Figure 1 - uploaded by Ahmed Shamel Fahmy
Content may be subject to copyright.
![Typical components of orthotropic deck bridges [2].](profile/Ahmed-Fahmy-9/publication/308302620/figure/fig1/AS:668970352922629@1536506369387/Typical-components-of-orthotropic-deck-bridges-2.png)
Source publication
![Figure 1 Typical components of orthotropic deck bridges [2].](profile/Ahmed-Fahmy-9/publication/308302620/figure/fig1/AS:668970352922629@1536506369387/Typical-components-of-orthotropic-deck-bridges-2_Q320.jpg)
For orthotropic bridge decks a lot of progress has been made in the development of codes to aid in the design process, in addition to software tools for numerical analysis and design. However, professional software tools will not aid the designer in choosing a preliminary economic layout at the conceptual design stage. Designers would go through it...
Contexts in source publication
Context 1
... curing temperature required for concrete. The orthotropic deck is made up of ribs and crossbeams welded to a steel plate in two orthogonal direc- tions, all acting as one unit. It is called orthotropic as it has dif- ferent properties in two perpendicular directions. There are two types of orthotropic decks open-ribs and closed-ribs as shown in Fig. 1 [2]. The open-rib could be a steel plate, L-shape, or inverted T-section, while the closed-rib could be trapezoidal, triangular, or trapezoidal with a circular base as shown in Fig. ...
Context 2
... and batch training were tried, and online training gave better results, see Fig. 7. Numerous configurations were tried see Fig. 8. The one that gave the best results in a quite adequate time was a 10-20-8 structure, with a 0.00815 training error and a Figure 10 Design sheet. 0.00894 testing error. ...
Context 3
... Trained Neural Network generated was transformed to an Excel sheet, with visual basic codes, in order to get a simple user interface for future designs. Fig. 10 shows the Excel sheet main page where one is required to enter the estimated dimen- sions and, the program decides whether it is safe or ...
Citations
... Because of its exceptional characteristics of self-learning, fault tolerance, non-linearity, adaptability, and progression of input to output planning; ANNs have become the most widely used for universal function approximation in numerical models [73,117]. NN techniques have been widely applied in many fields of industry including the construction sector [70]. ...
Contingency is a critical component in the cost estimation process for any construction project. The contingency reserve considers potential costs related to risks and uncertainties associated with construction projects. It is usually assumed to damp any resulting uncertain monetary impact and to prevent project cost overrun. Many contingency calculation methods for construction projects proposed in literature ranged from simple percentage to complex mathematical methods. Deciding the optimum contingency method for a given project at a given phase represents the main challenge in cost estimation process. This study presents a comprehensive compilation of all contingency calculation methods and divided them into three main groups: deterministic, probabilistic, and modern mathematical methods which have been discussed in details. Appropriate method for estimating contingency amount depends on many criteria such as project peculiarity, complexity, ease of method used, and the accuracy level of the estimates. This study proposed a practical guidance approach for construction agencies to choose their appropriate cost contingency method. This research is expected to help agencies/owners in the budget development stage to allocate a contingency budget for their construction projects.
... Other studies on the load-carrying capacity of CFST columns under different conditions have indicated the high applicability and reliability of this method [44][45][46][47]. In addition, artificial neural networks (ANNs) have been employed with success in various fields such as design [48][49][50], prediction [51][52][53], optimization [54][55][56], and damage detection [57][58][59][60]. An ANN is a network inspired by computational capacities of biological neural networks and comprises interconnected processing elements. ...
The literature on predicting the load-carrying capacity of symmetrical concrete-filled steel tube (Sy-CFST) columns using different machine learning methods has mainly focused on a single method or cross-section type in each study. Sy-CFST column has been widely used in the engineering field because of its several benefits such as increased strength due to confinement generation, better ductility due to high steel ratio, and less construction cost and time as compared to the encased reinforced concrete. This study attempted to evaluate the load-carrying capacity of these columns with circular and square cross-sections based on the simultaneous use of the two gene expression programming (GEP) and artificial neural network (ANN) approaches. The database required for extracting GEP and ANN models was based on the empirical results of 993 specimens. Variables considered here include the compressive strength of concrete (f c), yield stress of steel (f y), cross-sectional areas of concrete (A c) and steel (A s), diameter to thickness ratio of the steel tube (D/t or B/t), and slenderness ratio of Sy-CFST columns (λ). Moreover, parametric and sensitivity analyses were conducted separately to assess the contribution of each effective parameter to the axial capacity. To validate the efficiency of the models, prediction values of GEP and ANN were compared with the predictions of existing codes (6 codes) and different studies (8 studies). The results indicated that the developed models provide accurate predictions for the load-carrying capacity of Sy-CFST columns. In addition, the variation of parameters in the proposed models is consistent with experimental trends observed in other studies, which confirms the consistency of the proposed numerical models with physical observations.
... In other words, there is no position change on the truck path. From these conditions, it can be concluded that durability is one of the main considerations in the design of the bridge (Fahmy et al., 2016). ...
This paper contributes a technocultural perspective in understanding a socialconstruction of the Jembatan Hati 3 bridge as a technology, to uncover the technologicaland social dimensions of the bridge. An ethnographic research method is employed inunderstanding a bridge as a technological and social product. The design, construction,and maintenance of bridge in Kampong Cipadung, Desa Daroyon, Kecamatan Cileles,Kabupaten Lebak, Banten, Indonesia. This method is based on a participatory model,in which a team of engineers and researchers (the outsiders) and the local people (theinsiders) collaborate in defining the design, function and maintenance of the bridge,based on a geographical, environmental, and social conditions. The result of the researchshows that the bridge construction is a symbiosis of technical logic of functionality,simplicity, efficiency, durability, and social logics of connectedness, improvement,cohesiveness, and commonness.
... [4,5]), deep learning and neural networks (e.g. [6][7][8][9]), constraint search (e.g. [10]), evolutionary computation and genetic algorithm (e.g. ...
Monte Carlo Tree Search (MCTS) is a search technique that in the last decade emerged as a major breakthrough for Artificial Intelligence applications regarding board- and video-games. In 2016, AlphaGo, an MCTS-based software agent, outperformed the human world champion of the board game Go. This game was for long considered almost infeasible for machines, due to its immense search space and the need for a long-term strategy. Since this historical success, MCTS is considered as an effective new approach for many other scientific and technical problems. Interestingly, civil structural engineering, as a discipline, offers many tasks whose solution may benefit from intelligent search and in particular from adopting MCTS as a search tool. In this work, we show how MCTS can be adapted to search for suitable solutions of a structural engineering design problem. The problem consists of choosing the load-bearing elements in a reference reinforced concrete structure, so to achieve a set of specific dynamic characteristics. In the paper, we report the results obtained by applying both a plain and a hybrid version of single-agent MCTS. The hybrid approach consists of an integration of both MCTS and classic Genetic Algorithm (GA), the latter also serving as a term of comparison for the results. The study’s outcomes may open new perspectives for the adoption of MCTS as a design tool for civil engineers.
... It shows that overfitting occurs with 49 neurons in the hidden layer. Vis-à-vis, underfitting may have occurred with 5,8,9,12, and 13 neurons in the hidden layer. The literature recommends the highest number to be equal to 2Ni + 1, where Ni is the number of input neurons. ...
External bonding of fiber reinforced composites is currently the most popular method of strengthening building structures. Debonding performance is critical to the effectiveness of such strengthening. Many models of bond prediction can be found in the literature. Most of them were developed based on laboratory research, therefore, their accuracy with less popular strengthening systems is limited. This manuscript presents the possibility of using a model based on neural networks to analyze and predict the debonding strength of steel-reinforced polymer (SRP) and steel-reinforced grout (SRG) composites to concrete. The model is built on the basis of laboratory testing of 328 samples obtained from the literature. The results are compared with a dozen of the most popular analytical methods for predicting the load capacity. The prediction accuracy in the neural network model is by far the best. The total correlation coefficient reaches a value of 0.913 while, for the best analytical method (Swiss standard SIA 166 model), it is 0.756. The sensitivity analysis confirmed the importance of the modulus of elasticity and the concrete strength for debonding. It is also interesting that the width of the element proved to be very important, which is probably related to the low variability of this parameter in the laboratory tests.
... By optimizing these hyperparameters, the surrogate model accuracy can be improved greatly. In most of the studies on the surrogate modeling in mechanical design, their values were selected either in an arbitrary way or not mentioned [14]. Since these hyperparameters could improve the model accuracy greatly, in this study, a sequential optimization algorithm [15] was used to optimize the hyperparameters based on a developed multi-objective hyperparameters optimization framework [8]. ...
Machine learning for classification has been used widely in engineering design, for example, feasible domain recognition and hidden pattern discovery. Training an accurate machine learning model requires a large dataset; however, high computational or experimental costs are major issues in obtaining a large dataset for real-world problems. One possible solution is to generate a large pseudo dataset with surrogate models, which is established with a smaller set of real training data. However, it is not well understood whether the pseudo dataset can benefit the classification model by providing more information or deteriorates the machine learning performance due to the prediction errors and uncertainties introduced by the surrogate model. This paper presents a preliminary investigation towards this research question. A classification-and-regressiontree model is employed to recognize the design subspaces to support design decision-making. It is implemented on the geometric design of a vehicle energy-absorbing structure based on finite element simulations. Based on a small set of real-world data obtained by simulations, a surrogate model based on Gaussian process regression is employed to generate pseudo datasets for training. The results showed that the tree-based method could help recognize feasible design domains efficiently. Furthermore, the additional information provided by the surrogate model enhances the accuracy of classification. One important conclusion is that the accuracy of the surrogate model determines the quality of the pseudo dataset and hence, the improvements in the machine learning model.
... İnşaat mühendisliğindeki çok güçlü tasarım pratiklerinin uygulandığı köprü mühendisliğinde de yapay zekâ uygulamaları yer edinmiştir. Özellikle köprü sağlığı izleme [12], köprü muayenesi [13], köprü bileşenlerinin davranışı [14] ve tasarımı [15,16] alanlarında bu uygulamalar görülebilir. ...
Yapay zekâ konusunda kaydedilen ilerlemeler günümüzde her alanda çok önemli dönüşümlere neden olmaktadır. İnşaat mühendisliği alanında da yapay zekâ, makine öğrenmesi ve yapay sinir ağları uygulamaları ve kullanımı her geçen gün artmakta ve çeşitlenmektedir. Bu gelişmelere paralel olarak, bu çalışmada, yapay sinir ağları kullanılarak köprü tasarımında kullanılan hareketli yüklerin köprü kirişlerine dağılımı için kapalı formüller elde edilmiştir. Bu formüllerde, farklı yapısal köprü parametrelerinin yanı sıra, AASHTO LRFD’de verilen denklemlerde dahil edilmemiş olan kiriş sayısı parametresi de eklenmiştir. Bu amaçla, birçok verevsiz basit mesnetli köprü modeli hazırlanarak olası tüm kamyon yükleri altında sonlu elemanlar analizleri yapılmış ve hareketli yük dağılım katsayıları elde edilmiştir. Yapay sinir ağları ile elde edilen hareketli yük dağılım faktörleri, sonlu elemanlar analiz sonuçları ile ve AASHTO LRFD’de verilmiş olan hareketli yük dağılım katsayıları ile karşılaştırılmıştır. Bu karşılaştırmalar göstermektedir ki, sinir ağları ile elde edilen formüller dağılım faktörlerini oldukça iyi tahmin edebilmektedir.
... Where, z RS is the normalized value, x RS is the S th value of the R-variable, μ R , and σ R are the mean value and the standard deviation of the R-variable, respectively. The second common approach is the so-called Min-Max scaling with a fixed range (Pinar et al., 2010;Zare et al., 2013;Fahmy et al., 2016). A Min-Max scaling is typically represented via Eq. ...
This study presents a new hybrid method to develop seismic fragility curves for horizontally-curved steel I-girder bridges using Artificial neural network and logistic regression methods. The approach for developing fragility curves based on the assumption that engineering demand parameters follow the lognormal distribution for calculating the probability of damage occurrence. A sufficient number of input data including a set of earthquake ground motion records and macro-structural parameters together with the output data resulting from nonlinear structural analyses was assigned to neural network structure to achieve satisfactory approximations of responses. Logistic regression statistical method was used to determine the probability of occurrence or non-occurrence of limit states for earthquake ground motion parameters and structural characteristics. In this study, based on the estimation of engineering demand parameters, the proposed method is compared with the neural network method, simplified mathematical model and analytical method. The nonlinear time history analysis of three dimensional horizontally curve bridges were performed using the OpenSEES software. The statistical results indicate the accuracy and efficiency of the predicted limit state occurrence of the proposed method at a low computational cost. Comparison of fragility curves using the mentioned methods represent a proper estimation for slight, moderate, extensive and collapse limit states at different levels of seismic intensity.
... For instance, artificial neural networks (ANNs) and decision trees (DTs) have shown great potential as computationally efficient surrogate models. Fahmy et al.[105] used ANNs for conceptual design of orthotropic steel-deck bridge. Their motivation is that the professional software tools do not aid the designer in choosing a preliminary economic layout at the conceptual design stage. ...
Machine learning techniques promise to greatly accelerate structural design and optimiza- tion. In this thesis, deep learning and active learning techniques are applied to different non-convex structural optimization problems. Finite Element Analysis (FEA) based stan- dard optimization methods for aircraft panels with bio-inspired curvilinear stiffeners are computationally expensive. The main reason for employing many of these standard opti- mization methods is the ease of their integration with FEA. However, each optimization requires multiple computationally expensive FEA evaluations, making their use impractical at times. To accelerate optimization, the use of Deep Neural Networks (DNNs) is proposed to approximate the FEA buckling response. The results show that DNNs obtained an accu- racy of 95% for evaluating the buckling load. The DNN accelerated the optimization by a factor of nearly 200. The presented work demonstrates the potential of DNN-based machine learning algorithms for accelerating the optimization of bio-inspired curvilinearly stiffened panels. But, the approach could have disadvantages for being only specific to similar struc- tural design problems, and requiring large datasets for DNNs training. An adaptive machine learning technique called active learning is used in this thesis to accelerate the evolutionary optimization of complex structures. The active learner helps the Genetic Algorithms (GA) by predicting if the possible design is going to satisfy the required constraints or not. The approach does not need a trained surrogate model prior to the optimization. The active learner adaptively improve its own accuracy during the optimization for saving the required number of FEA evaluations. The results show that the approach has the potential to reduce the total required FEA evaluations by more than 50%. Lastly, the machine learning is used
to make recommendations for modeling choices while analyzing a structure using FEA. The decisions about the selection of appropriate modeling techniques are usually based on an analyst’s judgement based upon their knowledge and intuition from past experience. The machine learning-based approach provides recommendations within seconds, thus, saving significant computational resources for making accurate design choices.
... Where, z RS is the normalized value, x RS is the S th value of the R-variable, μ R , and σ R are the mean value and the standard deviation of the R-variable, respectively. The second common approach is the so-called Min-Max scaling with a fixed range (Pinar et al., 2010;Zare et al., 2013;Fahmy et al., 2016). A Min-Max scaling is typically represented via Eq. ...
This study presents a new hybrid method to develop seismic fragility curves for horizontally-curved steel I-girder bridges using Artificial neural network and logistic regression methods. The approach for developing fragility curves based on the assumption that engineering demand parameters follow the lognormal distribution for calculating the probability of damage occurrence. A sufficient number of input data including a set of earthquake ground motion records and macro-structural parameters together with the output data resulting from nonlinear structural analyses was assigned to neural network structure to achieve satisfactory approximations of responses. Logistic regression statistical method was used to determine the probability of occurrence or non-occurrence of limit states for earthquake ground motion parameters and structural characteristics. In this study, based on the estimation of engineering demand parameters, the proposed method is compared with the neural network method, simplified mathematical model and analytical method. The nonlinear time history analysis of three dimensional horizontally curve bridges were performed using the OpenSEES software. The statistical results indicate the accuracy and efficiency of the predicted limit state occurrence of the proposed method at a low computational cost. Comparison of fragility curves using the mentioned methods represent a proper estimation for slight, moderate, extensive and collapse limit states at different levels of seismic intensity.
