Application of machine learning based algorithm to predict performance of turning Al–SiC-MWCNT using cryogenically treated textured insert

This work intends to improve dry machining of Al–SiC-MWCNT (Aluminum–Silicon Carbide-Multi-Walled Carbon Nanotube) composites with cryogenically treated textured cutting tool inserts. The study aims to optimize machining parameters such feed rate, cutting speed, depth of cut, and nanoparticle concen...

Celý popis

Uloženo v:
Podrobná bibliografie
Vydáno v:Hybrid Advances Ročník 10; s. 100432
Hlavní autoři: Saikrupa, Ch, Reddy, G ChandraMohan, Venkatesh, Sriram
Médium: Journal Article
Jazyk:angličtina
Vydáno: Elsevier B.V 01.09.2025
Elsevier
Témata:
Cryogenically treated tool
Machine learning based algorithm
Power consumption
prediction
Surface roughness
Turning: MMC
prediction
Turning: MMC
Surface roughness
Power consumption
Machine learning based algorithm
Cryogenically treated tool
ISSN:2773-207X, 2773-207X
On-line přístup:Získat plný text
Tagy: Přidat tag
Žádné tagy, Buďte první, kdo vytvoří štítek k tomuto záznamu!
Popis
Shrnutí:This work intends to improve dry machining of Al–SiC-MWCNT (Aluminum–Silicon Carbide-Multi-Walled Carbon Nanotube) composites with cryogenically treated textured cutting tool inserts. The study aims to optimize machining parameters such feed rate, cutting speed, depth of cut, and nanoparticle concentration to assess their effects on surface roughness and power utilization. These characteristics are key indications of machining processes' product quality and energy efficiency. Textured tools and solid lubrication have been studied; however, lubrication supply systems and high-temperature endurance are still issues. Cryogenic treatment is a strong option that addresses these issues by greatly improving cutting tools' hardness and strength. The L27 Taguchi Orthogonal Array was used to design the experiment. The machining trials included different feed rates, cutting speeds, depths of cut, and nanoparticle concentrations. The machining process's surface roughness and power use were analyzed. A Support Vector Machine (SVM) model was created for predictive study of surface roughness, giving a data-driven way to evaluate machining performance. The SVM model's prediction accuracy and error margin were used to measure its efficacy. The Support Vector Machine model was quite accurate, with a margin of error under 5 %. The model's R2 values of 0.87 and 0.90 for power consumption and surface roughness prediction show strong correlation and dependability. The findings imply that cryogenically treated textured cutting tools boost machining efficiency by lowering surface roughness and optimizing power usage. These findings support the use of cryogenic treatment and machine learning models in advanced machining procedures for composite materials.
ISSN:2773-207X
2773-207X
DOI:10.1016/j.hybadv.2025.100432