Complex engineering systems—such as ultra-long horizontal wells in energy exploitation and distributed rail transit infrastructure—operate under harsh physical and environmental conditions, where accurate physical modeling and real-time parameter estimation are essential for ensuring safety, efficiency, and reliability. Traditional empirical and black-box data-driven approaches often fail to account for the underlying physical mechanisms, thereby limiting interpretability and generalizability. To address this, we propose a unified framework that integrates physics-informed scenario-based modeling with data-driven parameter inversion. In the first stage, critical system parameters—such as friction coefficients in drill string movement or contact forces in rail–wheel interactions—are explicitly formulated based on mechanical theory, leveraging symmetries and boundary conditions to improve model structure and reduce computational complexity. In the second stage, model parameters are identified or updated through inverse modeling using historical or real-time field data, enhancing predictive performance and engineering insight. The proposed methodology is demonstrated through two representative cases. The first involves friction estimation during tripping operations in the SU77-XX-32H5 ultra-long horizontal well of the Sulige Gas Field, where a mechanical load model is constructed and field-calibrated. The second applies the framework to rail transit systems, where wheel–rail friction is estimated from dynamic response signals to support condition monitoring and wear prediction. The results from both scenarios confirm that incorporating physical symmetry and data-driven inversion significantly enhances the accuracy, robustness, and interpretability of engineering analyses across domains.
Zhang et al. (Fri,) studied this question.
Synapse has enriched 5 closely related papers on similar clinical questions. Consider them for comparative context: