MétaCan
Menu
Back to cohort
Record W4319996762 · doi:10.5267/j.esm.2022.12.003

Comparison of different supervised machine learning algorithms for bead geometry prediction in GMAW process

2023· article· en· W4319996762 on OpenAlexvenueno aff
Teerapun Saeheaw

Bibliographic record

VenueEngineering Solid Mechanics · 2023
Typearticle
Languageen
FieldEngineering
TopicWelding Techniques and Residual Stresses
Canadian institutionsnot available
Fundersnot available
KeywordsGas metal arc weldingSupport vector machineArtificial neural networkMean squared errorArtificial intelligenceMachine learningWeldingAlgorithmComputer scienceLinear regressionMean absolute percentage errorDecision treeMathematicsEngineeringMechanical engineeringArc weldingStatistics

Abstract

fetched live from OpenAlex

Gas Metal Arc Welding (GMAW) is an extensively implemented arc welding process through the control of input process parameters and the metal from the filler wire. Despite its popular use in various industries, the complex interrelationship between the actual bead and the varying welding parameters makes it challenging to predict appropriate bead geometries via mathematical modeling in a continually changing welding process. In this study, the Regression Learner App was used to compare the performance of supervised Machine Learning (ML) predictive models comprising the Linear Regression (LR), Regression Tree (RT), Support Vector Machine (SVM), Ensembles of Tree (ET), Gaussian Process Regression (GPR), and Artificial Neural Network (ANN) using GMAW dataset. The dataset was scaled and normalized at a range of -1 to +1 to facilitate the visualization of the variation effect. The wire feed speed, voltage, weld velocity, unmelted wire length, and melted wire volume were considered as the input parameters to predict the bead geometry. In addition, the five-fold cross-validation was employed to avoid overfitting and poor generalization. Finally, statistical indicators, namely the Coefficient of Determination (R2), Root Mean Squared Error (RMSE), and Mean Absolute Error (MAE), were performed on all developed models to evaluate their performance. Thus, the fine tree and ANN models achieved the highest prediction accuracies of 88–91%, signifying their potential use in future research. In short, the present study demonstrated the performance of various supervised ML algorithms for bead geometry prediction, which would assist the selection of appropriately supervised ML algorithms in future studies.

Fetched live from OpenAlex and de-inverted. Abstracts are not stored in this database: the inverted indexes are 8.6 GB of the frame’s 9.3 GB of text, and the host has 13 GB free.

How this classification was reachedexpand

Full frame distilled prediction

Teacher imitation

Not calibrated prevalence, not ground truth. Human validation pending. Learned from the 10,348 direct Codex labels and 10,348 direct Gemma labels. Candidate is the union of thresholded teacher heads; consensus is their intersection. These outputs are machine_predicted_unvalidated and are not human labels or direct frontier model labels.

metaresearch head score (Codex)0.000
metaresearch head score (Gemma)0.000
Version: codex-gemma-dda1882f352aValidation status: machine_predicted_unvalidated
Candidate categoriesnone
Consensus categoriesnone
DomainCandidate signal: none · Consensus signal: none
Study designCandidate signal: Simulation or modeling · Consensus signal: Simulation or modeling
GenreCandidate signal: Empirical · Consensus signal: Empirical
Teacher disagreement score0.319
Threshold uncertainty score0.784

Codex and Gemma teacher scores by category

CategoryCodexGemma
Metaresearch0.0000.000
Meta-epidemiology (narrow)0.0000.000
Meta-epidemiology (broad)0.0000.000
Bibliometrics0.0000.001
Science and technology studies0.0000.000
Scholarly communication0.0000.000
Open science0.0000.000
Research integrity0.0000.000
Insufficient payload (model declined to judge)0.0000.000

Machine scores (provisional)

The two teacher heads of the student model, read on this work. A score orders the frame for review; it never asserts a category, and the validation status ships verbatim with every row.

Baseline scores from an immature model (maturity gate not passed, 7 training rounds). Scores rank; they never assert a category.

Opus teacher head0.023
GPT teacher head0.289
Teacher spread0.266 · how far apart the two teachers sit on this one work
Validation statusscore_only:v0-immature-baseline · verbatim from the scoring run: score_only means the number may rank works, and no category label ships from it

Classification

machine, unvalidated

Machine predicted; a candidate call from one teacher head, not a consensus.

The models applied no category: nothing in the taxonomy fit this work.
Study designSimulation or modeling
Domainnot available
GenreEmpirical

How this classification was reached, model by model and score by score, is at the end of the page under "How this classification was reached".

Quick stats

Citations8
Published2023
Admission routes1
Has abstractyes

Explore more

Same venueEngineering Solid MechanicsSame topicWelding Techniques and Residual StressesFrench-language works237,207