimation using artificial neural network model

Estimating equipment production rates is both an art and a science. An accurate prediction of the productivity of earthmoving equipment is critical for accurate construction planning and project control. Owing to the unique work requirements and changeable environment of each construction project, the influences of job and management factors on operation productivity are often very complex. Hence, construction productivity estimation, even for an operation with well‐known equipment and work methods, can be challenging. This study develops and compares two methods for estimating construction productivity of dozer operations (the transformed regression analysis, and a non‐linear analysis using neural network model). It is the hypothesis of this study that the proposed neural networks model may improve productivity estimation models because of the neural network's inherent ability to capture non‐linearity and the complexity of the changeable environment of each construction project. The comparison of results suggests that the non‐linear artificial neural network (ANN) has the potential to improve the equipment productivity estimation model.     

Dynamic wind response of tall buildings using artificial neural network

This paper presents an alternative approach for predicting the dynamic wind response of tall buildings using artificial neural network (ANN). The ANN model was developed, trained, and validated based on the data generated in the context of Indian Wind Code (IWC), IS 875 (Part 3):2015. According to the IWC, dynamic wind responses can be calculated for a specific configuration of buildings. The dynamic wind loads and their corresponding responses of structures other than the specified configurations in IWC have to be estimated by wind tunnel tests or computational techniques, which are expensive and time intensive. Alternatively, ANN is an efficient and economical computational analysis tool that can be implemented to estimate the dynamic wind response of a building. In this paper, ANN models were developed to predict base shear and base bending moment of a tall building in along‐ and across‐wind direction by giving the input as the configuration of the building, wind velocity, and terrain category. Multilayer perceptron ANN models with back‐propagation training algorithm was adopted. On comparison of results, it was found that the predicted values obtained from the ANN models and the calculated responses acquired using IWC standards are almost similar. Using the best fit model of ANN, an extensive parametric study was performed to predict the dynamic wind response of tall buildings for the configurations on which IWC is silent. Based on the results obtained from this study, design charts are developed for the prediction of dynamic wind response of tall buildings.     

基于人工神经网络的软土路基沉降预测

为分析路基的沉降变形规律,采用人工神经网络对软基路基的沉降进行了预测,通过Matlab建立了人工神经网络模型,同时与实际检测结果对比验证模型的准确性,对比结果表明该方法具有较高精度。     

Patterning and predicting aquatic macroinvertebrate diversities using artificial neural network

A counterpropagation neural network (CPN) was applied to predict species richness (SR) and Shannon diversity index (SH) of benthic macroinvertebrate communities using 34 environmental variables. The data were collected at 664 sites at 23 different water types such as springs, streams, rivers, canals, ditches, lakes, and pools in The Netherlands. By training the CPN, the sampling sites were classified into five groups and the classification was mainly related to pollution status and habitat type of the sampling sites. By visualizing environmental variables and diversity indices on the map of the trained model, the relationships between variables were evaluated. The trained CPN serves as a 'look-up table' for finding the corresponding values between environmental variables and community indices. The output of the model fitted SH and SR well showing a high accuracy of the prediction (r>0.90 and 0.67 for learning and testing process, respectively) for both SH and SR. Finally, the results of this study, which uses the capability of the CPN for patterning and predicting ecological data, suggest that the CPN can be effectively used as a tool for assessing ecological status and predicting water quality of target ecosystems.     

Performance evaluation of open-cycle solar regenerator using artificial neural network technique

Theoretical investigation on the performance of lithium chloride (LiCl) absorption cooling system using an artificial neural network (ANN) model is presented. Tabulated data from the literature are used to construct the ANN model. Solar collector desiccant/regenerator is applied to re-concentrate the working solution. Using the proposed model, the effect of system design parameters; namely regenerator length, and air flow rate on the performance of the system is demonstrated. The variation of the thermo-physical parameters along the regenerator length is highlighted.     

Applying radial basis function neural networks to estimate next-cycle production rates in tunnelling construction

To better cater to tunnel construction productivity studies, the present research extends time series analysis by accounting for additional critical state variables of the tunnelling construction system which represent geological factors and operation delay factors. Those state variables are readily assessed at the end of each tunnelling cycle or can be easily obtained from the actual data recorded in current data collection systems. Radial basis function (RBF) neural networks (NN) provide the accuracy, flexibility and efficiency in mapping complex non-linear relationships between system states and system outputs at consecutive time events. Using data obtained from a tunnel project in Hong Kong, a case study of applying the RBF-based time series analysis for estimating next-cycle production rates was conducted. Identification of those additional state variables for rock tunnel construction by the “drill and blast” method is elaborated. The RBF NN model is retrained at the end of each cycle with the most recent data added to the NN training set. The updated RBF NN model is then used to assist tunnel engineers in estimating the production rate on the immediately following cycle.     

径向基函数神经网络预测城市用水量模型及应用

以城市用水人口和城市生产总值作为输入向量,年用水量数据作为目标向量,建立了径向基函数神经网络并对城市用水量进行预测。采用不同的扩展速度,预测误差不同。当扩展速度spread=1时,预测数据与实际数据的相对误差均小于0.05%,取得了很好的预测效果,说明采用径向基函数神经网络模型预测城市用水量的方法是可行的。     

Prediction of bed load sediments using different artificial neural network models

Modeling and prediction of bed loads is an important but difficult issue in river engineering. The introduced empirical equations due to restricted applicability even in similar conditions provide different accuracies with each other and measured data. In this paper, three different artificial neural networks (ANNs) including multilayer percepterons, radial based function (RBF), and generalized feed forward neural network using five dominant parameters of bed load transport formulas for the Main Fork Red River in Idaho-USA were developed. The optimum models were found through 102 data sets of flow discharge, flow velocity, water surface slopes, flow depth, and mean grain size. The deficiency of empirical equations for this river by conducted comparison between measured and predicted values was approved where the ANN models presented more consistence and closer estimation to observed data. The coefficient of determination between measured and predicted values for empirical equations varied from 0.10 to 0.21 against the 0.93 to 0.98 in ANN models. The accuracy performance of all models was evaluated and interpreted using different statistical error criteria, analytical graphs and confusion matrixes. Although the ANN models predicted compatible outputs but the RBF with 79% correct classification rate corresponding to 0.191 network error was outperform than others.     

基于神经网络-蒙特卡罗法的隧道初衬可靠度研究

对于功能函数是隐函数的可靠性分析问题,传统的有限元蒙特卡罗法计算量极大。为了克服此缺点,提出了径向基神经网络-有限元蒙特卡罗法(RBF-MCS)。通过样本训练,创建了径向基神经网络模型。利用ANSYS软件中的可靠度分析模块,分析了基本随机变量对隧道初衬轴力的灵敏度大小的顺序。通过此方法和传统的有限元蒙特卡罗法分别计算了大瑶山隧道初衬的轴力和可靠度,并进行了对比分析。基于径向基神经网络-有限元蒙特卡罗法(RBF-MCS)的计算结果与施工实际吻合较好,通过现场观察也没有发现喷层混凝土压裂破坏,可见计算结果是符合实际的。径向基神经网络-有限元蒙特卡罗法比传统有限元蒙特卡罗法更加适合复杂结构的计算,具有更高的效率、精度和适用性。     

Predicting chaotic time series of PM10 concentration using artificial neural network

Respirable particulate matter (PM10) concentration at one residential site in Delhi, India was predicted using the neural network approach. The concepts of chaotic systems theory were utilized to build the neural network model. The embedding dimension was estimated to provide the inputs to the neural network. The model evaluation results indicated the importance of noise reduction before selecting the embedding dimension of the time series. The selection of a proper embedding dimension is considered to be essential for obtaining reliable predictions. The model’s performance shows the capability of neural networks in modelling the chaotic time series.