一种基于三源异构信号融合的高速卡簧故障识别检测方法
By using a three-source heterogeneous signal fusion method, combining vibration, acoustic emission, and microphone signals, a baseline statistical model is established, overcoming the limitations of a single signal source in traditional snap ring detection and achieving efficient identification and type differentiation of high-speed snap ring damage.
Patent Information
- Authority / Receiving Office
- CN · China
- Patent Type
- Applications(China)
- Current Assignee / Owner
- KERN LIEBERS TAICANG
- Filing Date
- 2026-06-15
- Publication Date
- 2026-07-17
AI Technical Summary
Traditional snap ring condition detection relies on a single signal source, which makes it difficult to effectively identify local damage under high-speed conditions. Furthermore, different damage types are prone to overlap with the normal group in the single-source feature space, leading to missed detection of weak damage samples.
A three-source heterogeneous signal fusion method is adopted, which combines vibration signal, microphone sound signal and acoustic emission signal. Through standardization, feature extraction and fusion, a baseline statistical model is established using highly sensitive features, and anomaly scores are calculated for fault identification.
It improves the robustness and accuracy of fault identification, significantly enhances the ability to identify weak damage to high-speed snap rings, and can distinguish the damage type.
Smart Images
Figure CN122409174A_ABST