Inelastic lateral-torsional buckling capacity of corroded web opening steel beams using artificial neural networks

Steel beams are extensively used as main structural in various building infrastructures such as bridge girders. Steel structures are prone to suffer various types of damage as they get older. Corrosion may be one of the most important types of damage in ageing steel structures. In a pessimistic state, an area of opening may be created along the bottom zone of the beam's web due to corrosion. The existence of opening in the web of a beam can reduce the resistance of the beam to shear, bending or buckling. This study deals with the stability of damaged steel I-beams with web opening. A three-dimensional finite element (FE) model using ABAQUS for inelastic analysis of beams has been developed to assess the effect of web opening on the lateral-torsional buckling (LTB) capacity. Artificial neural network approach has also been employed to derive empirical formula for predicting the residual ultimate LTB moment of damaged steel I-beams using obtained FE results. It is found out that the proposed formula can accurately predict ultimate capacities of doubly symmetric steel I-beams with different sizes of web opening. Hence, the results of this study can be used for better prediction of residual ultimate LTB moment of corrosion damaged girders of steel existing structures by practice engineers.     

A neural network bid/no bid model: the case for contractors in Syria

Despite the crucial importance of the ‘bid/no bid’ decision in the construction industry, it has been given little attention by researchers. This paper describes the development and testing of a novel bid/no bid model using the artificial neural network (ANN) technique. A back‐propagation network consisting of an input buffer with 18 input nodes, two hidden layers and one output node was developed. This model is based on the findings of a formal questionnaire through which key factors that affect the ‘bid/no bid’ decision were identified and ranked according to their importance to contractors operating in Syria. Data on 157 real‐life bidding situations in Syria were used in training. The model was tested on another 20 new projects. The model wrongly predicted the actual bid/no bid decision only in two projects (10%) of the test sample. This demonstrates a high accuracy of the proposed model and the viability of neural network as a powerful tool for modelling the bid/no bid decision‐making process. The model offers a simple and easy‐to‐use tool to help contractors consider the most influential bidding variables and to improve the consistency of the bid/no bid decision‐making process. Although the model is based on data from the Syrian construction industry, the methodology would suggest a much broader geographical applicability of the ANN technique on bid/no bid decisions.     

空间网格结构节点螺栓松动损伤定位有限元分析

以单层柱面网壳试验模型为背景进行损伤定位研究,采用ANSYS软件对其螺栓松动损伤进行了有限元分析,利用神经网络的模式分类功能进行了螺栓松动的分步损伤定位,即首先以整体结构为研究对象,采用面向子结构的损伤定位,确定结构是否存在损伤及损伤的大致位置;然后采用面向节点的损伤定位法,确定子结构中螺栓松动损伤的节点位置。研究结果表明：损伤识别的成功率与杆件灵敏度密切相关,为了保证识别结果准确性,其灵敏度达到2%以上才能正确识别,当杆件的灵敏度过低时将无法通过动力测试识别;采用分步损伤定位方法可以显著减少损伤精确定位时训练样本的数量,适合于不完备的模态数据,利用低阶模态数据即可准确识别损伤的子结构与节点位置。     

人工神经网络模型在应对城市内涝中的应用

现在城市排水系统的规划和运营管理一般不考虑城市下游受纳水体变化的影响,这也是国内城市内涝频发的原因之一。目前,越来越多的城市应用模型来应对城市内涝,模型中受纳水体的水位一直以来都是利用经验设定一个恒定值。本文利用ANN(人工神经网络)技术,以城市上游观测站的实测水位为输入,以城市未来某时段的水位为目标选择合理的参数,建立了预测河流水位模型。利用更准确的动态预测值代替恒定值,可以提高城市排水系统水力模型的精度。选择某地区水位站的资料,对预报模型进行了检验,结果表明,在合理选择输入层数据和预测时间段的条件下,可以取得很好的预报结果。     

基于小波包分解和奇异谱分析方法的立铣加工颤振监测

在立铣加工过程中,颤振是加工过程失稳的一个最重要的原因。颤振将会严重影响工件表面质量和材料去除率,加剧刀具磨损和恶化工作环境。虽然大部分颤振监测系统可以监测到颤振发生,但颤振发生时已经对工件和刀具产生了严重的损伤,因此,需要提前监测到颤振特征。在颤振发生过程中,振动信号具有在时域中不断增大,在频域中能量频移的特性。考虑这两个振动信号特征,提出了一种颤振特征提取方法。提取颤振发生频带中振动信号的能量比和奇异谱熵系数作为两个颤振特征,并通过人工神经网络模型实现切削颤振的识别。文中提出的颤振监测系统包括特征提取和分类,能够精确辨识立铣加工中的稳定、过渡和颤振状态。     

ANFIS和ANN在圆弧滑动边坡稳定性分析中的应用研究

影响边坡稳定性的因素复杂,且在力学上多表现为随机模糊性。ANN和ANFIS的性能特征使其适于进行非确定性的边坡稳定性问题的评判。从各自的基本原理出发,集成学习训练样本,构建神经网络和自适应神经模糊推理方法,通过训练和测试来检验其可靠性和适用性,并将得出的结果与工程现状进行对照。最后将其应用于4个边坡检验样本,并比较研究两者的准确性。研究说明ANN和ANFIS在边坡稳定性预测中的有效性和适用性。     

Toward an automatic wheat purity measuring device: A machine vision-based neural networks-assisted imperialist competitive algorithm approach

Wheat product quality is closely related to wheat seed purity. Purity is an important factor that has a considerable impact on wheat product prices in grain storage silos. The aim of this paper was to introduce a machine vision based approach as a primarily step for fabricating an automatic wheat purity determination and grading device. Experimental data consists of 52 color, morphology, and texture characteristic parameters, extracted from images of samples, including four local wheat grades and eight common weed seeds growing in wheat fields of Iran, were used to build the classification models. A new algorithm that combines Imperialist Competitive Algorithm (ICA) and Artificial Neural Networks (ANNs) has been used for two purposes: to find the best characteristic parameters set and to create robust classification models. Based upon the results obtained from this study, the total classification rate of ICA–ANN approach for wheat grains vs. non-wheat seeds, wheat grain classes, and non-wheat seed classes was 96.25%, 87.50%, and 77.22%, respectively.     

CFD and artificial neural network modeling of two-phase flow pressure drop

A large number of experiments in a 2 cm diameter and 6 m length tube were carried out in order to study the two-phase flow regimes and pressure drops in it. The two-phase flow in the experimental tube was modeled using commercial CFD code, Fluent 6.2. An Artificial Neural Network (ANN) with three inputs including gas and liquid velocities and tube slope was designed and trained to predict average pressure drop across the tube. The comparison between CFD and ANN predictions of pressure drops with experimental measurements shows that the CFD results are more accurate than the ANN evaluations for new conditions.