Intelligent Ballistic and High-Performance Mechanical Systems: A Systematic Review of Artificial Intelligence, Metaheuristic Optimization, Advanced Materials, Thermofluids, Structural Dynamics, And Reliability
Keywords:
intelligent ballistics, machine learning, metaheuristic optimization, armor materials, interior ballistics, structural dynamics, reliability, systematic review.Abstract
Objective: This systematic review maps the relationships among artificial intelligence (AI), metaheuristic optimization, advanced materials, thermofluids, structural dynamics, and reliability in ballistic and high-performance mechanical systems.
Methods: The review follows PRISMA 2020 guidelines and screens records published from 1 January 2020 to 18 October 2026 across Google Scholar, ScienceDirect, SpringerLink, Wiley Online Library, MDPI, CNKI, and Wanfang Data. A six-domain engineering appraisal framework rates model validation, uncertainty reporting, baseline comparison, reproducibility, scale bridging, and engineering relevance for each included study.
Results: Sixteen studies meet the eligibility criteria. Eight studies use experimental data or tests as their primary validation basis, seven use numerical validation, and one uses statistical inference with experimental data. Materials and structural dynamics appear most frequently, in ten and nine studies respectively. Artificial intelligence appears in seven studies, thermofluids in three, optimization in three, and reliability in three. Two studies couple learning models with optimization, and two studies link learning models with uncertainty quantification. Thermal and structural analysis share one study.
Conclusions: The evidence indicates strong progress within individual domains but weak coupling across domains. Future work requires experimentally validated, uncertainty-aware, surrogate-assisted frameworks for protective and launch systems.
