Pavement maintenance and rehabilitation prioritization are conducted based on the accessibility of overall measures for evaluating the condition of each section in the pavement network. Regularly, the pavement condition of each section has been evaluated by some common condition indicators. One of the most important indicators is the present serviceability index (PSI) which is adapted to depict the functional performance regarding ride quality. The main aim of this study is to develop a prediction model of ride quality for flexible pavement using the fuzzy logic technique. The data of input variables are extracted from the database of Long-Term Pavement Performance (LTPP). The research involved 36 pavement sections with 319 data samples for pavement networks of different states in the USA. The ride quality measure which is PSI estimated by the AASHTO equation represents the output variable, whereas patching area, cracking length, slope variance, and rut depth are considered input variables. The results showed that the fuzzified model of ride quality prediction has a decent accuracy with a high determination coefficient. In addition, based on the testing results, the developed prediction model showed a strong accuracy to predict the ride quality index
Abstract:This study explores the potential of back propagation neural networks (BPNN) computingparadigm to predict the ultimate bearing capacity of shallow foundations on cohesionlesssoils. The data from 97 load tests on footings (with sizes corresponding to those of realfootings and smaller sized model footings) were used to train and validate the model. Fiveparameters are considered to have the most significant impact on the magnitude ofultimate bearing capacity of shallow foundations on cohesionless soil and are thus used asthe model inputs. These include the width of the footing, depth of embedment, length towidth ratio, dry or submerge unit weight and angle of internal friction of the soil. Themodel output is the ultimate bearing capacity. Performance of the model wascomprehensively evaluated. The values of the performance evaluation measures such ascoefficient of correlation, root mean square error, mean absolute error reveal that themodel can be effectively used for the bearing capacity prediction. BPNN model iscompared with the values predicted by most commonly used bearing capacity theories.The results indicate that the model perform better than the theoretical methods.KEYWORDS: Ultimate bearing capacity; Shallow foundations; cohesionless soil; backpropagation neural network (BPNN); prediction
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.
Several different deterministic and probabilistic mathematical approaches have been used to develop modal split models. The data collected by a questionnaire survey approach is frequently associated with subjectivity, imprecision, and ambiguity. additionally, several linguistic terms are used to express some of the transportation planning variables. This can be solved by modeling mode choosing behavior with artificial intelligence techniques such as fuzzy logic. In this research, Ramadi city in Iraq has been selected as a study area. For the purpose of obtaining data, the study area was divided into traffic analysis zones (TAZ). The total number of traffic zones was set as 28 traffic zones, 22 were internal traffic zones and 6 external traffic zones. Field surveys and questionnaires are used to collect data on traffic, land use, and socioeconomic characteristics factors (age, gender, vehicle ownership, family income, trip purpose, trip origin and destination, trip time, waiting duration, duration inside mode, trip origin and destination, trip cost, and type of mode used for transport). The results showed that the modal split models based on the fuzzy inference system can deal with linguistic variables as well as address uncertainty and subjectivity and they gave very good prediction accuracy for future prediction. Fuzzy inference system proved that all factors affected the mode choice with a very strong correlation coefficient (R) equal to 93.1 for general trips but when the results were compared with multiple linear regression model found that the correlation coefficient (R) equal to 28.9 for general trips and the most influential factors on the mode choice are car ownership, age and trip cost. Thus, it can be concluded that fuzzy logic models were more capable of capturing and integrating human knowledge in mode selection behavior. In addition, this study will help decision-makers to plan transportation policies for Ramadi city
Asphalt pavement temperatures were estimated at surface and depth of 50 mm. Differences between estimated maximum surface temperatures and maximum air temperatures were found to be remarkably high, whereas the minimum surface temperatures were slightly different from minimum air temperatures. Different studies showed that the maximum pavement temperatures at depth (50 mm) were less than that of the maximum surface temperatures, whereas, minimum pavement temperature at the same depth showed slightly higher readings than that of the minimum surface temperatures.Algorithms that discussed in this research work found to produce remarkably different estimations of depth temperatures. The undergoing research work aims to cast light on the performance of these models in terms of data regarding Anbar province of Iraq.
In the civil engineering, the prediction of cracks for tunnel lining is too hard because it depends by different factors for example concrete strength, tunnel operation conditions, stress and geological surroundings. The aim of this study is to design a Fuzzy inspect System (FIS) for evaluating the concrete cracks of tunnel lining. Fuzzy logic is a method to signify a type of uncertainty which is understandable for user. The system has been designed to meet permit crack formula that issued in “Highway Tunnel Design Specifications”. When the maximal permit crack width as example is chosen as 0.7mm, 1.2mm and 3.3mm separately the fuzziness set accordingly is Minor , moderate and severe. The average error for the predicted crack (element sample) in FIS is 8.34%. The fuzzy evaluation model is based on the information of a real in-service PESHRAW highway tunnel, which reflects field status. Therefore, this evaluation is comfortable.
The purpose of this paper is to investigate the relationship between the Ultrasonic Pulse Velocity (UPV) and the compressive strength and the flexural strength of hardened concrete when subjected to different concentrations of sulfate attacks. The specimens used in the studies were made of concrete with different water-cement ratios (w/c). The UPV measurement and compressive and flexural strengths tests were carried out for concrete specimens of ages (4-40) days. The experimental results show that the relationship between UPV and the compressive and the flexural strengths of concrete is significantly influenced by age and the concentration of sulfate attack. The UPV and the compressive strength of concrete grow with age, but the growth rate varies with w/c ratio. It is found that with the same concentration of sulfate attack, a clear relationship curve can be drawn to describe the UPV and compressive and flexural strengths of hardened concrete. This paper presents the UPV-strength relationship curves for concrete having different (w/c) ratios subjected to different concentrations of sulfate attack. These curves are thought to be suitable for prediction of hardened concrete strength with a measured UPV value when sulfate attack is considered. It is concluded that the UPV increases with the increase of the compressive and flexural strength. The observed range for UPV was (3.5 to 4.75 km/sec) corresponds to (24 to 28.5 N/mm2) for compressive strength and to (4.6 to 6.5 N/mm2) for flexural strength. The UPV decreases with the increase of the concentration of sulfate exposure. The obtained maximum reduction in UPV was 31.6% with respect to the control spacemen at age of 40 days.
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.
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
Crack monitoring of pavements is an ever-evolving technology with new crack identification technologies being introduced frequently. Although older technologies consisted of physical removing the pavement section using coring, however new methods are available that are non-destructive and yield a higher performance than conventional technologies. This paper compiles various crack monitoring technologies such as wireless sensor networks, photo imaging, laser imaging, 3D road surface profile scans, acoustics wave propagation technology, embedded strain sensors and onboard vehicle sensors that majorly use an artificial intelligence algorithm to identify and categorize the cracks. The research also includes the use of convolutional neural network that can be used to analyze pavement images and such neural network can localize and classify the cracks for crack initiation and propagation stage. The research concludes with the favor of using the optical imaging technology called Syncrack which serves better performance in terms of time of prediction by 25% and accuracy by 30% when compared to other sensing technologies.
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.