Abnormal vibration signal generation method and system
The synchronized training of a GAN's discriminator and classifier addresses the scarcity of abnormal signal samples, enhancing the generation and classification of diverse abnormal patterns in industrial equipment, achieving improved accuracy and efficiency in fault detection.
Patent Information
- Application Number
- TW114124581
- Authority / Receiving Office
- TW · TW
- Patent Type
- Patents
- Current Assignee / Owner
- Filing Date
- 2025-06-30
- Publication Date
- 2026-08-01
- Estimated Expiration
- 2045-06-29
AI Technical Summary
Existing methods for fault detection and classification of abnormal vibration signals in industrial equipment face challenges due to the scarcity of real abnormal signal samples, limitations in data annotation, and the instability of generative adversarial networks, leading to ineffective generation and classification of diverse abnormal patterns.
A method involving a generative adversarial network (GAN) with a synchronized discriminator and classifier, trained using a labeled dataset, to generate and classify abnormal vibration signals, optimizing both components through a total loss value to enhance data representation and classification accuracy.
The approach effectively expands the number of abnormal vibration signal samples and improves classification accuracy by jointly optimizing the generator and classifier, enabling accurate simulation and automatic classification of abnormal states.