A novel version of grey wolf optimizer based on a balance function and its application for hyperparameters optimization in deep neural network (DNN) for structural damage identification. (December 2022)

• Record Type: Journal Article
• Authors: Cuong-Le, Thanh; Minh, Hoang-Le; Sang-To, Thanh; Khatir, Samir; Mirjalili, Seyedali; Abdel Wahab, Magd
• Is Part Of: Engineering failure analysis. Volume 142(2022)
• Publication Date: 2022-12
• Subjects: Structural damage identification -- New balance Grey Wolf Optimizer -- Deep neural network -- Hyper parameters -- Optimization; System failures (Engineering) -- Periodicals; Fracture mechanics -- Periodicals; Reliability (Engineering) -- Periodicals; Pannes -- Périodiques; Rupture, Mécanique de la -- Périodiques; Fiabilité -- Périodiques; Fracture mechanics; Reliability (Engineering); System failures (Engineering); Periodicals; Electronic journals; 620.112
• DOI: 10.1016/j.engfailanal.2022.106829
• Languages: English
• ISSNs: 1350-6307

Abstract

Highlights: A new balance of grey wolf optimizer (NB-GWO) was proposed. A new stage of balance between the ability of exploitation and exploration. 23 classical benchmark functions are verified. NB-GWO performs better in exploitation and exploration compared to the other algorithms. An enhanced DNN was proposed based on NB-GWO for the damage detection problems. The hyperparameters in DNN were optimized using NB-GWO. Abstract: In this paper, a new method has been proposed to optimize the hyper parameters in Deep neural network (DNN). For this purpose, a new version of Grey Wolf Optimizer named New Balance Grey Wolf Optimizer (NB-GWO) is successfully developed for the first time. NB-GWO introduces an equation to control the movement strategies at each iteration. Based on this equation, the exploitation ability will be prioritized during the first few iterations to improve the convergence rate and gain quick access to potential search spaces. Meanwhile, during the last few iterations, the exploration ability will be biased toward exploitation to increase the opportunities of escaping the local optima's problem or exploring new spaces with the hope of finding better solutions. Because of the diversity of movement strategies, the NB-GWO has established a better balance between the ability of exploitation and exploration than that of in the original GWO. To demonstrate the effectiveness of NB-GWO, 23 classical benchmark functions combined with eight well-known optimization algorithms are used to evaluate the performance of NB-GWO as the first example. Then, NB-GWO will be used to optimize the hyper parameters in deep neural networks (DNN) for damage detection in 2D concrete frame. The results show that NB-GWO is a grown-up version of GWO, the results obtained in this work have proved the effectiveness and reliability of NB-GWO in solving optimization problems, especially, for optimizing the hyper parameters in DNN.