Railway track quality evaluation method and device
By performing wavelet decomposition on track geometry detection data and training a prediction model, the problem that the existing track quality evaluation method cannot reflect vehicle response is solved, scientific assessment of track quality and discovery of invisible diseases are achieved, and the safety and comfort of train operation are improved.
Patent Information
- Application Number
- CN202210108642.8
- Authority / Receiving Office
- CN · China
- Patent Type
- Patents(China)
- Current Assignee / Owner
- Filing Date
- 2022-01-28
- Publication Date
- 2025-09-05
- Estimated Expiration
- 2042-01-28
AI Technical Summary
The existing track quality evaluation methods based on track geometry statistics cannot objectively reflect the actual vehicle response and cannot detect the invisible track geometry defects that affect the safety and comfort of train operation.
By acquiring the track geometry detection data of the railway track, wavelet decomposition is used to classify it into different wavelength components, and these components are imported into the prediction model. The prediction model is trained to determine the vehicle response, and finally the track quality is evaluated based on the vehicle response.
It realizes the conversion of track geometry detection data into vehicle response, can discover invisible defects that affect the safety and comfort of train operation, and provide scientific track quality assessment and reasonable maintenance and repair guidance.
Smart Images

Figure CN114462700B_ABST
Abstract
Citation Information
Patent Citations
Security judging method of rail irregularity state
CN102521432A
Method for predicting orbit quality by using fuzzy neural network
CN112036599A