Downloads: 2
Experimental Result Paper | Mechanical Engineering | Volume 15 Issue 7, July 2026 | Pages: 459 - 467 | India
Experimental and ANN-Based Multi-Response Milling Parameter Optimization for Ti-6Al-4V Tire Mold Surface Quality Enhancement
Abstract: Titanium alloy Ti-6Al-4V is widely utilized in high-performance engineering applications because of its excellent strength-to-weight ratio, corrosion resistance, and thermal stability. To improve surface finish and functional performance, its use in the production of tyre molds necessitates exact control over machining settings. Nevertheless, systematic milling optimization of Ti-6Al-4V for this particular application is the subject of few investigations. This study examines how surface roughness, material removal rate (MRR), and surface hardness are affected by spindle speed, feed rate, and depth of cut. Grey Relational Analysis (GRA) was used for multi-response optimization, while the Taguchi approach was used for experimental design. To forecast surface roughness from machining parameters and identify ideal circumstances for a particular surface finish, an Artificial Neural Network (ANN) model was created in Python. Surface integrity was greatly enhanced while manufacturing efficiency was maintained by the combined experimental, statistical, and artificial intelligence framework. The suggested method offers a dependable and clever way to maximize Ti-6Al-4V milling in tire mold production applications.
Keywords: Milling optimisation, Surface roughness, Artificial Neural Network, Grey Relational Analysis, Tyre moulds
How to Cite?: Arul Raja R A, Sankar E, Anilkumar S, "Experimental and ANN-Based Multi-Response Milling Parameter Optimization for Ti-6Al-4V Tire Mold Surface Quality Enhancement", Volume 15 Issue 7, July 2026, International Journal of Science and Research (IJSR), Pages: 459-467, https://www.ijsr.net/getabstract.php?paperid=SR26215224734, DOI: https://dx.doi.org/10.21275/SR26215224734