Prediction of buckling damage of steel equal angle structural members using hybrid machine learning techniques

Scientific Reports, Год журнала: 2025, Номер 15(1)

Опубликована: Фев. 8, 2025

This article deals with prediction of buckling damage steel equal angle structural members using a surrogate model combining machine learning and metaheuristic optimization technique. In particular, hybrid Artificial Intelligence (AI)-based involving Neural Network (ANN) Particle Swarm Optimization (PSO) was developed calibrated for the problem at hand. For this purpose, database concerning compression tests constructed from available resources geometry variables such as length, width, thickness, mechanical properties materials yield strength initial imperfections (i.e. residual peak stress geometric imperfections) critical load columns. The PSOANN adopted because its capability is higher than traditional technique - i.e. scaled conjugate gradient (SCG). Indeed, ANN trained by PSO delivered better performance in terms RMSE, MAE, ErrorStD, R2 Slope comparison to SCG, instance. RMSE decreases 0.141 0.055; MAE 0.108 0.042; increases 0.749 0.959, when switching alone PSOANN, respectively. Moreover, Partial Dependence (PD) investigation performed interpret "black-box" model.

Язык: Английский

---

Physics-based modeling and intelligent optimal decision method for digital twin system towards sustainable CNC equipment

Robotics and Computer-Integrated Manufacturing, Год журнала: 2025, Номер 95, С. 103028 - 103028

Опубликована: Апрель 11, 2025

Язык: Английский

---

Edge device deployment for intelligent machine tools: A lightweight and interpretable tool wear monitoring method considering wear behavior

Robotics and Computer-Integrated Manufacturing, Год журнала: 2025, Номер 95, С. 103033 - 103033

Опубликована: Май 6, 2025

Язык: Английский

---

Titreşim Optimizasyonu için Akıllı Cnc Router Sistem Tasarımı

Gazi Üniversitesi Fen Bilimleri Dergisi Part C Tasarım ve Teknoloji, Год журнала: 2025, Номер unknown, С. 1 - 1

Опубликована: Май 16, 2025

Dünyada dijital teknolojiler ile ivmelenen Endüstri 4.0, geleneksel üretim sistemlerine entegre edilerek, sektörünü önemli boyutta dönüştürmekte ve mevcut endüstriyel süreçlerin dijitalleştirilmesini amaçlamaktadır. Bu dijitalleştirme, insan hatası faktörüne bağlı olmayan, akıllı kendisini uyarlayan, kalitesi verimi daha yüksek, hızlı bir imalat sanayinin en büyük adımı olmaktadır. çalışmada, olması gereken titreşim seviyesi istenilen kaliteye göre kesme parametrelerini optimize edebilen CNC Router tasarımı montajı yapılmıştır. Router’ın tahmin etmesi gerçek zamanlı olarak güncellemesi için Stepcraft Router’a ait makine kontrol kartı, sürücüleri, fener mili, güç kaynağı değiştirilmiştir. Ayrıca veri toplama parametrelerine müdahale edebilmek ara yüz gerçekleştirilmiştir. Sonuç olarak, beklenilen edebilen, operatör müdahalesi olmadan operasyon sürecine karar verebilen kendini uyarlayan özgün elde edilmiştir.

---

Tribological impact and surface roughness prediction in nano-MQL assisted AA2024 machining

Proceedings of the Institution of Mechanical Engineers Part J Journal of Engineering Tribology, Год журнала: 2025, Номер unknown

Опубликована: Июнь 4, 2025

In this study, we investigate the tribological influence of incorporating nano MoS 2 particles into MQL environment during turning Aluminium Alloy AA2024. nano-minimum quantity lubrication (nano-MQL) technique, a very tiny amount high-performance lubricant is applied straight to cutting zone. Generally, in nanodroplets, which are substantially smaller than standard minimum (MQL) droplets. Achieving desired surface roughness crucial machining operations. The experiment explores various parameters on (R ). addition, four machine learning models used estimate and compare experimental value anticipated values. For coefficient determination ), mean absolute percentage error (MAPE), square (MSE) were all assess how accurate projected values were. Machine Gradient boosting, linear regression Random Forest has estimated following R-squared 1.000, 0.999 0.959 respectively. Experimental results reveal that nano-MQL significantly improves quality tool wear, achieving 0.8399 µm 0.024 mm wear at 339.12 m/min speed, 0.1 mm/rev feed rate, 0.25 depth cut. average decreases by 28% when compared with dry environment.

Язык: Английский

---

Modeling and optimization of hard turning: predictive analysis of surface roughness and cutting forces in AISI 52100 steel using machine learning

International Journal on Interactive Design and Manufacturing (IJIDeM), Год журнала: 2024, Номер unknown

Опубликована: Ноя. 15, 2024

Язык: Английский

---