Springer proceedings in physics, Год журнала: 2024, Номер unknown, С. 101 - 107
Опубликована: Янв. 1, 2024
Язык: Английский
Springer proceedings in physics, Год журнала: 2024, Номер unknown, С. 101 - 107
Опубликована: Янв. 1, 2024
Язык: Английский
International Journal on Interactive Design and Manufacturing (IJIDeM), Год журнала: 2025, Номер unknown
Опубликована: Март 17, 2025
Язык: Английский
Процитировано
0Scientific Reports, Год журнала: 2025, Номер 15(1)
Опубликована: Апрель 18, 2025
Язык: Английский
Процитировано
0International Journal of Structural Integrity, Год журнала: 2025, Номер unknown
Опубликована: Апрель 20, 2025
Purpose Auxetic tubular structures with negative Poisson’s ratios have gained significant attention in biomedical applications, particularly vascular and esophageal stents, due to their potential reduce embolism risks. This study aims investigate the nonlinear vibration characteristics of such develop accurate predictive models using machine learning (ML) techniques. Design/methodology/approach The governing equations auxetic tubes are derived Hamilton’s principle von-Kármán’s assumptions, while Malek-Gibson relations determine effective mechanical properties. behavior polylactic acid (PLA) is experimentally analyzed through tensile testing digital image correlation (DIC) additional insights from scanning electron microscopy. solved via Ritz method, vibrational assessed direct displacement control approach. Predictive modeling performed six ML algorithms – CatBoost, decision tree, random forest, gradient boosting extreme (XGBoost) support vector regression (SVR) along an artificial neural network (ANN). Response surface methodology employed optimize effects edge supports, radius cell geometry on behavior. Findings results demonstrate a strong agreement between ML/ANN predictions analytical confirming reliability developed models. analysis reveals that variations significantly influence response structures. optimized configurations enhance structural performance, making these metastructures highly suitable for applications. Originality/value uniquely integrates modeling, experimental ML-based comprehensively assess metastructures. findings provide valuable design next-generation improving performance expanding
Язык: Английский
Процитировано
0Thin-Walled Structures, Год журнала: 2024, Номер 200, С. 111984 - 111984
Опубликована: Май 7, 2024
Язык: Английский
Процитировано
3International Journal of Mechanical Sciences, Год журнала: 2024, Номер unknown, С. 109840 - 109840
Опубликована: Ноя. 1, 2024
Язык: Английский
Процитировано
3Опубликована: Янв. 22, 2024
This study is a pioneering endeavor to investigate the capabilities of Large Language Models (LLMs) in addressing conceptual questions within domain mechanical engineering with focus on mechanics. Our examination involves manually crafted exam encompassing 126 multiple-choice questions, spanning various aspects mechanics courses, including Fluid Mechanics, Mechanical Vibration, Engineering Statics and Dynamics, Mechanics Materials, Theory Elasticity, Continuum Mechanics. Three LLMs, ChatGPT (GPT-3.5), (GPT-4), Claude (Claude-2.1), were subjected evaluation against faculties students with/without background. The findings reveal GPT-4’s superior performance over other two LLMs human cohorts answering across topics, except for signals potential future improvements GPT models handling symbolic calculations tensor analyses. performances all significantly improved explanations prompted prior direct responses, underscoring crucial role prompt engineering. Interestingly, GPT-3.5 demonstrates prompts covering broader domain, while GPT-4 excels focusing specific subjects. Finally, exhibits notable advancements mitigating input bias, as evidenced by guessing preferences humans. unveils substantial highly knowledgeable assistants both pedagogy scientific research.
Язык: Английский
Процитировано
2Acta Mechanica Sinica, Год журнала: 2024, Номер 40(8)
Опубликована: Июнь 25, 2024
Процитировано
1Опубликована: Янв. 1, 2024
Язык: Английский
Процитировано
0Опубликована: Янв. 1, 2024
Download This Paper Open PDF in Browser Add to My Library Share: Permalink Using these links will ensure access this page indefinitely Copy URL DOI
Язык: Английский
Процитировано
0International Journal of Mechanical Sciences, Год журнала: 2024, Номер 279, С. 109487 - 109487
Опубликована: Окт. 1, 2024
Язык: Английский
Процитировано
0