EUVIMEDEUVIMED entdecken
Crossref

Machine learning assisted process modelling and optimization of high precision electrochemical micromachining of alloy C276 with hybrid electrolytes

Gowtham Kumarasamy, Poovazhagan Lakshmanan, Salem Alagappan Srinivasan, Ponraj Saravanamuthukumar

Metallurgical Research & Technology · 2026 · 123 (4) · 414

DOI: 10.1051/metal/2026043 ↗

Kurz gefasst

Fachartikel in der Zeitschrift Metallurgical Research & Technology, online erschienen am 09.06.2026. Verfasst von Gowtham Kumarasamy und 3 weiteren Autor:innen. Die Arbeit nennt 57 Literaturangaben.

AbstractBibliografische AngabenZitierenVerwandte Studien

Abstract (Originalsprache)

Machining of superalloys such as Alloy C-276 is extremely difficult due to its high strength, corrosion resistance, and low thermal conductivity, resulting in poor surface finish, tool wear, and dimensional inaccuracies. Therefore, to improve machining of such materials, this study aims to investigate the micro-electrochemical machining (m-ECM) of Alloy C-276 with a novel hybrid electrolyte containing sodium chloride (NaCl), sodium nitrate (NaNO 3 ), and citric acid (C 6 H 8 O 7 ) with the aim of achieving the highest material removal rate (MRR) and minimizing overcut (OC). Five machine learning (ML) models, namely Polynomial Regression (PR), Support Vector Regression (SVR), k-Nearest Neighbors (KNN), Decision Tree (DT), and Random Forest (RF), were developed using experimental results obtained using an L27 orthogonal array design. Among these models, PR exhibited superior predictive performance with R 2 values of 0.93 for MRR and 0.85 for OC, and stable generalization confirmed through five-fold cross-validation. Residual and correlation analyses indicated low bias, minimal variance, and negligible overfitting, while SHAP analysis identified voltage as the primary factor influencing MRR (∼60%) and electrolyte concentration as the key driver of OC (>80%). Optimization using PR achieved a maximum MRR of 0.2236 mm 3 /min and minimum OC of 63.2 μm, closely matching experimental results (

Zitieren

APA

Kumarasamy, G., Lakshmanan, P., Srinivasan, S. A., & Saravanamuthukumar, P. (2026). Machine learning assisted process modelling and optimization of high precision electrochemical micromachining of alloy C276 with hybrid electrolytes. Metallurgical Research & Technology, 123(4), 414. https://doi.org/10.1051/metal/2026043

Vancouver

Kumarasamy G, Lakshmanan P, Srinivasan SA, Saravanamuthukumar P. Machine learning assisted process modelling and optimization of high precision electrochemical micromachining of alloy C276 with hybrid electrolytes. Metallurgical Research & Technology. 2026;123(4):414. doi:10.1051/metal/2026043

BibTeX
@article{Kumarasamy2026,
  author = {Kumarasamy, Gowtham and Lakshmanan, Poovazhagan and Srinivasan, Salem Alagappan and Saravanamuthukumar, Ponraj},
  title = {Machine learning assisted process modelling and optimization of high precision electrochemical micromachining of alloy C276 with hybrid electrolytes},
  journal = {Metallurgical Research & Technology},
  year = {2026},
  volume = {123},
  number = {4},
  pages = {414},
  doi = {10.1051/metal/2026043}
}
Kostenlos starten →