一种列车客室低频声学状态的多源融合表征方法
By synchronously collecting low-frequency sound and vibration signals in the train passenger compartment and combining them with train operation status information, a multi-source dataset is constructed and audio encoding and multimodal fusion are performed. This solves the problems of insufficient accuracy and stability in low-frequency noise source identification and acoustic state analysis in existing technologies, and achieves more accurate noise source identification and acoustic state characterization.
Patent Information
- Authority / Receiving Office
- CN · China
- Patent Type
- Patents(China)
- Current Assignee / Owner
- DALIAN UNIV OF TECH
- Filing Date
- 2026-05-18
- Publication Date
- 2026-07-17
AI Technical Summary
Existing technologies are unable to accurately reflect the correlation between low-frequency sounds inside the train passenger compartment and the vibration of the train body, operating conditions and the location of measuring points, resulting in insufficient accuracy and stability in low-frequency noise source identification and acoustic state analysis.
By setting up sound acquisition units and vibration acquisition units in the train passenger compartment, low-frequency sound signals, vibration signals and train operation status information are acquired synchronously. Multi-source data synchronization and correlation are performed to construct a multi-source synchronous input dataset. Low-frequency sound signals are preprocessed, time-frequency analyzed and audio encoded. Noise sources are identified using an acoustic recognition model, and low-frequency acoustic state characterization results are generated through a multi-modal fusion model.
It improves the accuracy of low-frequency noise source identification in train passenger compartments and the stability of acoustic state analysis, enhances the digital expression and interpretability of low-frequency acoustic states, and can more accurately identify the composition of noise sources under multi-source coupling and operating condition switching conditions.
Smart Images
Figure CN122224223B_ABST