{"id":"W3173537256","doi":"10.1016/j.optlastec.2021.107338","title":"On the application of machine learning for defect detection in L-PBF additive manufacturing","year":2021,"lang":"en","type":"article","venue":"Optics & Laser Technology","topic":"Additive Manufacturing Materials and Processes","field":"Engineering","cited_by":99,"is_retracted":false,"has_abstract":false,"ca_institutions":"McMaster University","funders":"","keywords":"Computer science; Artificial intelligence; Artificial neural network; Pattern recognition (psychology); Autoencoder; Classifier (UML); Acoustic emission; Dimensionality reduction; Cluster analysis; Machine learning; Principal component analysis; Curse of dimensionality; Materials science","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":[0.00008519739,0.0001022978,0.0001389928,0.0001104107,0.00005177236,0.0000101819,0.00008727924,0.0001162174,0.00002594801],"category_scores_gemma":[0.0001472858,0.00008659899,0.00003489729,0.0001266045,0.00003562878,0.00002608156,0.00003114273,0.0001899378,0.00000705147],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.00003113934,"about_ca_system_score_gemma":0.000006151291,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.000005009394,"about_ca_topic_score_gemma":0.00005934805,"domain_scores_codex":[0.9995084,0.0000152336,0.0001440979,0.0001402596,0.00004717472,0.0001447991],"domain_scores_gemma":[0.9995194,0.0002450825,0.00004535909,0.0001431866,0.00003753388,0.000009442415],"domain_codex":null,"domain_gemma":null,"domain_candidate":null,"domain_consensus":null,"study_design_codex":"design_other","study_design_gemma":"bench_or_experimental","study_design_scores_codex":[0.0001788898,0.0001755402,0.0003264615,0.0008954494,0.0002755918,0.00002639029,0.0003235966,0.266058,0.3032335,0.03205711,0.0000958839,0.3963536],"study_design_scores_gemma":[0.0001605226,0.00005607191,0.0001314081,0.00002498213,0.00001089711,0.000004208774,0.00006302819,0.0133141,0.9726448,0.01058612,0.002918867,0.00008500594],"study_design_candidate":"bench_or_experimental","study_design_consensus":null,"genre_codex":"empirical","genre_gemma":"empirical","genre_scores_codex":[0.9437106,0.00008617876,0.05510344,0.0001064752,0.00008171199,0.0002001314,0.00003924372,0.0001803781,0.0004918507],"genre_scores_gemma":[0.9989922,0.0000739695,0.0006656211,0.00001383453,0.00002285318,0.0001569381,0.00003333153,0.00002345843,0.0000178128],"genre_candidate":"empirical","genre_consensus":"empirical","teacher_disagreement_score":0.6694112,"threshold_uncertainty_score":0.3531404,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.00586955777655261,"score_gpt":0.2066787581551406,"score_spread":0.200809200378588,"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."}}