{"id":"W4319067216","doi":"10.21203/rs.3.rs-2535141/v1","title":"Artificial Intelligence-based optimization of Variable Blank Holder Force to reduce residual stress and improve formability; Experimental and statistical analysis","year":2023,"lang":"en","type":"preprint","venue":"Research Square","topic":"Metal Forming Simulation Techniques","field":"Engineering","cited_by":1,"is_retracted":false,"has_abstract":true,"ca_institutions":"Université du Québec à Trois-Rivières; Université du Québec à Rimouski","funders":"","keywords":"Blank; Formability; Tearing; Deep drawing; Artificial neural network; Process (computing); Residual; Residual stress; Sheet metal; Moment (physics); Computer science; Finite element method; Structural engineering; Mechanical engineering; Engineering; Artificial intelligence; Materials science; Algorithm; Composite material","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":"codex-gemma-dda1882f352a","candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.001244599,0.0002023054,0.000397836,0.0008877745,0.00008528791,0.0001340127,0.0001811385,0.0002348517,0.00009597056],"category_scores_gemma":[0.0005574799,0.0002104753,0.00005113174,0.0007603531,0.0001503176,0.00009248555,0.0004211711,0.0004514062,0.000002065317],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.0001324424,"about_ca_system_score_gemma":0.00009287932,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.0002911549,"about_ca_topic_score_gemma":0.00002826046,"domain_scores_codex":[0.9978413,0.0001553086,0.0005273607,0.0004647876,0.0006573889,0.0003538631],"domain_scores_gemma":[0.9984619,0.0005487485,0.00005102981,0.0004599005,0.0003041895,0.0001742034],"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":[0.00009659707,0.00005626501,0.0006117149,0.001555719,0.0001657587,0.000002733002,0.0004821449,0.9885668,0.003112436,0.003236431,0.0000553393,0.002058092],"study_design_scores_gemma":[0.00004553955,0.0001875867,0.0006126806,0.0002005476,0.00005993087,1.543017e-7,0.0003834733,0.8155954,0.1772169,0.005502749,0.000003853496,0.0001911305],"study_design_candidate":"simulation_or_modeling","study_design_consensus":"simulation_or_modeling","genre_codex":"methods","genre_gemma":"empirical","genre_scores_codex":[0.298747,0.0001148952,0.6987294,0.00003819078,0.00006921171,0.001143391,0.0008311144,0.0002240364,0.0001027946],"genre_scores_gemma":[0.941067,0.00002289776,0.05812043,0.000001969571,0.0000486136,0.0002112342,0.0004298469,0.00004385541,0.00005409941],"genre_candidate":"empirical","genre_consensus":null,"teacher_disagreement_score":0.64232,"threshold_uncertainty_score":0.8582935,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.08473371466953349,"score_gpt":0.4074696155907956,"score_spread":0.3227359009212621,"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."}}