An anomaly detection method for rotating machinery based on pre-trained Speech Recognition Large Model
ID：127
Submission ID：42 View Protection：ATTENDEE
Updated Time：2024-10-23 10:02:34 Hits：31
Poster Presentation
Start Time：Pending （Asia/Shanghai）
Duration：Pending
Session：[No Session] » [No Session Block]
Presentation File
Tips: The file permissions under this presentation are only for participants. You have not logged in yet and cannot view it temporarily.
Abstract
旋转机械是现代工业生产中的关键设备，广泛应用于许多工业领域。其正常运行对于提高生产效率和确保生产安全至关重要。但是，设备的长期运行会导致部件老化和失效，从而造成一系列不利因素。因此，进行有效的异常检测以确保旋转机械的稳定运行显得尤为重要。本文提出的方法利用预训练语音识别大模型的编码器部分提取工业机器信号的时频域特征，并将语音处理领域的技术转移到机械故障诊断中。该方法使用参数较少的监控模型来适应数据变化，并评估在有监督和无监督条件下异常检测的 AUC 值。实验结果表明，该方法在一定程度上提高了异常检测的准确率，增强了模型的泛化能力。
Keywords
anomaly detection,machine health monitoring,transfer learning,speech recognition large model
Speaker
YangYuQi
student Beijing University of Chemical TechnologySubmission Author
All comments
15th August 2024 31st August 2024- Manuscript Submission
15th September 2024 - Acceptance Notification
1st October 2024 - Camera Ready Submission
1st October 2024 – Early Bird Registration
Contact Us
Website:
https://icsmd2024.aconf.org/
Comment submit