{"id":"W4394601366","doi":"10.1016/j.egyai.2024.100366","title":"Advanced wind turbine blade inspection with hyperspectral imaging and 3D convolutional neural networks for damage detection","year":2024,"lang":"en","type":"article","venue":"Energy and AI","topic":"Icing and De-icing Technologies","field":"Engineering","cited_by":34,"is_retracted":false,"has_abstract":true,"ca_institutions":"École de Technologie Supérieure; Université du Québec à Trois-Rivières; Université du Québec à Rimouski","funders":"Natural Sciences and Engineering Research Council of Canada","keywords":"Hyperspectral imaging; Convolutional neural network; Fault detection and isolation; Context (archaeology); Turbine; Wind power; Turbine blade; Computer science; Artificial intelligence; Remote sensing; Engineering; Aerospace engineering; Geology","routes":{"ca_aff":true,"ca_fund":true,"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":[0.00020245,0.0004324861,0.0002094998,0.0004942752,0.0001099939,0.000336924,0.0004115691,0.0004183304,0.0006592926],"category_scores_gemma":[0.000518264,0.0002773315,0.000324946,0.0003821345,0.0002224787,0.0005959828,0.0003912316,0.000476604,0.000264089],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.0004617584,"about_ca_system_score_gemma":0.000378017,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.005166363,"about_ca_topic_score_gemma":0.01076973,"domain_scores_codex":[0.9998821,0.00001689749,0.000004590828,0.00003164425,0.00004882311,0.00001584785],"domain_scores_gemma":[0.9998548,0.00003722469,0.00003396527,0.00002222877,0.00004254158,0.000009141724],"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":[0.0002050713,0.0002008022,0.00687347,0.0001288349,0.0001120979,0.0002391294,0.00009318384,0.3693917,0.128492,0.003679735,0.004132009,0.486452],"study_design_scores_gemma":[0.000001431752,0.00001366369,0.001006284,0.000003616959,0.000004878107,0.00002583161,0.000005585763,0.9925641,0.005280237,0.0005861748,0.0005032456,0.000004875921],"study_design_candidate":"bench_or_experimental","study_design_consensus":null,"genre_codex":"methods","genre_gemma":"empirical","genre_scores_codex":[0.1368875,0.001089434,0.856007,0.0003884405,0.00008898482,0.00004529306,0.0002256175,0.001637478,0.003630209],"genre_scores_gemma":[0.7834987,0.0006693152,0.2120744,0.0001391974,0.00004595035,0.00003920533,0.0003856943,0.00005090384,0.003096667],"genre_candidate":"empirical","genre_consensus":null,"teacher_disagreement_score":0.005166363,"threshold_uncertainty_score":0.01027256,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.002914102991037246,"score_gpt":0.1852232878992273,"score_spread":0.1823091849081901,"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."}}