Effect of powder composition, PTAW parameters on dilution, microstructure and hardness of Ni–Cr–Si–B alloy deposition: Experimental investigation and prediction using machine learning technique
Venkatesh Chenrayan,
Kiran Shahapurkar,
Chandru Manivannan,
L. Rajeshkumar,
N. Sivakumar,
R. Rajesh sharma,
R. Venkatesan
Affiliations
Venkatesh Chenrayan
AU-Sophisticated Testing and Instrumentation Centre (AU-STIC) and Department of Mechanical Engineering, Alliance School of Applied Engineering, Alliance University, Bengaluru, 562106, India; Corresponding author.
Kiran Shahapurkar
Centre of Molecular Medicine and Diagnostics (COMManD), Saveetha Dental College and Hospitals, Saveetha Institute of Medical and Technical Sciences, Saveetha University, Chennai, 600077, India; Department of Mechanical Engineering, Faculty of Engineering, University of Malaya, Kuala Lumpur, 50603, Malaysia
Chandru Manivannan
Department of Mechanical Engineering, Dhirajlal Gandhi College of Technology, Salem, India
L. Rajeshkumar
AU-Sophisticated Testing and Instrumentation Centre (AU-STIC) and Department of Mechanical Engineering, Alliance School of Applied Engineering, Alliance University, Bengaluru, 562106, India; Corresponding author.
N. Sivakumar
Department of Computer Science Engineering, School of Advanced Computing, Alliance University, Bengaluru, India
R. Rajesh sharma
Department of Computer Science Engineering, School of Advanced Computing, Alliance University, Bengaluru, India
R. Venkatesan
Department of Mechanical Engineering, SRM-TRP Engineering College, Tiruchirapalli, India
The implementation of hard-facing alloy on the existing materials caters the need for high-performance surfaces in terms of wear and high temperatures. The present research explore the effect of Plasma Transferred Arc Welding (PTAW) parameters and powder composition on dilution, microstructure and hardness of the commonly used hard-facing alloy Ni–Cr–Si–B powder. The hard-facing alloy was deposited with three weight proportions of boron (2.5 %, 3 % and 3.5 %). The statistical-based Grey Relational Analysis (GRA) followed by a Machine Learning Algorithm (MLA) was implemented to identify the ideal parameters and degree of significance of each parameter and for the prediction of the responses. The dilution percentage, microstructure analysis, and phase detection were estimated through elemental analysis, Scanning electron Microscopy (SEM) and X-ray Diffraction Analysis (XRD) respectively. The experimental and modelling results revealed that 400 mm/min of scanning speed, 8 gm/min of powder delivery, 14 mm of stand-off distance, and 120 A of current were the optimal parameters along with 3.5 wt% of boron powder composition to yield a better dilution, microstructure and hardness.
