Predictive Operation and Maintenance Decision-Making for Underground Pipelines Based on Fusion of Multi-Source Monitoring Data

Abstract:

Underground pipe networks are the critical infrastructures for urban and industrial energy supply. The predictive operation and maintenance （O&M） is the key issue for ensuring service throughout their life cycle. According to the failure damage mechanism of underground continuous pipelines， a stress analysis model is proposed based on the multi-source monitoring data fusion， and specific fusion algorithms are provided. A decision model for the first maintenance inspection plan is presented based on the time-dependent reliability， which considers the structural deterioration caused by uniform corrosion. A practical case showed that the fusion algorithm can successfully estimate unpredictable longitudinal bending stress and axial thermal stress， which demonstrates the effectiveness of the method proposed in this paper. The comparison result between the proposed model and existing model proves that the longitudinal bending stress cannot be ignored in the safety assessment and service life prediction of underground pipelines.

Key words:underground pipelines;predictive operation and maintenance;time-dependent reliability;data fusion;Bayesian formula