International Scientific Journal of Engineering and Management

An International Scholarly || Multidisciplinary || Open Access || Indexing in all major Database & Metadata
The journal follows the UGC Guidelines and is evaluated for inclusion in the Web of Science
ISSN: 2583-6129

Impact Factor: 7.839

Categorization and evaluation of orbital weld bead data incorporating Machine Learning techniques

  • Version
  • Download 15
  • File Size 401.49 KB
  • File Count 1
  • Create Date 18 April 2025
  • Last Updated 18 April 2025

Categorization and evaluation of orbital weld bead data incorporating Machine Learning techniques

 

 

Authors:

Mr. R. Hariharan1*, Dr.T.Senthilkumar2, Dr.M.Chandrasekar3 Dr.M.Arulmozhi4, Dr.S.Siddharth5

1*Research Scholar, University College of Engineering, BIT Campus, Anna University Tiruchirappalli

2Professor  & Dean, Department of Automobile Engineering, University College of Engineering, BIT Campus, Anna University Tiruchirappalli

3Assistant Professor, Department of Mechanical Engineering, University College of Engineering, BIT Campus, Anna University Tiruchirappalli

4Professor, Department of Petrochemical Technology, University College of Engineering, BIT Campus, Anna University Tiruchirappalli

5Associate Professor, Department of Mechanical Engineering, PSN College of Engineering & Technology, Tirunelveli

Abstract - The classification and evaluation of orbital weld bead data using Machine Learning techniques provides a novel way to enhancing weld quality assessment processes. In this study, the random forest machine learning method was used to categorize weld quality using digital pictures of weld beads from 50 samples. The random forest model was trained utilizing essential picture elements to distinguish between acceptable and unsatisfactory weld quality, allowing for accurate categorization. The model's performance was evaluated using three categorization indicators: classification accuracy, F1-score, and the area under the receiver operating characteristic (ROC) curve (AUC). The RF model has a classification accuracy of 93.5%, an F1-score of 92.8%, and an AUC of 0.96, indicating its great dependability and robustness in determining weld bead quality. Feature selection and hyperparameter optimization improved the model's capacity to distinguish between high-quality and faulty welds. This work highlights the possibility for incorporating machine learning techniques, notably the random forest algorithm, into automated weld quality evaluation systems. The random forest model's great performance in categorizing weld quality demonstrates its usefulness in industrial settings, providing a path to increased efficiency and precision in defect identification and quality assurance procedures.

Key Words: random forest, hyperparameters, machine learning, categorization, feature selection


Download

Author's Blog

What is the difference between a Research Paper and a Review Paper?

A research paper and a review paper are both scholarly documents, but they serve different purposes and have different characteristics....
Read More
Author's Blog

What is DOI?

A Digital Object Identifier (DOI) is a unique alphanumeric string that is used to identify and provide a persistent link...
Read More
Author's Blog

What do you need to do during production of your Research Paper?

During the production of a research paper, the following steps need to be taken: conducting research, organizing and analyzing data,...
Read More
Author's Blog

What are the advantages of publishing a research paper?

Publishing a research paper can have many advantages for researchers, including: Career advancement, professional recognition, opportunities for collaboration, increased visibility,...
Read More
Author's Blog

Ways to Support your Academic Wellbeing which preparing the Research Paper/Article

To support your academic wellbeing while publishing a research paper, it's important to set realistic goals, manage your time effectively,...
Read More
Author's Blog

How to improve your Research Paper writing Skills?

Read extensively: One of the best ways to improve your research paper skills is to read extensively in your field...
Read More
Author's Blog

Is DOI compulsory to publish a research paper in a Journal?

DOI is not strictly required to publish a research paper, but it is highly recommended. Basically, the International Scientific Journal...
Read More
Author's Blog

In what ways does research paper give weight to career development?

Publishing a research paper can give weight to a researcher's career development in several ways, such as: establishing oneself as...
Read More
Author's Blog

How to develop a Research Paper from Scratch

Developing a research paper involves several steps including: choosing a topic, conducting background research, formulating a research question or hypothesis,...
Read More
Author's Blog

How Plagiarism report plays crucial role in Research Paper Publication?

Plagiarism is a major concern in the academic and research community, as it undermines the integrity of the research and...
Read More