{"id":"W3125741799","doi":"10.1002/pip.3395","title":"Deep learning‐based automatic detection of multitype defects in photovoltaic modules and application in real production line","year":2021,"lang":"en","type":"article","venue":"Progress in Photovoltaics Research and Applications","topic":"Photovoltaic System Optimization Techniques","field":"Energy","cited_by":67,"is_retracted":false,"has_abstract":true,"ca_institutions":"Optech (Canada)","funders":"National Natural Science Foundation of China","keywords":"Confusion matrix; Computer science; Artificial intelligence; Convolutional neural network; Line (geometry); Production line; Object detection; Photovoltaic system; Pattern recognition (psychology); Deep learning; Compensation (psychology); Confusion; Computer vision; Engineering; Mathematics; Electrical engineering","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":[0.001398118,0.0001994033,0.0003612256,0.001028624,0.000151455,0.00006097673,0.0001715965,0.0002284975,0.000006667738],"category_scores_gemma":[0.0004256543,0.000224875,0.0000310024,0.00283307,0.0003710836,0.0001912985,0.0001336205,0.0005776624,0.000003094756],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.0002592938,"about_ca_system_score_gemma":0.000119307,"about_ca_topic_candidate":true,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.003418877,"about_ca_topic_score_gemma":0.02117081,"domain_scores_codex":[0.9972664,0.0004258288,0.0006927779,0.0007215766,0.0004612118,0.0004322639],"domain_scores_gemma":[0.9983553,0.0003172071,0.0001886603,0.0004770696,0.0005533337,0.0001084179],"domain_codex":null,"domain_gemma":null,"domain_candidate":null,"domain_consensus":null,"study_design_codex":"bench_or_experimental","study_design_gemma":"bench_or_experimental","study_design_scores_codex":[0.0001471292,0.001474004,0.3097937,0.001120078,0.00001863573,0.00001314951,0.0006937135,0.009460752,0.4961174,0.001664398,0.000002780154,0.1794942],"study_design_scores_gemma":[0.0007975343,0.000117911,0.0407007,0.0001930607,0.000005518979,0.000009034753,0.0003584345,0.4749647,0.4778329,0.004338991,0.0004821784,0.0001990072],"study_design_candidate":"bench_or_experimental","study_design_consensus":"bench_or_experimental","genre_codex":"empirical","genre_gemma":"empirical","genre_scores_codex":[0.9836113,0.002118468,0.01086233,0.00004510271,0.00002120312,0.002816464,0.000005406494,0.0001827748,0.0003368957],"genre_scores_gemma":[0.9865459,0.001660958,0.004832101,0.000005837381,0.00003311508,0.006762615,0.00008293393,0.00003988517,0.00003661753],"genre_candidate":"empirical","genre_consensus":"empirical","teacher_disagreement_score":0.4655039,"threshold_uncertainty_score":0.9966903,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.02982781175951469,"score_gpt":0.3402785281248892,"score_spread":0.3104507163653745,"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."}}