On the comparative performance of recent swarm intelligence based algorithms for optimization of real-life Sterling cycle operated refrigeration/liquefaction system

Raja B. D., Patel V. K., Savsani V. J., YILDIZ A. R.

ARTIFICIAL INTELLIGENCE REVIEW, vol.56, no.2, pp.1297-1317, 2023 (SCI-Expanded) identifier identifier

  • Publication Type: Article / Article
  • Volume: 56 Issue: 2
  • Publication Date: 2023
  • Doi Number: 10.1007/s10462-022-10201-9
  • Journal Indexes: Science Citation Index Expanded (SCI-EXPANDED), Scopus, ABI/INFORM, Aerospace Database, Applied Science & Technology Source, Communication Abstracts, Compendex, Computer & Applied Sciences, Educational research abstracts (ERA), Index Islamicus, INSPEC, Library and Information Science Abstracts, Library, Information Science & Technology Abstracts (LISTA), Metadex, Psycinfo, zbMATH, Civil Engineering Abstracts
  • Page Numbers: pp.1297-1317
  • Keywords: Swarm intelligence algorithm, Constraint optimization, Comparative performance, Constraint handling techniques, Convergence behaviour, MULTIOBJECTIVE OPTIMIZATION
  • Bursa Uludag University Affiliated: Yes


In the recent past year of 2020-2021, researchers proposed many swarm intelligence based algorithms. In the present work, an effort has been made to compare the performance of these algorithms for the real-life constraint optimization problem. Swarm intelligence-based algorithms developed during 2020-2021 such as GEO, WHO, MPA, JSO, ChoA, MA, BWO, AO, COOT, and TSA are considered in the present work. These algorithms are implemented for the performance optimization of the Sterling cycle operated refrigeration/liquefaction system. Four operating variables and two output constraints of the Sterling cycle based system are considered for optimization. Comparative results are presented with statistical data to judge the performance of the algorithm and subsequently identify the statistical significance and rank of the algorithm. The effect of various constraint handling methods on the performance of algorithms is evaluated and presented. The behaviour of constraint handling methods is analyzed and presented with statistical data. Statistical analysis is also performed to observe whether the constraint handling methods produce a significant difference on the output of the considered algorithm. The effect of output constraints on the performance of algorithms is also evaluated and presented. Finally, the convergence behaviour of the competitive algorithms is obtained and demonstrated.