A data-driven underground gas storage production system string failure prediction model for time-varying reliability analysis

In underground gas storage (UGS) systems, the production tubing string system undergoes complex thermomechanical loading conditions, leading to fatigue damage accumulation and potential failure risks. To accurately assess the fatigue reliability and mitigate risks, it is crucial to develop a data-driven physics-informed uncertainty modeling approach that captures the coupled thermo-mechanical effects and accounts for various uncertainties. This study proposes a data-driven physics-informed modeling method based on thermomechanical coupling for fatigue reliability assessment and risk mitigation in critical UGS systems. A quantitative analysis method is introduced, which relies on small-scale multi-stage loading experiments and combines the stochastic degradation process with time-series reliability theory. To analyze the fatigue life of joints under complex loading conditions, a modified S-N curve model is developed. This model takes into account the influences of the dimension coefficient, stress concentration factors, surface finish coefficients, and thermal load. It considers the uncertainties associated with different temperature loads and surface finish on fatigue life. By integrating physics-informed modeling, uncertainty quantification, and fatigue damage accumulation analysis, this approach provides a comprehensive framework for fatigue reliability assessment and risk mitigation in critical UGS systems. It enables informed decision-making for safe and reliable operations, as well as optimized maintenance strategies, ultimately enhancing the overall system performance and mitigating potential failures.