{"id":"W4416174720","doi":"10.1016/j.jmapro.2025.10.104","title":"Real-time and data-efficient springback prediction in tube bending using force measurement and physics-informed machine learning","year":2025,"lang":"en","type":"article","venue":"Journal of Manufacturing Processes","topic":"Model Reduction and Neural Networks","field":"Physics and Astronomy","cited_by":8,"is_retracted":false,"has_abstract":true,"ca_institutions":"","funders":"Norges Forskningsråd; Alexander Family Foundation; Norges Teknisk-Naturvitenskapelige Universitet","keywords":"Bending; Displacement (psychology); Artificial neural network; Convolutional neural network; Stability (learning theory); Deformation (meteorology); Tube (container)","routes":{"ca_aff":false,"ca_fund":true,"ca_venue":false,"about_ca":false,"invisible_to_affiliation_only":true},"retraction":null,"screen":null,"direct_labels":[],"prediction":{"model_version":"codex-gemma-dda1882f352a","candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0003603038,0.000121559,0.0001993202,0.00009534338,0.0001320702,0.00008525364,0.0001033625,0.00002438809,0.00001634717],"category_scores_gemma":[0.00002611142,0.00010308,0.00002224923,0.00009476757,0.00002362138,0.0003179592,0.0001097218,0.0002605504,3.055664e-7],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.000056184,"about_ca_system_score_gemma":0.000106622,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.00005576347,"about_ca_topic_score_gemma":0.000003649978,"domain_scores_codex":[0.9991289,0.00002388278,0.0003311652,0.0001609855,0.0002020507,0.0001530221],"domain_scores_gemma":[0.9994931,0.00004985039,0.0002427756,0.00008754667,0.00007482398,0.00005192845],"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":[0.0002272574,0.0001803786,0.02458129,0.0008010584,0.0002253632,0.000005276188,0.0007976659,0.8997917,0.005682303,0.00009647235,0.0001163286,0.06749493],"study_design_scores_gemma":[0.003662434,0.0001989772,0.01751428,0.003057243,0.0003275083,0.00006056781,0.001014641,0.7105132,0.259037,0.001649141,0.002390006,0.0005750249],"study_design_candidate":"simulation_or_modeling","study_design_consensus":"simulation_or_modeling","genre_codex":"empirical","genre_gemma":"empirical","genre_scores_codex":[0.9877554,0.0002720276,0.01121765,0.00006301999,0.0001133865,0.00009376342,0.000004465757,0.00001092574,0.0004694159],"genre_scores_gemma":[0.9988985,0.0001566789,0.00063242,0.00000620114,0.0001775438,9.366548e-7,0.000005184472,0.000008299483,0.0001142014],"genre_candidate":"empirical","genre_consensus":"empirical","teacher_disagreement_score":0.2533547,"threshold_uncertainty_score":0.4203481,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.03868577682903988,"score_gpt":0.2871793523791608,"score_spread":0.2484935755501209,"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."}}