{"id":"W4414090142","doi":"10.1016/j.aei.2025.103803","title":"Physics-informed deep learning method for surface roughness prediction in milling process","year":2025,"lang":"en","type":"article","venue":"Advanced Engineering Informatics","topic":"Advanced machining processes and optimization","field":"Engineering","cited_by":9,"is_retracted":false,"has_abstract":false,"ca_institutions":"University of British Columbia, Okanagan Campus; University of British Columbia","funders":"National Natural Science Foundation of China","keywords":"Surface roughness; Mean squared error; Surface finish; Root mean square; Leverage (statistics); Process (computing); Artificial neural network; Mean absolute percentage error","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":[0.0002702307,0.0004633706,0.0005733168,0.0003904453,0.0002334887,0.0004742377,0.0009900711,0.0008701684,0.001892084],"category_scores_gemma":[0.0006623347,0.0003503242,0.0005694824,0.0003724535,0.000240208,0.0007320009,0.0005263847,0.001015274,0.0004085367],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.0004639757,"about_ca_system_score_gemma":0.0008668891,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.005845262,"about_ca_topic_score_gemma":0.006921354,"domain_scores_codex":[0.9998978,0.00001335454,0.000004974258,0.00002979311,0.00003433567,0.00001961241],"domain_scores_gemma":[0.9997811,0.00008827277,0.00002223867,0.00002331824,0.00006938899,0.00001569297],"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":[0.000102872,0.0001080962,0.001309635,0.00008874998,0.00005530249,0.00005200313,0.00002213983,0.8761269,0.007009105,0.002923151,0.001930602,0.1102714],"study_design_scores_gemma":[0.000001135341,0.000003984595,0.00006702549,8.284306e-7,0.000001573238,0.000002016081,5.845527e-7,0.9992564,0.0002764785,0.00032845,0.00006051537,9.929229e-7],"study_design_candidate":"simulation_or_modeling","study_design_consensus":"simulation_or_modeling","genre_codex":"methods","genre_gemma":"methods","genre_scores_codex":[0.08331984,0.0009049515,0.9101087,0.0003017873,0.00009808248,0.00003615965,0.0002716398,0.001756584,0.0032022],"genre_scores_gemma":[0.9161493,0.0003486925,0.07741711,0.0001779833,0.00006500238,0.00007066062,0.0004902598,0.0001218129,0.005159269],"genre_candidate":"methods","genre_consensus":"methods","teacher_disagreement_score":0.005845262,"threshold_uncertainty_score":0.01162243,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.004591595288886932,"score_gpt":0.2610111578436111,"score_spread":0.2564195625547241,"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."}}