Sensor-Driven Bridge Digital Twins for Predictive Maintenance Under Sparse and Noisy Monitoring Data: An Illustrative Structural Health Study

This article presents a clearly labeled simulated empirical study spanning Civil Engineering. A simulated three-span bridge digital twin was driven by accelerometer, strain, temperature, and traffic-load streams. Sensor noise, missing data, seasonal temperature shifts, stiffness loss, and bearing degradation were introduced. Conventional threshold monitoring was compared with a continuously updated digital-twin estimator using modal frequency, strain residuals, and uncertainty bounds. The digital-twin approach detected the simulated 8% local stiffness-loss scenario earlier than threshold monitoring and reduced false maintenance alerts during temperature-driven modal shifts. Confidence degraded when more than 30% of sensing channels were unavailable, emphasizing the need for redundancy and uncertainty reporting. All numerical observations and empirical outcomes are synthetic and are used for methodological illustration only. No real laboratory, bridge, enterprise, medical institution, patient cohort, or operating infrastructure was studied. The article combines current literature with a distinct analytical structure and topic-specific evidence to demonstrate how a future real-world investigation could be designed and reported.