An optimisation approach guided by crack variation mechanism in the informer prediction model

Structural health monitoring (SHM) faces a fundamental challenge in reconciling predictive performance with physical interpretability for infrastructure diagnostics. Conventional deep learning (DL) approaches neglect essential mechanisms governing crack width variation—including thermal gradients, hysteretic responses, and phase-shifted correlations—limiting their reliability in real-world applications. To bridge this gap, we propose a mechanism-guided optimization (MGO) framework that integrates domain knowledge into the Informer architecture through physics-informed enhancements: auto-correlation modeling for capturing temperature-crack hysteresis, static gated fusion for multi-feature integration, and adaptive elastic net regularization for feature selection. Validated on cable-stayed bridge monitoring data, our framework achieves significant mean absolute error reductions (MAE) (5 %–60 %) and root mean square error reductions (RMSE) (10 %–55 %) versus baseline Informer across all cracks and prediction horizons, with diebold-mariano (DM) tests confirming statistical superiority in most cases. Crucially, it demonstrates superior precision relative to six state-of-the-art benchmarks across all evaluation scenarios. The ordinary least squares (OLS)-enhanced variant further delivers volatility reduction, while sensor failure tests establish quantifiable robustness benchmarks through MAE progression from 0.013 mm to 0.391 mm. This work establishes an interpretable, physics-grounded paradigm that explicitly links environmental drivers to structural degradation.