Info: Zenodo’s user support line is staffed on regular business days between Dec 23 and Jan 5. Response times may be slightly longer than normal.

Published October 1, 2020 | Version v1
Journal article Open

Structural Health Monitoring using Neural Networks in IoT and CPS paradigm- A Review

  • 1. Assistant Professor, Dept. of Civil Engineering, C. V. Raman Global University, Bhubaneswar

Contributors

Contact person:

Researcher:

Description

Wireless based smart structural health monitoring is very essential for smart city applications. The huge civil structures are more vulnerable to public safety that needs efficient smart monitoring. In the past, an attempt has been made to go for an efficient way of monitoring by using wires connected to the sensors. But due to the vulnerability of wires in the physical environment wireless SHM has been the focal point of research. But certain limitations make wireless monitoring inefficient such as delay in latency and loss of data. In this paper exhaustive review has been done on wireless systems of SHM along with the usage of many emerging technologies such as the Internet of Things (IoT), Cyber-Physical System (CPS), along with the usage of Neural Networks (NN) in damage detection problems. Civil Engineers give more emphasis to the physics of damages in SHM rather than designing an optimal SHM concerning networking aspects. So, we take into consideration both mechanical as well as networking aspects in SHM. This paper helps both civil engineering and computer science and engineering researchers/engineers to understand and design Smart Wireless Structural Health Monitoring using eminent technologies such as IoT, CPS and NN based damage assessment. This paper strives to comprehend the works of major areas of both domains of engineering so that the subject SHM is looked upon comprehensively from all spheres and development takes place using new or better technologies taking it in the forum of interdisciplinary research and discussion.

Files

IJSRED-V3I5P108 (2).pdf

Files (854.2 kB)

Name Size Download all
md5:0fbed69bce13b692dc14e84e1deffc3c
854.2 kB Preview Download