{"id":"W4205843111","doi":"10.1109/tii.2021.3134250","title":"Development of an Explainable Fault Diagnosis Framework Based on Sensor Data Imagification: A Case Study of the Robotic Spot-Welding Process","year":2021,"lang":"en","type":"article","venue":"IEEE Transactions on Industrial Informatics","topic":"Welding Techniques and Residual Stresses","field":"Engineering","cited_by":33,"is_retracted":false,"has_abstract":true,"ca_institutions":"University of Calgary","funders":"National Research Foundation of Korea","keywords":"Interpretability; Computer science; Artificial intelligence; Fault (geology); Data mining; Machine learning; Process (computing); Convolutional neural network; Field (mathematics); Fault detection and isolation; Inference; Pattern recognition (psychology)","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":[0.0002102904,0.0001578447,0.0002242375,0.0001085361,0.0002143161,0.00004602853,0.0003371641,0.0001654864,0.00003439301],"category_scores_gemma":[0.00005425962,0.0001251323,0.00003740652,0.0005584349,0.00003039434,0.0002528397,0.000005722661,0.0004541942,0.000001003984],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.00006321497,"about_ca_system_score_gemma":0.0001429731,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.0000433252,"about_ca_topic_score_gemma":0.00004378839,"domain_scores_codex":[0.998702,0.00004255171,0.0006640986,0.0001105086,0.000323864,0.000156982],"domain_scores_gemma":[0.9986972,0.0002206876,0.0001410862,0.000770012,0.0001161215,0.00005492703],"domain_codex":null,"domain_gemma":null,"domain_candidate":null,"domain_consensus":null,"study_design_codex":"simulation_or_modeling","study_design_gemma":"bench_or_experimental","study_design_scores_codex":[0.00001822752,0.0005448945,0.00003965076,0.0001617004,0.00005501885,0.000019294,0.003770255,0.9871271,0.00002523058,0.000001809545,0.00007020689,0.00816656],"study_design_scores_gemma":[0.001188776,0.0002801702,0.00002108533,0.0009550101,0.0001924085,0.00007666979,0.05414983,0.2436569,0.6987512,0.00001437255,0.0003405648,0.0003730341],"study_design_candidate":"simulation_or_modeling","study_design_consensus":null,"genre_codex":"empirical","genre_gemma":"empirical","genre_scores_codex":[0.8439781,0.000004048229,0.1549131,0.00003474153,0.0003509286,0.0004873001,0.00006036785,0.0001023542,0.00006903933],"genre_scores_gemma":[0.9816445,0.000008127324,0.01818269,0.00001500121,0.00003275706,0.00008350878,0.000009429231,0.00001816222,0.00000589663],"genre_candidate":"empirical","genre_consensus":"empirical","teacher_disagreement_score":0.7434703,"threshold_uncertainty_score":0.5102748,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.0951140719468133,"score_gpt":0.3104665422492357,"score_spread":0.2153524703024224,"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."}}