Improvement and Application of Hybrid Firefly Algorithm

Aiming at the problem of poor global search ability and slow convergence speed when solving optimization problems, this paper proposes improved hybrid firefly algorithm (HFA). HFA improves the position updating method, mutation strategy, chaotic search method and evolution strategy of the population. Specifically, the improved position update formula considers both the effect of high-brightness fireflies on position-updated fireflies, and the effects of the optimal firelfy on position-updated fireflies. At the same time, a method of adaptive adjustment parameters in the position update formula is presented, which makes the position update method exhibit strong global search ability and local search ability in the initial stage and the later stage of iteration, respectively. In addition, a combined mutation operator is introduced into HFA, which effectively takes the local search and global search ability of the algorithm into account. Since chaotic search exhibits good ergodicity, an operation of randomly moving all fireflies in the population according to chaotic search is given, which enhances the ability of the algorithm to traverse the whole search space, and further improves the global search ability of the algorithm. To verify the effectiveness of HFA, 28 CEC2017 test problems are selected. The calculation results of 28 CEC2017 test problems show that compared with other algorithms, the accuracy of HFA is obviously better than that of other algorithms. Finally, HFA and other intelligent optimization methods in the literatures are used to optimize the structural parameters of cantilever beams. The optimization results show that the weight of the cantilever beam obtained by HFA is obviously smaller than other algorithms. The calculation results of CEC2017 test problems and practical problem show that the solving quality of HFA is obviously better than other algorithms.