Measurement, Год журнала: 2025, Номер unknown, С. 117892 - 117892
Опубликована: Май 1, 2025
Язык: Английский
Measurement, Год журнала: 2025, Номер unknown, С. 117892 - 117892
Опубликована: Май 1, 2025
Язык: Английский
Advanced Engineering Informatics, Год журнала: 2025, Номер 66, С. 103487 - 103487
Опубликована: Май 26, 2025
Язык: Английский
Процитировано
0Journal of Engineering Design, Год журнала: 2025, Номер unknown, С. 1 - 24
Опубликована: Март 5, 2025
Язык: Английский
Процитировано
0Quality and Reliability Engineering International, Год журнала: 2025, Номер unknown
Опубликована: Май 6, 2025
ABSTRACT Considering scenarios in mechanical equipment involving continuous high‐frequency signal acquisition and challenges data transmission, this paper proposes an edge‐based fault diagnosis framework (EdgeDiag) based on high‐confidence information extraction to enhance model training improve the efficiency of diagnostic processing, including storage uploading. First, ensure accuracy while reducing computational burden edge devices, a lightweight is designed minimize number parameters. Next, high confidence–based strategy processing considering risk levels are developed, utilizing uncertainty analysis evaluate performance each class data. Finally, effectiveness proposed method validated through Raspberry Pi critical components systems. This approach addresses challenge transmitting all from significantly improving diagnosis.
Язык: Английский
Процитировано
0Measurement, Год журнала: 2025, Номер unknown, С. 117892 - 117892
Опубликована: Май 1, 2025
Язык: Английский
Процитировано
0