A modified adaptive guided differential evolution algorithm applied to engineering applications. (August 2022)

• Record Type: Journal Article
• Authors: Houssein, Essam H.; Rezk, Hegazy; Fathy, Ahmed; Mahdy, Mohamed A.; Nassef, Ahmed M.
• Is Part Of: Engineering applications of artificial intelligence. Volume 113(2022)
• Publication Date: 2022-08
• Subjects: Adaptive guided differential evolution algorithm -- Solid oxide fuel cell -- Meta-heuristic algorithms -- Parameter estimation -- mAGDE; Engineering -- Data processing -- Periodicals; Artificial intelligence -- Periodicals; Expert systems (Computer science) -- Periodicals; Ingénierie -- Informatique -- Périodiques; Intelligence artificielle -- Périodiques; Systèmes experts (Informatique) -- Périodiques; Artificial intelligence; Engineering -- Data processing; Expert systems (Computer science); Periodicals; 620.00285
• DOI: 10.1016/j.engappai.2022.104920
• Languages: English
• ISSNs: 0952-1976

Abstract

Abstract: This paper develops a robust strategy based on integrating three mutation phases and adapted control parameters into the Adaptive Guided Differential Evolution algorithm called (mAGDE) to improve diversity and exploration of the original AGDE. The mAGDE performance is evaluated using IEEE CEC'2020 test suite. Furthermore, the mAGDE is employed to identify the solid oxide fuel cell (SOFC) model optimal parameters. Two modes of SOFC operation are investigated, steady and transient states. The results obtained from the proposed mAGDE are compared with a number of recent, well-established and reputed meta-heuristics, including Particle swarm optimization, Teaching learning-based optimization, Whale optimization algorithm, Harris hawks optimization, Marine predators algorithm, Archimedes optimization algorithm, Differential evolution, and the original AGDE. Additionally, the statistical parameters that measure the performance of the proposed optimizer and the other competitors are calculated. The main finding demonstrated the preference and robustness of the suggested mAGDE in constructing the SOFC circuit that closely converges to the actual one. During the steady-state operation, the best fitness value obtained via the suggested mAGDE for operation at 1273 K is 2.2995E−06, while in the transient-state operation, the best SMSE is 1.04. The average cost function is decreased by 43.33% compared to the one obtained by the original AGDE. From the aforementioned assessments, it can be concluded that the proposed mAGDE is outstanding and promising. Highlights: This paper introduces a modified mAGDE based on the integration of a modified three-phases AGDE with the DE_SPA algorithm. A modified three-phases AGDE has been introduced to maintain diversity and convergence of the evolutionary process. The CEC'2020 test suite problems are used to demonstrate the performance mAGDE against other competitors. Applying for first time mAGDE to identify the optimal parameters of SOFC model. The robustness of the proposed strategy-based mAGDE is proved.