A three-stage learning algorithm for deep multilayer perceptron (DMLP) with effective weight initialisation based on sparse auto-encoder is proposed in this paper, which aims to overcome difficulties in training deep neural networks with limited training data in high-dimensional feature space. At the first stage, unsupervised learning is adopted using sparse auto-encoder to obtain the initial weights of the feature extraction layers of the DMLP. At the second stage, error back-propagation is used to train the DMLP by fixing the weights obtained at the first stage for its feature extraction layers. At the third stage, all the weights of the DMLP obtained at the second stage are refined by error back-propagation. Network structures an

A novel demountable shear connector is proposed to link a concrete slab to steel sections in a way that resulting steel-concrete composite floor is demountable, i.e. it can be easily dismantled at the end of its service life. The proposed connectors consist of two parts: the first part is a hollow steel tube with internal threads at its lower end. The second part is a compatible partially threaded bolted stud. After linking the stud to the steel section, the hollow steel tube can be fastened over the threaded stud, which create a complete demountable shear connector. The connector is suitable for use in both composite bridges and buildings, and using cast in-situ slabs, precast solid slabs, or hollow-core precast slabs. A series of push-off

One of the most important challenges facing the designers of the sewerage system is the corrosion of sewers due to the influence of sewerage contaminates which lead to failure of the main lines of sewers. In this study, a reference mix of 1: 1.5: 3 was used and the 4% Flocrete PC200 by weight of cement was added to the same mixing ratio in the second mixture. Twenty-four samples were tested for each mixture, 12 of which were used to compression strength test in ages (7, 14 and 28) day and six samples were submerged after 28 days of wet treatment at (5 and 10) % concentrations of sulfuric acid. The other six samples were painted after 28 days of wet treatment with coating Polyurethane and after 24 hours were flooded with a concentrat

Rutting is a crucial concern impacting asphalt concrete pavements’ stability and long-term performance, negatively affecting vehicle drivers’ comfort and safety. This research aims to evaluate the permanent deformation of pavement under different traffic and environmental conditions using an Artificial Neural Network (ANN) prediction model. The model was built based on the outcomes of an experimental uniaxial repeated loading test of 306 cylindrical specimens. Twelve independent variables representing the materials’ properties, mix design parameters, loading settings, and environmental conditions were implemented in the model, resulting in a total of 3214 data points. The network accomplished high prediction accuracy with an R

This paper presents a study to investigate the behavior of post-tensioned segmental concrete beams that exposed to high-temperature. The experimental program included fabricating and testing twelve simply supported beams that divided into three groups depending on the number of precasting concrete segments. All specimens were prepared with an identical length of 3150 mm and differed in the number of the incorporated segments of the beam (9, 7, or 5 segments). To simulate the genuine fire disasters, nine out of twelve beams were exposed to a high-temperature flame for one hour. Based on the standard fire curve (ASTM – E119), the temperatures of 300◦C (572◦F), 500◦C (932◦F), and 700◦C (1292◦F) were adopted. Consequently,

This paper presents a study to investigate the behavior of post-tensioned segmental concrete beams that exposed to high-temperature. The experimental program included fabricating and testing twelve simply supported beams that divided into three groups depending on the number of precasting concrete segments. All specimens were prepared with an identical length of 3150 mm and differed in the number of the incorporated segments of the beam (9, 7, or 5 segments). To simulate the genuine fire disasters, nine out of twelve beams were exposed to a high-temperature flame for one hour. Based on the standard fire curve (ASTM – E119), the temperatures of 300◦C (572◦F), 500◦C (932◦F), and 700◦C (1292◦F) were adopted. Consequently,

Productivity estimating of ready mixed concrete batch plant is an essential tool for the successful completion of the construction process. It is defined as the output of the system per unit of time. Usually, the actual productivity values of construction equipment in the site are not consistent with the nominal ones. Therefore, it is necessary to make a comprehensive evaluation of the nominal productivity of equipment concerning the effected factors and then re-evaluate them according to the actual values.

In this paper, the forecasting system was employed is an Artificial Intelligence technique (AI). It is represented by Artificial Neural Network (ANN) to establish the predicted model to estimate wet ready mixe