Performance of swarm intelligence based chaotic meta-heuristic algorithms in civil structural health monitoring

发布时间: 2021-02-01 00:00:00
期刊: Measurement
doi: 10.1016/j.measurement.2020.108533
作者: Swagato Das;Purnachandra Saha
摘要: Whale Optimization Algorithm, Eagle Perching Optimization, Dragonfly Algorithm, Flower Pollination Algorithm, Bird Swarm Algorithm (BSA) and Firefly Algorithm (FA), are few of the Swarm-Intelligence based optimization techniques that have been developed by researchers and tested on benchmark functions only and have not been explored for real-life structural health monitoring (SHM). This paper deals with the use of these six algorithms for SHM on real-life quarter-scaled ASCE-Benchmark structure using stiffness-based objective function. It is observed that the performances of all the algorithms are smooth except for BSA and FA due to increased randomness and entrapment in local optima. Hence to improve their performances, modification has been introduced using the chaotic maps in the foraging behaviour of BSA and randomized movement of FA. With the proposed chaotic modifications, it is observed that Chaotic BSA and FA shows good accuracy in damage analysis, with 95% of damage results falling well-within the acceptable range.