Search

This paper presents the numerical simulation of permeable, semi-permeable and impermeable crack interaction study in 2D piezoelectric domains using an element-free Galerkin method (EFGM). The elect...

Deep learning is a computer-based modeling approach, which is made up of many processing layers that are used to understand the representation of data with several levels of abstraction. This review paper presents the state of the art in deep learning to highlight the major challenges and contributions in computer vision. This work mainly gives an overview of the current understanding of deep learning and their approaches in solving traditional artificial intelligence problems. These computational models enhanced its application in object detection, visual object recognition, speech recognition, face recognition, vision for driverless cars, virtual assistants, and many other fields such as genomics and drug discovery. Finally, this paper also showcases the current developments and challenges in training deep neural network.

For the present work, the dynamic response of a cracked-cantilevered glass–epoxy composite beam has been investigated using numerical as well as experimental studies. Linear free vibration of a cantilevered composite beam with an open edge crack is considered. The presence of crack certainly changes the dynamic behaviour such as natural frequencies and natural modes of the system. A proper investigation of this behaviour is essential to understand and perform an improved way of online condition monitoring based on vibration signals of such systems. The primary objective of this work is to convert a continuous system into an equivalent single degree of freedom (SDOF) system by applying the lumped parameter concept. Subsequently, a reduction in the equivalent stiffness has been observed due to the presence of a crack by using fracture mechanics approach. Variation of material properties of glass epoxy composites are along all the three dimensions, however, the properties in transverse direction are of our main concern. The dynamic behaviour of such cracked composite beams is firstly computed using the reduced equivalent dynamical model of the beam with varying crack locations. Subsequently, experiments are performed to obtain the natural frequency of the cracked-composite beam, results are also obtained using finite element packages using numerical computation. Results obtained from the lumped parameter model and numerical simulations are compared with that of experimental results. A strong agreement between the results obtained using various methods was observed. Finally, a wide parametric study is performed using these methods for various geometric and crack parameters.