Scour around bridge piers is a well-known threat to bridge stability worldwide. It can cause losses in lives and the economy, especially during floods. Therefore, an artificial intelligence approach called artificial neural network (ANN) was used to predict the scour depth around bridge piers. The ANN model was trained with laboratory data, including pier width, flow velocity, particle diameter, sediment critical velocity, flow depth, and scour depth. The data was divided into 70% for training, 15 for validation, and 15% for testing. Besides, the ANN model was trained using various training algrthins and a single hidden layer with 20 neurons in the hidden layer. The results showed that the ANN model with Bayesian regularization backpropagation training algorithm provides a better predicted scour depth with a correlation coefficient (R) equal to 0. 9692 and 0.926 for training and test stages, respectively. Besides, it showed a low mean squared error (MSE), which was 0.0034 for training and 0.0066 for the test. These results were slightly better than the ANN with Levenberg-Marquardt backpropagation with R training equals 0.9552 (MSE training = 0.0047), and R test equals 0.838 (MSE test = 0.007).On the other hand, the ANN model with a scaled conjugate gradient backpropagation training algorithm showed worse predictions (R training = 0.7407 and R test = 0.6409). Besides, the ANN model shows better outcomes than the linear regression model. Finally, the sensitivity analysis has shown that the pier width is the most crucial parameter for estimating scour depth using the ANN model.
ABSTRACT: In this paper, artificial neural networks (ANNs) are used in attempt to obtain the strength of polymer-modified concrete (PMC). A database of 36 case records is used to develop and verify the ANN models. Four parameters are considered to have the most significant impact on the magnitude of (PMC) strength and are thus used as the model inputs. These include the Polymer/cement ratio, sand/cement ratio, gravel/cement ratio, and water/ cement ratio. The model output is the strength of (PMC). Multi-layer perceptron trained using the back-propagation algorithm is used. In this work, the feasibility of ANN technique for modeling the concrete strength is investigated. A number of issues in relation to ANN construction such as the effect of ANN geometry and internal parameters on the performance of ANN models are investigated. Design charts for prediction of polymer modified concrete strength are generated based on ANN model. It was found that ANNs have the ability to predict the strength of polymer modified concrete, with a very good degree of accuracy. The ANN models developed to study the impact of the internal network parameters on model performance indicate that ANN performance is reality insensitive to the number of hidden layer nodes, momentum terms or transfer functions. On the other hand, the impact of the learning rate on model predictions is more pronounced.keywords:; Artificial Neural networks; Strength; Polymer Modified Concrete; Modeling.
Local scour is a primary reason for bridge collapse, presenting a complex challenge due to the numerous factors influencing its occurrence. The complexity of local scour increases with clay-sand beds, particularly in predicting scour depth, as empirical equations are inadequate for such calculations. This study aims to predict local scour around cylindrical bridge piers in clay-sand beds using an artificial neural network (ANN) model. The ANN model was developed using 264 observations from various laboratory experiments. Eight variables were included in the ANN model: clay fraction, pier diameter, flow depth, flow velocity, critical sediment velocity, sediment particle size, bed shear strength, and pier Reynolds number. Sensitivity and statistical analyses were conducted to evaluate the impact of each variable and the accuracy of the ANN model in predicting local scour depth in clay-sand beds. The findings indicate that the ANN model predicted local scour with high accuracy, achieving a mean absolute percentage error (MAPE) of 14.6%. All dimensional variables significantly influenced the prediction of local scour depth, particularly clay fraction and bed shear strength, which were identified as the most crucial parameters. Finally, the MAPE values for local scour depth calculated using empirical equations were significantly higher than those for the ANN model, leading to an overestimation of local scour depth by the empirical equations.
Abstract. In this research, Artificial Neural Networks (ANNs) will be used in an attempt to predict collapse potential of gypseous soils. Two models are built one for collapse potential obtained by single oedemeter test and the other is for collapse potential obtained by double oedemeter test. A database of laboratory measurements for collapse potential is used. Six parameters are considered to have the most significant impact on the magnitude of collapse potential and are being used as an input to the models. These include the Gypsum content, Initial void ratio, Total unit weight, Initial water content, Dry unit weight, Soaking pressure. The output model will be the corresponding collapse potential. Multi-layer perceptron trainings using back propagation algorithm are used in this work. A number of issues in relation to ANN construction such as the effect of ANN geometry and internal parameters on the performance of ANN models are investigated. Information on the relative importance of the factors affecting the collapse potential are presented and practical equations for prediction of collapse potential from single oedemeter test and double oedemeter test in gypseous soils are developed. It was found that ANNs have the ability to predict the collapse potential from single oedemeter test and double oedemeter test in gypseous soil samples with a good degree of accuracy. The ANN models developed to study the impact of the internal network parameters on model performance indicate that ANN performance is sensitive to the number of hidden layer nodes, momentum terms, learning rate, and transfer functions. The sensitivity analysis indicated that for the models the results indicate that the initial void ratio and gypsum content have the most significant affect on the predicted the collapse potential.Keywords. Artificial Neural Networks, collapse potential, gypseous soils
In recent years, a number of researchers have adopted the wet packing (WP) approach to design different types of concrete mixes. Particle grading is a key to the optimization of the wet compactness density; for that reason, all empty spaces that exist in between large-size particles need to be completely filled with particles of smaller size. Previously-conducted studies in this field have been focused on measuring the particle size distribution’s packing density (PD) of the of granular matrices is the purpose of investigating how to increase the PD of cementitious materials. Thus, literature lacks models capable of predicting the optimal PD value. The current study collected and analyzed 216 datasets in order to construct a model for accurate prediction of PD. The main datasets were organized into two categories: modeling datasets and validation datasets. To configure the model in the best way, a hybrid gravitational search algorithm-artificial neural network (GSA-ANN) was also developed in this study. The findings confirmed ANN as an effective alternative for measuring the ultimate PD of cementitious pastes. ANN provided high levels of accuracy, practicality, and effectiveness in the process of predicting the PD value. Based on the final results, the implementation of the hybrid GSA-ANN technique causes a significant decrease in the number of tests conducted on experimental samples, which results in not only saving time and money, but also reducing the CO2 emission volume.
The Light Falling Weight Deflectometer (LFWD) was developed to estimate the in-situ elastic modulus directly to the layers near the base as subgrade and subbase layers. The field tests were carried out on selected sections from landfill project within Anbar Province. Furthermore, Forty test sections have been constructed and tested at the Civil Engineering Department- University of Anbar. All sections were tested using the ZFG 3000 model - LFWD in companion with the Plate Load Test (PLT) which were used as reference measures. Regression analyzes were performed to determine the best correlation between the elastic modulus obtained from LFWD and PLT tests. ANN model was used to calculate Evd and compare the regression statistical model. It was found that the ANN model showed a higher performance than regression analysis in predicting Evd. Satisfactory correlations were obtained, which showed that LFWD could be a promising device for in-situ characterizing of subsurface and subgrade layers.
AbstractConstruction of concrete structures involves at least two different main materials: concrete and steel. Design of these structures should be based on cost rather than weight minimization. In this work, least cost design of singly and doubly reinforced beams is done by applying of the Lagrangian multipliers method (LMM) under ultimate design constraint beside other constraints. Cost objective functions and moment constraints are derived and implemented within the optimization method. The optimum solution comparisons with conventional design methods are performed and the result reported, showing that the LMM can be successfully applied to the minimum cost deign of reinforced concrete beams without need for iterative trials. Optimum design solution surfaces have been developed. Good and reliable results have been obtained and confirmed by using standard design procedures. The artificial neural networks (ANN) has been trained with design data obtained from optimal design formulas. After successful trials, the model predicted the optimum depth of the beam sections and optimum areas of steel required for the problems with accuracy satisfying all design constraints.
Land cover assessment is a significant research area in GIS and remote sensing, aiding decision-makers in understanding land use changes' underlying forces and enabling effective actions. In general, Iraqi cities are experiencing severe degradation of agricultural lands due to population growth and residential development, impacting socio-economic and environmental quality. In addition, the deriving forces of transforming the lands from agricultural to other land cover types are not well understood. Research is needed to map and assess agricultural lands for better economic and environmental solutions. The study uses ANN-CA integration to predict agricultural land changes in Babil province, central Iraq. The CNN model achieved the highest accuracy, with a total land cover transformation of 2143.1 square kilometres between 2000 and 2020. the overall accuracy was 0.95, 0.93, and 0.90 based on images captured in 2020, 2000, 2010) respectively. This methodology is considered an efficient tool for monitoring agricultural lands and developing development plans in Iraq.