Open Science Research Excellence

O Zarrin

Publications

2

Publications

2
10003177
Design of Roller Compacting Concrete Pavement
Abstract:
The quality of concrete is usually defined by compressive strength, but flexural strength is the most important characteristic of concrete in a pavement which control the mix design of concrete instead of compressive strength. Therefore, the aggregates which are selected for the pavements are affected by higher flexural strength. Roller Compacting Concrete Pavement (RCCP) is not a new construction method. The other characteristic of this method is no bleeding and less shrinkage due to the lower amount of water. For this purpose, a roller is needed for placing and compacting. The surface of RCCP is not smooth; therefore, the most common use of this pavement is in an industrial zone with slower traffic speed which requires durable and tough pavement. For preparing a smoother surface, it can be achieved by asphalt paver. RCCP decrease the finishing cost because there are no bars, formwork, and the lesser labor need for placing the concrete. In this paper, different aspect of RCCP such as mix design, flexural, compressive strength and focus on the different part of RCCP on detail have been investigated.
Keywords:
Flexural Strength, Compressive Strength, Pavement, Asphalt.
1
10009640
Introduce Applicability of Multi-Layer Perceptron to Predict the Behaviour of Semi-Interlocking Masonry Panel
Abstract:
The Semi Interlocking Masonry (SIM) system has been developed in Masonry Research Group at the University of Newcastle, Australia. The main purpose of this system is to enhance the seismic resistance of framed structures with masonry panels. In this system, SIM panels dissipate energy through the sliding friction between rows of SIM units during earthquake excitation. This paper aimed to find the applicability of artificial neural network (ANN) to predict the displacement behaviour of the SIM panel under out-of-plane loading. The general concept of ANN needs to be trained by related force-displacement data of SIM panel. The overall data to train and test the network are 70 increments of force-displacement from three tests, which comprise of none input nodes. The input data contain height and length of panels, height, length and width of the brick and friction and geometry angle of brick along the compressive strength of the brick with the lateral load applied to the panel. The aim of designed network is prediction displacement of the SIM panel by Multi-Layer Perceptron (MLP). The mean square error (MSE) of network was 0.00042 and the coefficient of determination (R2) values showed the 0.91. The result revealed that the ANN has significant agreement to predict the SIM panel behaviour.
Keywords:
Semi interlocking masonry, artificial neural network, ANN, multi-layer perceptron, MLP, displacement, prediction.