A shield machine fault prediction method based on operation big data

CN121637261BActive Publication Date: 2026-07-14CHINA CONSTR FIFTH ENG DIV CORP LTD +2

Patent Information

Authority / Receiving Office: CN · China
Patent Type: Patents(China)
Current Assignee / Owner: CHINA CONSTR FIFTH ENG DIV CORP LTD
Filing Date: 2025-12-29
Publication Date: 2026-07-14

AI Technical Summary

Technical Problem

Existing methods for diagnosing and predicting tunnel boring machine (TBM) faults are unable to distinguish between parameter fluctuations caused by changes in operating conditions and actual equipment degradation. They lack consideration of the correlation between multiple operating parameters, cannot effectively characterize the fault evolution process, and lack explicit modeling of uncertain factors, resulting in unstable prediction results.

Method used

By collecting tunnel boring machine operating parameters in real time, calculating the reliability coefficient for correction, performing adaptive normalization processing of working conditions, extracting monotonic degradation features, constructing a long short-term memory network fault probability prediction model, and setting graded early warning probability thresholds for early warning.

Benefits of technology

It effectively eliminates interfering factors, accurately quantifies the equipment degradation process, achieves accurate prediction of failure probability, and provides tiered early warning alerts, thereby improving the accuracy and stability of prediction.

✦ Generated by Eureka AI based on patent content.

Smart Images

Figure CN121637261B_ABST

Patent Text Reader

Abstract

The application discloses a shield machine fault prediction method based on operation big data, first, real-time operation parameters of the shield machine are collected and parameter correction is carried out, then after the corrected parameters are subjected to working condition self-adaptive normalization processing, monotone degradation features are extracted, a comprehensive degradation index is calculated, the historical sequence corresponding to the comprehensive degradation index before the current moment is input into a fault probability prediction model for fault prediction, a fault probability is obtained, finally, a graded early warning probability threshold is set, and graded early warning reminding is carried out. The application can effectively eliminate interference factors and quantify the equipment degradation process, so that accurate prediction of the fault probability is realized.

Need to check novelty before this filing date? Find Prior Art