Title: An improved multi-objective genetic algorithm and data fusion in structural damage identification

Authors: Along Yu; Jiajia Ji; Shiyu Sun

Addresses: School of Physics and Electronic Electrical Engineering, Huaiyin Normal University, Huaian, 223300, China ' School of Electrical Engineering and Control Science, Nanjing Tech University, Nanjing, 211816, China ' School of Physics and Electronic Electrical Engineering, Huaiyin Normal University, Huaian, 223300, China

Abstract: With the aging of civil engineering structures, it is urgent to detect the damage status of structures for timely maintenance. Genetic algorithm has been gradually applied to structural damage identification owing to its powerful global search capability and better adaptability. In this paper, we present a novel multi-objective genetic algorithm based on fuzzy optimisation theory to identify damage for large-scale structures. Furthermore, fuzzy logic data fusion is implemented to process a large amount of data collected by displacement sensors, acceleration sensors and stress sensors in order to improve the accuracy of identification results. The experimental results show that the improved multi-objective genetic algorithm has faster convergence speed and higher computational efficiency than traditional genetic algorithm. Besides, the data fusion method can process the displacement parameter and the frequency mode parameter synchronously, which shows more reliable recognition results than single-class parameter identification.

Keywords: large-scale structures; genetic algorithm; damage identification; fuzzy optimisation; data fusion.

DOI: 10.1504/IJSN.2019.100087

International Journal of Security and Networks, 2019 Vol.14 No.2, pp.95 - 102

Received: 29 Nov 2018
Accepted: 01 Dec 2018
Published online: 07 Jun 2019 *

Full-text access for editors Full-text access for subscribers Purchase this article Comment on this article