Special vehicle engine digital maintenance system based on big data analysis
By using an improved SegmenTier algorithm and directed transition similarity calculation, combined with adaptive segmentation cost generation and evidence interval resegmentation, the temporal analysis problem of the engine maintenance system under extreme environments was solved, and the accuracy and reliability of operating condition identification and maintenance triggering were improved.
Patent Information
- Authority / Receiving Office
- CN Β· China
- Patent Type
- Applications(China)
- Current Assignee / Owner
- CHINA NORTH ENGINE INST TIANJIN
- Filing Date
- 2026-04-27
- Publication Date
- 2026-07-17
AI Technical Summary
Existing engine maintenance systems struggle to establish a stable and reliable time-series analysis foundation under extreme environments, failing to accurately characterize directional changes and state continuity during operating condition transitions. This results in delayed early warning identification, impacting the accuracy and practicality of maintenance results.
An improved SegmenTier algorithm is adopted, which combines directed transition similarity calculation, adaptive segmentation cost generation and evidence interval resegmentation processing to recursively divide the engine operating condition state segment and determine maintenance triggers, forming continuous and comparable engine time series characterization results. The maintenance feedback records are used to locate the precursor evidence interval for resegmentation processing.
It improves the accuracy of operating condition segment division and the reliability of maintenance triggering, enhances the stability of operating condition identification results and the pertinence of maintenance results under complex engine operating conditions, and reduces the risk of misjudgment.
Smart Images

Figure CN122415064A_ABST