Adik M. Takale
Adik M. Takale has a total of 6 co-authors. Here are the top co-authors by number of shared publications:
- B. Vinod
VVCE
1 shared publication - Kishor K. Powar
Department of Mechanical Engineering DKTE Society's Textile and Engineering Institute Ichalkaranji Maharashtra India
1 shared publication - Manjunatha G Avalappa
Department of Mechanical Engineering, Atria Institute of Technology, Bengaluru, India
1 shared publication Mukesh Kumar
Department of Mechanical Engineering Assosa University Assosa Ethiopia
1 shared publication- Uday A. Dabade
Professor, Department of Mechanical Engineering, Walchand College of Engineering, Sangli, Maharashtra-416 415, India
1 shared publication - Uttam U. Deshpande
Department of Electronics and Communication Engineering KLS Gogte Institute of Technology Belagavi Karnataka India
1 shared publication
Latest Publications
- Open Access
- 16 April 2026
- Published by Wiley in Engineering Reports
- Vol. 8 (4) , e70769
Hybrid GRA –Machine Learning Framework for Surface and Performance Optimization of Ti 49. 3 Ni 50 .7 SMA in Biomedical Applications
Shape memory alloys (SMAs), such as Ti49.3Ni50.7, are well known for their remarkable mechanical and biocompatibility with human bone tissues. Thus, creating research opportunities in innovative machining processes using these alloys to design high‐quality biomedical implants using these alloys. However, this alloy's complex thermo‐mechanical reaction makes the standard machining process more challenging. To overcome this problem, we propose an enhanced Wire Electrical Discharge Machining (WEDM) process specifically designed to produce Ti49.3Ni50.7 orthopedic components. The effects of five important machining elements were investigated using a systematic experimental framework based on a Taguchi L18 orthogonal design. Gray relational analysis (GRA) was used to optimize both surface roughness and material removal rate, while Random Forest Regression combined with Bayesian optimisation was used to improve to optimal condition predictions. An experimental validation confirmed the surface roughness of 1.298 μm and a material removal rate of 2.537 mm 3 /min. To evaluate the post‐machining surface integrity, SEM, XRD, microhardness profiling, and residual stress analysis were used. The results revealed reduced tensile stress concentrations, enhanced hardness gradients, and minimal recast layer formation. Bending recovery tests confirmed that the alloy's shape memory behavior was restored by post‐machining annealing. This comprehensive strategy creates a reliable and scalable framework for the high‐precision TiNi‐based orthopedic implant production.
- 16 April 2026
- Published by Wiley in Engineering Reports
- Vol. 8 (4) , e70769
Open AccessHybrid GRA –Machine Learning Framework for Surface and Performance Optimization of Ti 49. 3 Ni 50 .7 SMA in Biomedical Applications
Shape memory alloys (SMAs), such as Ti49.3Ni50.7, are well known for their remarkable mechanical and biocompatibility with human bone tissues. Thus, creating research opportunities in innovative machining processes using these alloys to design high‐quality biomedical implants using these alloys. However, this alloy's complex thermo‐mechanical reaction makes the standard machining process more challenging. To overcome this problem, we propose an enhanced Wire Electrical Discharge Machining (WEDM) process specifically designed to produce Ti49.3Ni50.7 orthopedic components. The effects of five important machining elements were investigated using a systematic experimental framework based on a Taguchi L18 orthogonal design. Gray relational analysis (GRA) was used to optimize both surface roughness and material removal rate, while Random Forest Regression combined with Bayesian optimisation was used to improve to optimal condition predictions. An experimental validation confirmed the surface roughness of 1.298 μm and a material removal rate of 2.537 mm 3 /min. To evaluate the post‐machining surface integrity, SEM, XRD, microhardness profiling, and residual stress analysis were used. The results revealed reduced tensile stress concentrations, enhanced hardness gradients, and minimal recast layer formation. Bending recovery tests confirmed that the alloy's shape memory behavior was restored by post‐machining annealing. This comprehensive strategy creates a reliable and scalable framework for the high‐precision TiNi‐based orthopedic implant production.