Waqas Ahmed

In recent years, convolutional neural networks (CNNs) have been used for optical flow estimation with great success. Convolutional neural networks are multilayer’s structures, highly competent to estimate the complex, nonlinear transformation between input imagery and the output. At present, it is one of the top and dynamic research domains in image processing. Modern researchers of optical flow have combined numerous strategies and ideas from traditional methods with deep learning settings, consequently producing massive amount of work within few years. In this paper we present an analysis of deep learning methods for optical flow estimation. We highlight the important features, key components and discuss factors for benefits and limitations of deep learning schemes of optical flow estimation. We also compare the performance in terms of accuracy, size and training procedures of different models based on convolutional neural networks proposed by modern researchers.

Fiber-reinforced polymer (FRP) composite bridges are usually constructed for rapid installation. The durability of the bridge is increased by stiffness, strength to weight ratio, and corrosion resistance. The main factors on which the design of the composite sandwiched bridge considerably depends are ply layers, material system, alignment of ply angles, and thickness of the core. In this work, a parametric design study for a bridge using finite element analysis (FEA) is presented. Two types of composite materials—carbon fiber reinforced polymer (CFRP) and glass fiber reinforced polymer (GFRP)—were used as the sandwich structure’s skin, and three different types of woods were used as a core. Different design configurations were acquired based on material and instability constraints by using Euro-codes. Failure criterion of Tsai-Hill, Tsai-Wu, MS, equivalent stress, and maximum shear stress were implemented to analyze the overall failure of the bridge deck under Ultimate Limit State (ULS) conditions. The total deformation was examined under Serviceability Limit State (SLS) conditions, and the results were compared and verified by the previous study. The core was also examined using the core-factor and increasing the thickness of the core through parametric modeling.

Radomes are usually constructed from sandwich structures made of materials which usually have a low dielectric constant so that they do not interfere with electromagnetic waves. Performance of the antenna is increased by the appropriate assortment of materials enabling it to survive under marine applications, and it depends on composite strength-to-weight ratio, stiffness, and resistance to corrosion. The design of a sandwich core submarine radome greatly depends on the material system, number of layers, orientation angles, and thickness of the core material. In this paper, a conceptual design study for a sandwich core submarine radome is carried out with the help of finite element analysis (FEA) using two unidirectional composite materials—glass fiber reinforced polymer (GFRP) and carbon fiber reinforced polymer (CFRP)—as a skin material and six different core materials. Conceptual designs are obtained based on constraints on the composite materials’ failure, buckling, and strength. The thickness of the core is reduced under constraints on material and buckling strength. Finite element analysis software ANSYS WORKBENCH is used to carry out all the simulations.