A novel dynamic opposite learning enhanced Jaya optimization method for high efficiency plate–fin heat exchanger design optimization. (March 2023)

• Record Type: Journal Article
• Authors: Zhang, Lidong; Hu, Tianyu; Zhang, Linxin; Yang, Zhile; McLoone, Seán; Menhas, Muhammad Ilyas; Guo, Yuanjun
• Is Part Of: Engineering applications of artificial intelligence. Volume 119(2023)
• Publication Date: 2023-03
• Subjects: Plate–fin heat exchangers -- Jaya algorithm -- Optimal design -- Dynamic-opposite learning; 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.2022.105778
• Languages: English
• ISSNs: 0952-1976

Abstract

Abstract: A Plate–fin heat exchanger (PFHE) is a compact and efficient thermal device, whose performance strongly depends on its structural design. However, the design optimization of a PFHE is a mixed-integer optimization problem with a strong nonlinear characteristic, which presents significant challenges for existing optimization algorithms. Meta-heuristic algorithms (MAs) are competitive for solving complex non-linear optimization problems. In this paper, an improved dynamic-opposite learning Jaya (DOLJaya) method, the goal is to make the algorithm adaptable to each problem. The results of eighteen unimodal and multi-modal benchmarks and nine hybrid benchmarks demonstrate that the proposed DOLJaya has competitive robustness, efficiency and effectiveness for solving complex nonlinear problems compared to its popular counterparts. At the same time, we selected the optimization of the plate–fin heat exchanger as the industrial test benchmark for optimization, and the results of DOLJaya algorithm have been improved by a maximum average of 108.29% and 7.60% compared with the original Jaya, which are also satisfactory.