A credal decision tree classifier approach for surface condition monitoring of friction stir weldment through vibration patterns

Dhanraj, Joshuva Arockia; Lingampalli, Bhavya; Prabhakar, Meenakshi; Sivakumar, Aravinth; Krishnamurthy, Balachandar; Ramanathan, Kuppan Chetty

doi:10.1016/j.matpr.2021.02.054

Cited by 6 publications

(1 citation statement)

References 24 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…Al has a less elastic modulus, minimal wear resistance, and a maximum corrosion rate, which are all signifcant problems. Various particle reinforcements have been reported to be added to the Al alloy matrix to solve these issues [1].…”

Section: Introductionmentioning

confidence: 99%

Investigation of the Wear Behavior of AA6063/Zirconium Oxide Nanocomposites Using Hybrid Machine Learning Algorithms

Roy

Shanmugam

Vinothini

et al. 2023

Journal of Chemistry

View full text Add to dashboard Cite

This research created hot-pressed composites of the AA6063 matrix with varying concentrations of ZrO2 (0.25, 0.5, and 1 wt %). At sliding speeds of 80, 120, and 150 mm/s, the wear performance of the specimen was studied at loads of 10 N, 15 N, 20 N, and 25 N. The authors analyzed the counter-face material, the wear debris, and the worn surfaces to learn about the wear mechanisms. Developing these three machine learning (ML) algorithms was to evaluate the ability to predict wear behavior using the same small dataset collected using varying test processes. A thorough examination of each model hyperparameter tuning phase was performed. The predictive performance was analyzed using several statistical tools. The most effective decision-making algorithms for this data collection were those based on trees. Predictions made by the decision tree algorithm for the test and validation measurements have an accuracy of 86% and 99.7%, respectively. The best model was picked out based on the results of the predictions.

show abstract

Section: Introductionmentioning

confidence: 99%

Investigation of the Wear Behavior of AA6063/Zirconium Oxide Nanocomposites Using Hybrid Machine Learning Algorithms

Roy

Shanmugam

Vinothini

et al. 2023

Journal of Chemistry

View full text Add to dashboard Cite

show abstract

Mass flash reduction strategies in friction stir processing of aluminum alloys: A review

Marazani,

Jeje,

Shongwe

et al. 2024

Engineering Reports

View full text Add to dashboard Cite

Friction Stir Processing (FSP) has become a famous solid‐state technology for the fabrication of a wide range of aluminum alloy‐based composites that today find multiple applications across the various metal industries. Generation of revolving, ribbon, bulk, excessive or mass flash as it is generally termed has been a common problem in numerous FSP works. When confronted by this challenge, many researchers apply different experimental and numerical modeling approaches or strategies to reduce the mass flash to practically acceptable limits since it often leads to undesirable loss of material and is also an unwanted defect. This subject is deficiently reviewed, and it therefore becomes the thrust of this paper, to investigate the common trends in mass flash generation during FSP and its commonly employed reduction strategies. Mass flash is caused by high rotational speed at low travel speed and vice versa, flat shoulder, no and low tilt angles, high plunge depth, axial force, and travel force. Mass flash causes material loss, loss of volume fraction control target, material thinning, and leads to poor quality fabrications. Mass flash reduction strategies include the use of high tool tilt angles, concaved tool shoulder, proportional rotational speed and travel speed, and optimal plunge depth, axial force and travel speed as supported by both the experimental and numerical modeling studies.

show abstract

Analysis of Robotic Arm for Friction Stir Welding Application

Balaji¹,

Ajay²,

Doss³

et al. 2022

Lecture Notes in Mechanical Engineering

View full text Add to dashboard Cite

A credal decision tree classifier approach for surface condition monitoring of friction stir weldment through vibration patterns

Cited by 6 publications

References 24 publications

Investigation of the Wear Behavior of AA6063/Zirconium Oxide Nanocomposites Using Hybrid Machine Learning Algorithms

Investigation of the Wear Behavior of AA6063/Zirconium Oxide Nanocomposites Using Hybrid Machine Learning Algorithms

Mass flash reduction strategies in friction stir processing of aluminum alloys: A review

Analysis of Robotic Arm for Friction Stir Welding Application

Contact Info

Product

Resources

About