{"id":"W2994952276","doi":"10.4236/jsea.2019.1212031","title":"A Study on Prediction of Weld Geometry in Laser Overlap Welding of Low Carbon Galvanized Steel Using ANN-Based Models","year":2019,"lang":"en","type":"article","venue":"Journal of Software Engineering and Applications","topic":"Welding Techniques and Residual Stresses","field":"Engineering","cited_by":3,"is_retracted":false,"has_abstract":true,"ca_institutions":"Cégep de Rimouski; Université du Québec à Rimouski","funders":"","keywords":"Welding; Artificial neural network; Taguchi methods; Galvanization; Laser beam welding; Reliability (semiconductor); Mechanical engineering; Laser power scaling; Structural engineering; Materials science; Laser; Power (physics); Engineering; Computer science; Artificial intelligence; Composite material; Optics","routes":{"ca_aff":true,"ca_fund":false,"ca_venue":false,"about_ca":false,"invisible_to_affiliation_only":false},"retraction":null,"screen":null,"direct_labels":[],"prediction":{"model_version":"metacan-v3-hybrid-931329e0061c","candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0004646801,0.0006212682,0.0003770767,0.0002703562,0.0001914466,0.0004266575,0.0004309644,0.0006742959,0.0005138225],"category_scores_gemma":[0.0008554612,0.000275335,0.0004636739,0.0002463451,0.0001862565,0.000367171,0.0001921234,0.0003595747,0.00008552337],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.0003981679,"about_ca_system_score_gemma":0.0003684953,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.00814856,"about_ca_topic_score_gemma":0.006668628,"domain_scores_codex":[0.9998394,0.0000486906,0.00001021431,0.00003682316,0.0000472033,0.00001757223],"domain_scores_gemma":[0.9994779,0.0003781269,0.00003991969,0.00002378024,0.00007019727,0.00001013601],"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":[0.00006624855,0.00004897829,0.001767696,0.00004318858,0.00001902937,0.00004616895,0.00002464849,0.9813703,0.004649534,0.0001342526,0.00004034782,0.01178965],"study_design_scores_gemma":[0.000001218673,0.0000468515,0.0005503984,0.000001845964,0.000003767369,0.000004004443,0.000004192288,0.9978454,0.001482291,0.00002763922,0.00003039152,0.000001937124],"study_design_candidate":"simulation_or_modeling","study_design_consensus":"simulation_or_modeling","genre_codex":"empirical","genre_gemma":"empirical","genre_scores_codex":[0.8412911,0.0002844312,0.155966,0.00005831077,0.00001598613,0.00004666325,0.00006838786,0.0002881684,0.001980877],"genre_scores_gemma":[0.9903548,0.00008023257,0.008838129,0.000006051863,0.000001620518,0.00002970163,0.00005191806,0.000007438384,0.000630159],"genre_candidate":"empirical","genre_consensus":"empirical","teacher_disagreement_score":0.00814856,"threshold_uncertainty_score":0.01620227,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.01244010525925806,"score_gpt":0.221964427258472,"score_spread":0.209524321999214,"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."}}