{"id":"W3212409379","doi":"10.1016/j.compind.2021.103554","title":"Data-driven strategies for predictive maintenance: Lesson learned from an automotive use case","year":2021,"lang":"en","type":"article","venue":"Computers in Industry","topic":"Time Series Analysis and Forecasting","field":"Computer Science","cited_by":47,"is_retracted":false,"has_abstract":false,"ca_institutions":"","funders":"General Motors of Canada","keywords":"Predictive maintenance; Automotive industry; Model predictive control; Prognostics; Exploit; Interpretability; Machine learning; Pipeline (software); Component (thermodynamics); Engineering; Computer science; Artificial intelligence; Reliability engineering; Control (management); Computer security","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":"metacan-v3-hybrid-931329e0061c","candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.001916175,0.000703493,0.0004327437,0.0007099938,0.0003896768,0.001498975,0.001590133,0.001243338,0.002085349],"category_scores_gemma":[0.007213349,0.0002796556,0.0004147038,0.000518317,0.0006589598,0.002085,0.0007606982,0.001664515,0.0003584595],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.0008920926,"about_ca_system_score_gemma":0.001012066,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.006544434,"about_ca_topic_score_gemma":0.008296834,"domain_scores_codex":[0.9993696,0.0002167192,0.00004115524,0.00008927476,0.0002349431,0.00004848667],"domain_scores_gemma":[0.996089,0.002697985,0.0001015605,0.0002983253,0.0007246355,0.00008846935],"domain_codex":null,"domain_gemma":null,"domain_candidate":null,"domain_consensus":null,"study_design_codex":"design_other","study_design_gemma":"observational","study_design_scores_codex":[0.0002339356,0.0006252383,0.01178006,0.0006286547,0.0001255013,0.001217472,0.001586239,0.3302687,0.006140205,0.08372897,0.01242057,0.5512444],"study_design_scores_gemma":[0.00006992224,0.0002328835,0.002833351,0.0002834212,0.0000662668,0.0005882439,0.00104797,0.8474717,0.01058449,0.1133333,0.02341756,0.00007083213],"study_design_candidate":"observational","study_design_consensus":null,"genre_codex":"methods","genre_gemma":"empirical","genre_scores_codex":[0.1294874,0.003367303,0.8206115,0.01328781,0.0002142372,0.0001950528,0.0002932118,0.0007558899,0.03178765],"genre_scores_gemma":[0.7660994,0.001558227,0.228085,0.0002911407,0.00005938616,0.00009018079,0.0001598013,0.000090765,0.003566252],"genre_candidate":"empirical","genre_consensus":null,"teacher_disagreement_score":0.006544434,"threshold_uncertainty_score":0.01301271,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.128938899315005,"score_gpt":0.3249527489904817,"score_spread":0.1960138496754766,"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."}}