{"id":"W4319996762","doi":"10.5267/j.esm.2022.12.003","title":"Comparison of different supervised machine learning algorithms for bead geometry prediction in GMAW process","year":2023,"lang":"en","type":"article","venue":"Engineering Solid Mechanics","topic":"Welding Techniques and Residual Stresses","field":"Engineering","cited_by":8,"is_retracted":false,"has_abstract":true,"ca_institutions":"","funders":"","keywords":"Gas metal arc welding; Support vector machine; Artificial neural network; Mean squared error; Artificial intelligence; Machine learning; Welding; Algorithm; Computer science; Linear regression; Mean absolute percentage error; Decision tree; Mathematics; Engineering; Mechanical engineering; Arc welding; Statistics","routes":{"ca_aff":false,"ca_fund":false,"ca_venue":true,"about_ca":false,"invisible_to_affiliation_only":true},"retraction":null,"screen":null,"direct_labels":[],"prediction":{"model_version":"metacan-v3-hybrid-931329e0061c","candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.002487223,0.001277206,0.001176196,0.001157474,0.0003757311,0.001025993,0.001427607,0.001087895,0.0006604931],"category_scores_gemma":[0.005540351,0.0003005158,0.001203855,0.0008650441,0.0003086257,0.001125506,0.0005812124,0.001024868,0.0004144206],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.0005990789,"about_ca_system_score_gemma":0.001110505,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.007110607,"about_ca_topic_score_gemma":0.004535768,"domain_scores_codex":[0.9989964,0.0003195358,0.0001026079,0.0002772887,0.0002076196,0.00009648902],"domain_scores_gemma":[0.9973563,0.001410336,0.0002650197,0.0001837216,0.0007223577,0.00006231119],"domain_codex":null,"domain_gemma":null,"domain_candidate":null,"domain_consensus":null,"study_design_codex":"simulation_or_modeling","study_design_gemma":"simulation_or_modeling","study_design_scores_codex":[0.0003998699,0.0003207239,0.006441989,0.000236501,0.000161487,0.0000902551,0.0001070098,0.759875,0.002346242,0.0008787714,0.00154688,0.2275954],"study_design_scores_gemma":[0.000005083501,0.00004163252,0.0006806061,0.000008152701,0.00001051244,0.000009395494,0.00001296021,0.9978194,0.0009728483,0.0002566866,0.0001771576,0.00000554089],"study_design_candidate":"simulation_or_modeling","study_design_consensus":"simulation_or_modeling","genre_codex":"methods","genre_gemma":"empirical","genre_scores_codex":[0.4464101,0.004105147,0.5368589,0.0005634267,0.0002294002,0.0001764162,0.0005677211,0.005281506,0.005807306],"genre_scores_gemma":[0.913611,0.0006427175,0.08271259,0.0001479143,0.00005598474,0.0001213782,0.001050976,0.0001071148,0.001550305],"genre_candidate":"empirical","genre_consensus":null,"teacher_disagreement_score":0.007110607,"threshold_uncertainty_score":0.0141384,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.02272664879365533,"score_gpt":0.2885369522678088,"score_spread":0.2658103034741535,"validation_status":"score_only:v0-immature-baseline","note":"Baseline scores from an immature model (maturity gate not passed). Scores rank; they never assert a category."}}