{"id":"W4320015847","doi":"10.1109/tii.2023.3240921","title":"Domain Discrepancy-Guided Contrastive Feature Learning for Few-Shot Industrial Fault Diagnosis Under Variable Working Conditions","year":2023,"lang":"en","type":"article","venue":"IEEE Transactions on Industrial Informatics","topic":"Machine Fault Diagnosis Techniques","field":"Engineering","cited_by":60,"is_retracted":false,"has_abstract":true,"ca_institutions":"University of British Columbia, Okanagan Campus; University of British Columbia","funders":"Fundamental Research Funds for the Central Universities; National Natural Science Foundation of China","keywords":"Computer science; Fault (geology); Artificial intelligence; Feature extraction; Feature (linguistics); Context (archaeology); Similarity (geometry); Pattern recognition (psychology); Machine learning; Domain (mathematical analysis); Sample (material); Data mining; Mathematics; Image (mathematics)","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":["metaepi_narrow"],"consensus_categories":[],"category_scores_codex":[0.0006280425,0.0005053095,0.000585054,0.000643784,0.0006604275,0.0002656491,0.0003318043,0.0009609628,0.0001839846],"category_scores_gemma":[0.0001413071,0.0005262989,0.0002700073,0.00145772,0.00009527781,0.0005622844,0.000006153391,0.001945833,0.00007098007],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.0003914896,"about_ca_system_score_gemma":0.0001307706,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.00004850841,"about_ca_topic_score_gemma":0.00002927537,"domain_scores_codex":[0.9974917,0.00009664914,0.000973042,0.0002360299,0.00043533,0.0007672695],"domain_scores_gemma":[0.9974105,0.001678177,0.000209206,0.0003538294,0.0001217523,0.0002264808],"domain_codex":null,"domain_gemma":null,"domain_candidate":null,"domain_consensus":null,"study_design_codex":"simulation_or_modeling","study_design_gemma":"not_applicable","study_design_scores_codex":[0.00009539897,0.0001206021,0.000187164,0.00006992388,0.000470941,0.000003506686,0.001046083,0.8661782,0.0002425591,0.001650339,0.1222636,0.007671595],"study_design_scores_gemma":[0.02119063,0.001538169,0.0001514255,0.003009995,0.00129894,0.00005891353,0.009639293,0.3979136,0.09850611,0.006403566,0.4560595,0.004229841],"study_design_candidate":"simulation_or_modeling","study_design_consensus":null,"genre_codex":"methods","genre_gemma":"empirical","genre_scores_codex":[0.08703521,0.00001549916,0.8947312,0.0006501094,0.004345465,0.003415869,0.001261317,0.004559393,0.003985901],"genre_scores_gemma":[0.9843006,0.0001868975,0.008786385,0.0002579787,0.0009773966,0.004127503,0.0005913476,0.0001899233,0.0005819784],"genre_candidate":"empirical","genre_consensus":null,"teacher_disagreement_score":0.8972654,"threshold_uncertainty_score":0.9997188,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.0694291012273845,"score_gpt":0.3109788012642973,"score_spread":0.2415497000369128,"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."}}