A Comparative Analysis of Two Artificial Neural Networks Using Pavement Performance Prediction

The management of pavements requires the ongoing allocation of substantial manpower and capital resources by the responsible agencies. These agencies ultimately report to the executive and legislative branches of government, which require justification and proof of the efficacy of these expenditures. This and the need for improved engineering technical feedback have encouraged the development of pavement management systems (PMS). One goal of a PMS is to provide decision makers at all levels with optimal resource-allocation strategies. This requires evaluation of alternatives over an analysis period based on predicted values of pavement performance. This necessitates more reliable pavement performance prediction models. Traditional modeling uses multiple regression techniques to predict pavement performance from traffic, time, and pavement distress or various combinations of these factors. Within the last 10 years, new modeling techniques, including artificial neural networks (ANNs), have been applied to transportation problems. The ANNs examined usually have been of a single type called a dot product ANN. This paper examines a different type called the quadratic function ANN and compares the results to the dot product ANN. The quadratic function ANN is a generalized adaptive, feedforward neural network that combines supervised and self-organizing learning. Models were developed to predict roughness using both types of ANN on the same data samples and the results compared. The data samples were drawn from the Kansas Department of Transportation's PMS database. The results indicate a significant improvement in the use of the self-organizing quadratic function ANNs and lead to recommendations for specific areas of additional research.     

BP神经网络在隧道围岩稳定性分类中的应用

将BP神经网络应用于隧洞围岩分类,BP神经网络通过学习记忆建立输入和输出变量之间的非线性关系。利用淮南洞山隧道围岩分类样本进行模拟检验,BP神经网络模型性能良好,对隧道围岩分类的精度较高,是一种值得推广和应用的围岩智能分类方法。     

A novel machine learning‐based algorithm to detect damage in high‐rise building structures

A novel model is presented for global health monitoring of large structures such as high‐rise building structures through adroit integration of 2 signal processing techniques, synchrosqueezed wavelet transform and fast Fourier transform, an unsupervised machine learning technique, the restricted Boltzmann machine, and a recently developed supervised classification algorithm called neural dynamics classification (NDC) algorithm. The model extracts hidden features in the frequency domain of the denoised measured response signals recorded by sensors on different elevations or floors of a structure. The extracted features are used as an input of the NDC to detect and classify the global health of the structure into categories such as healthy, light damage, moderate damage, severe damage, and near collapse. The proposed model is validated using the data obtained from a 3D 1:20 scaled 38‐story reinforced concrete building structure. The results are compared with 3 other supervised classification algorithms: k‐nearest neighbor (KNN), probabilistic neural networks (PNN), and enhanced PNN (EPNN). NDC, EPNN, PNN, and KNN yield maximum average accuracies of 96%, 94%, 92%, and 82%, respectively.     

基于SOM映射网络的人群流量预测在节能照明中的应用

通常比较常见的照明控制都是事先设定好的时间控制模式,不可调节且也不能满足精细化控制以及智能化的要求。运用SOM自组织映射网络将人流量历史数据进行特征提取并分类,再将各类数据结果运用BP神经元网络方法进行预测,并将预测结果结合照度需求,不同等级人群流量给予不同等级的照度输出,最后在节能方面也与传统照明方式做了对比。实验结果表明,SOM-BP神经元算法预测下的短期人流量预测数据比BP算法精度更高,结合照明调节后在节能方面具有更好的效果,为照明系统提供了新的节能方案。     

Quantification and localisation of damage in beam-like structures by using artificial neural networks with experimental validation

This paper presents a damage detection algorithm using a combination of global (changes in natural frequencies) and local (curvature mode shapes) vibration-based analysis data as input in artificial neural networks (ANNs) for location and severity prediction of damage in beam-like structures. A finite element analysis tool has been used to obtain the dynamic characteristics of intact and damaged cantilever steel beams for the first three natural modes. Different damage scenarios have been introduced by reducing the local thickness of the selected elements at different locations along finite element model (FEM) of the beam structure. The necessary features for damage detection have been selected by performing sensitivity analyses and different input–output sets have been introduced to various ANNs. In order to check the robustness of the input used in the analysis and to simulate the experimental uncertainties, artificial random noise has been generated numerically and added to noise-free data during the training of the ANNs. In the experimental analysis, two steel beams with eight distributed surface-bonded electrical strain gauges and an accelerometer mounted at the tip have been used to obtain modal parameters such as resonant frequencies and strain mode shapes. Finally, trained feed-forward backpropagation ANNs have been tested using the data obtained from the experimental damage case for quantification and localisation of the damage.     

Machine Learning in Engineering Analysis and Design: An Integrated Fuzzy Neural Network Learning Model

Applying neural network computing to structural engineering problems has received increasing interest, with particular emphasis placed on a supervised neural network with the backpropagation (BP) learning algorithm. In this article, we present an integrated fuzzy neural network (IFN) learning model by integrating a newly developed unsupervised fuzzy neural network (UFN) reasoning model with a supervised learning model in structural engineering. The UFN reasoning model is developed on the basis of a single-layer laterally connected neural network with an unsupervised competing algorithm. The IFN learning model is compared with the BP learning algorithm as well as with a counterpropagation learning algorithm (CPN) using two engineering analysis and design examples from the recent literature. This comparison indicates not only a superior learning performance in solved instances but also a substantial decrease in computational time for the IFN learning model. In addition, the IFN learning model is applied to a complicated engineering design problem involving steel structures. The IFN learning model also demonstrates superior learning performance in a complicated structural design problem with a reasonable computational time.     

Burst detection using hydraulic data from water distribution systems with artificial neural networks

This paper presents research into the application of artificial neural networks (ANNs) for analysis of data from sensors measuring hydraulic parameters (flow and pressure) of the water flow in treated water distribution systems. Two neural architectures (static and time delay) are applied for time series pattern classification from the perspective of detecting leakage. Results are presented using data from an experimental site in a distribution system of a UK water company in which bursts were simulated by hydrant flushing. Field trials have shown how ANNs can be used effectively for a leakage detection task. Both static and time delay ANNs learned patterns of leaks/bursts. The time delay neural network showed improved performance over the static network. It is concluded that the effectiveness of an ANN in discovering relationships within the data is dependent upon two key factors: availability of sufficient exemplars and data quality.     

Prediction of roadheaders' performance using artificial neural network approaches (MLP and KOSFM)

Application of mechanical excavators is one of the most commonly used excavation methods because it can bring the project more productivity, accuracy and safety. Among the mechanical excavators, roadheaders are mechanical miners which have been extensively used in tunneling, mining and civil industries. Performance prediction is an important issue for successful roadheader application and generally deals with machine selection, production rate and bit consumption. The main aim of this research is to investigate the cutting performance(instantaneous cutting rates(ICRs)) of medium-duty roadheaders by using artificial neural network(ANN) approach. There are different categories for ANNs, but based on training algorithm there are two main kinds: supervised and unsupervised. The multi-layer perceptron(MLP) and Kohonen self-organizing feature map(KSOFM) are the most widely used neural networks for supervised and unsupervised ones, respectively. For gaining this goal, a database was primarily provided from roadheaders' performance and geomechanical characteristics of rock formations in tunnels and drift galleries in Tabas coal mine, the largest and the only fullymechanized coal mine in Iran. Then the database was analyzed in order to yield the most important factor for ICR by using relatively important factor in which Garson equation was utilized. The MLP network was trained by 3 input parameters including rock mass properties, rock quality designation(RQD), intact rock properties such as uniaxial compressive strength(UCS) and Brazilian tensile strength(BTS), and one output parameter(ICR). In order to have more validation on MLP outputs, KSOFM visualization was applied. The mean square error(MSE) and regression coefficient(R) of MLP were found to be 5.49 and 0.97, respectively. Moreover, KSOFM network has a map size of 8 5 and final quantization and topographic errors were 0.383 and 0.032, respectively. The results show that MLP neural networks have a strong capability to predict and evaluate the performance of medium-duty roadheaders in coal measure rocks. Furthermore, it is concluded that KSOFM neural network is an efficient way for understanding system behavior and knowledge extraction. Finally, it is indicated that UCS has more influence on ICR by applying the best trained MLP network weights in Garson equation which is also confirmed by KSOFM.     

Using Machine Learning, Neural Networks, and Statistics to Predict Corporate Bankruptcy

Recent literature strongly suggests that machine learning approaches to classification outperform "classical" statistical methods. We make a comparison between the performance of linear discriminant analysis, classification trees, and neural networks in predicting corporate bankruptcy. Linear discriminant analysis represents the "classical" statistical approach to classification, whereas classification trees and neural networks represent artificial intelligence approaches. A proper statistical design is used to be able to test whether observed differences in predictive performance are statistically significant. The data set consists of a collection of 576 annual reports from Belgian construction companies. We use stratified 10–fold cross–validation on the training set to choose "good" parameter values for the different learning methods. The test set is used to obtain an unbiased estimate of the true prediction error. Using rigorous statistical testing, we cannot conclude that in the case of the data set studied, one learning method clearly outperforms the other methods.     

Training Artificial Neural Networks with the Aid of Fuzzy Sets

This article presents a technique of training artificial neural networks (ANNs) with the aid of fuzzy sets theory. The proposed ANN model is trained with field observation data for predicting the collapse potential of soils. This ANN model uses seven soil parameters as input variables. The output variable is the collapsibility (whether the soil is collapsible) or the collapse potential (if the soil is judged collapsible). The proposed technique involves a module for preprocessing input soil parameters and a module for postprocessing network output. The preprocessing module screens the input data through a group of predefined fuzzy sets, and the postprocessing module, on the other hand, "defuzzifies" the output from the network into a "nonfuzzy" collapse potential, a single value. The ANN with the proposed preprocessing and post-process techniques is shown to be superior to the conventional ANN model in the present study.     

ANN的改良KT法分析建筑工程投标决策

人工神经网络理论已在解决投标决策问题领域中有所应用。但其主要的缺点在于神经网络系统不能解释为什么和什么样的规则是合适的,这些对使用者是否能接受该系统影响很大。改良KT法用来收集和检验预测数据,解决预测问题。     

Predicting pile dynamic capacity via application of an evolutionary algorithm

This study presents the development of a new model obtained from the correlation of dynamic input and SPT data with pile capacity. An evolutionary algorithm, gene expression programming (GEP), was used for modelling the correlation. The data used for model development comprised 24 cases obtained from existing literature. The modelling was carried out by dividing the data into two sets: a training set for model calibration and a validation set for verifying the generalization capability of the model. The performance of the model was evaluated by comparing its predictions of pile capacity with experimental data and with predictions of pile capacity by two commonly used traditional methods and the artificial neural networks (ANNs) model. It was found that the model performs well with a coefficient of determination, mean, standard deviation and probability density at 50% equivalent to 0.94, 1.08, 0.14, and 1.05, respectively, for the training set, and 0.96, 0.95, 0.13, and 0.93, respectively, for the validation set. The low values of the calculated mean squared error and mean absolute error indicated that the model is accurate in predicting pile capacity. The results of comparison also showed that the model predicted pile capacity more accurately than traditional methods including the ANNs model.     

Analysis of durability of high performance concrete using artificial neural networks

This study aims to determine the influence of the content of water and cement, water–binder ratio, and the replacement of fly ash and silica fume on the durability of high performance concrete (HPC) by using artificial neural networks (ANNs). To achieve this, an ANNs model is developed to predict the durability of high performance concrete which is expressed in terms of chloride ions permeability in accordance with ASTM C1202-97 or AASHTO T277. The model is developed, trained and tested by using 86 data sets from experiments as well as previous researches. To verify the model, regression equations are carried out and compared with the trained neural network. The results indicate that the developed model is reliable and accurate. Based on the simulating durability model built using trained neural networks, the optimum cement content for designing HPC in terms of durability is in the range of 450–500 kg/m³. The results also revealed that the durability of concrete expressed in terms of total charge passed over a 6-h period can be significantly improved by using at least 20% fly ash to replace cement. Furthermore, it can be concluded that increasing silica fume results in reducing the chloride ions penetrability to a higher degree than fly ash. This study also illustrates how ANNs can be used to beneficially predict durability in terms of chloride ions permeability across a wide range of mix proportion parameters of HPC.     

Prediction of effective thermal conductivity of moist porous materials using artificial neural network approach

An artificial neural networks (ANNs) approach is presented for the prediction of effective thermal conductivity of porous systems filled with different liquids. ANN models are based on feedforward backpropagation network with training functions: Levenberg–Marquardt (LM), conjugate gradient with Fletcher–Reeves updates (CGF), one-step secant (OSS), conjugates gradient with Powell–Beale restarts (CGB), Broyden, Fletcher, Goldfrab and Shanno (BFGS) quasi-Newton (BFG), conjugates gradient with Polak–Ribiere updates (CGP). Training algorithm for neurons and hidden layers for different feedforward backpropagation networks at the uniform threshold function TANSIG-PURELIN are used and run for 1000 epochs. The complex structure encountered in moist porous materials, along with the differences in thermal conductivity of the constituents makes it difficult to predict the effective thermal conductivity accurately. For this reason, artificial neural networks (ANNs) have been utilized in this field. The resultant predictions of effective thermal conductivity (ETC) of moist porous materials by the different models of ANN agree well with the available experimental data.     

Hierarchical community classification and assessment of aquatic ecosystems using artificial neural networks

Benthic macroinvertebrate communities in stream ecosystems were assessed hierarchically through two-level classification methods of unsupervised learning. Two artificial neural networks were implemented in combination. Firstly, the self-organizing map (SOM) was used to reduce the dimension of community data, and secondly, the adaptive resonance theory (ART) was subsequently applied to the SOM to further classify the groups in different scales. Hierarchical grouping in community data efficiently reflected the impact of the environmental factors such as topographic conditions, levels of pollution, and sampling location and time across different scales. New community data not included in the training process were used to test the trained network model. The input data were appropriately grouped at different hierarchical levels by the trained networks, and correspondingly revealed the impact of environmental disturbances and temporal dynamics of communities. The hierarchical clusters based on a two-level classification method could be useful for assessing ecosystem quality and community variations caused by environmental disturbances.     

基于ELM的大坝变形分析与预报模型

传统的诸如BP神经网络等学习方法训练时需要设置大量的参数,并且容易产生局部最优解。极限学习机(Extreme Learning Machine,ELM)可以随机选择输入权重以及隐藏层偏差且不需要调节,最终只产生唯一最优解。将ELM引入大坝变形分析建模中,建立了基于ELM的变形预报模型。实例表明,相比传统的逐步回归模型与BP神经网络模型,基于ELM的大坝变形预报模型在效率和精度上都有提高。     

基于遗传神经网络模型的水质综合评价

建立了用于水质综合评价的遗传神经网络模型.该模型运用遗传算法优化改进型BP神经网络的初始权值和阈值,具有快速学习网络权重和全局搜索的能力,有效解决了BP神经网络容易陷入局部极小点和训练结果不稳定的问题.采用苏帕河梯级电站的水质监测数据对该模型进行了测试,并与其他方法进行了比较.结果表明,该方法用于水质综合评价客观、合理、准确,有其独特的优越性.     

The application of neural networks to rock engineering systems (RES)

This paper proposes a new approach for applying neural networks in Rock Engineering Systems (RES) based on the learning abilities of neural networks. By considering the analysis of the coding methods for the interaction matrix in RES and the learning processes of neural networks such as the Back Propagation (BP) method, neural networks can provide a useful mapping from system inputs to system outputs for rock engineering, so that the influence of inputs on outputs can be obtained. Then the results of the neural network analysis can be presented in a similar way to the global interaction matrix used in RES to present the fully-coupled system results. The neural network procedures are explained first, with illustrative demonstrations for simultaneous equations. Then, the link with the RES type of analysis is explained, together with some demonstration examples for rock engineering data sets. The specific analysis procedure is presented and then wider rock engineering examples are given relating to the characteristics of rock masses and engineering parameters. The main presentation tools used in this neural network approach are the Relative Strength Effect (RSE) and the Global Relative Strength Effect (GRSE) matrix. There is discussion of the value of this approach and an indication of the likely areas of future development.     

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BP网络的碳纤维混凝土强度研究

介绍了应用均匀设计理论设计碳纤维混凝土配方的方法,通过所得到的试验数据,运用人工神经网络(ANN)的方法预测碳纤维混凝土抗压强度和劈裂抗拉强度;阐述了采用BP算法建立碳纤维混凝土抗压强度神经网络模型的过程,仿真结果表明,BP网络可成功地建立非线性的强度模型,预测强度可达到较高精度。