Logo
ScienceStack
Table of Contents
Fetching ...
Sign In

Traffic and weather driven hybrid digital twin for bridge monitoring

Phani Raja Bharath Balijepalli, Bulent Soykan, Veeraraghava Raju Hasti

Abstract

A hybrid digital twin framework is presented for bridge condition monitoring using existing traffic cameras and weather APIs, reducing reliance on dedicated sensor installations. The approach is demonstrated on the Peace Bridge (99 years in service) under high traffic demand and harsh winter exposure. The framework fuses three near-real-time streams: YOLOv8 computer vision from a bridge-deck camera estimates vehicle counts, traffic density, and load proxies; a Lighthill--Whitham--Richards (LWR) model propagates density $ρ(x,t)$ and detects deceleration-driven shockwaves linked to repetitive loading and fatigue accumulation; and weather APIs provide deterioration drivers including temperature cycling, freeze-thaw activity, precipitation-related corrosion potential, and wind effects. Monte Carlo simulation quantifies uncertainty across traffic-environment scenarios, while Random Forest models map fused features to fatigue indicators and maintenance classification. The framework demonstrates utilizing existing infrastructure for cost-effective predictive maintenance of aging, high-traffic bridges in harsh climates.

Traffic and weather driven hybrid digital twin for bridge monitoring

Abstract

A hybrid digital twin framework is presented for bridge condition monitoring using existing traffic cameras and weather APIs, reducing reliance on dedicated sensor installations. The approach is demonstrated on the Peace Bridge (99 years in service) under high traffic demand and harsh winter exposure. The framework fuses three near-real-time streams: YOLOv8 computer vision from a bridge-deck camera estimates vehicle counts, traffic density, and load proxies; a Lighthill--Whitham--Richards (LWR) model propagates density and detects deceleration-driven shockwaves linked to repetitive loading and fatigue accumulation; and weather APIs provide deterioration drivers including temperature cycling, freeze-thaw activity, precipitation-related corrosion potential, and wind effects. Monte Carlo simulation quantifies uncertainty across traffic-environment scenarios, while Random Forest models map fused features to fatigue indicators and maintenance classification. The framework demonstrates utilizing existing infrastructure for cost-effective predictive maintenance of aging, high-traffic bridges in harsh climates.
Paper Structure (24 sections, 4 equations, 4 figures)

This paper contains 24 sections, 4 equations, 4 figures.

Table of Contents

  1. Traffic and weather driven hybrid digital twin for bridge monitoring
  2. Introduction
  3. Methodology
  4. Live data ingestion and pre-processing
  5. Computer vision: vehicle detection and traffic observables
  6. Observation-to-state mapping with missing-detection stabilization
  7. Environmental stress modifiers
  8. Physics core: LWR traffic flow model
  9. Shockwave and stress proxies
  10. Fatigue damage accumulation
  11. Reliability index for risk-informed assessment
  12. Machine learning layer: Random Forest fatigue prediction
  13. Monte Carlo uncertainty quantification
  14. Implementation and reproducibility
  15. Results
  16. ...and 9 more sections

Figures (4)

  • Figure 1: High-level hybrid digital twin workflow for camera- and weather-driven bridge condition monitoring.
  • Figure 2: Time-varying structural reliability index ($\beta$) from the hybrid digital twin: simulated ($\beta_\mathrm{sim}$), observation-derived ($\beta_\mathrm{obs}$), and the composite primary series ($\beta_\mathrm{primary}$), which defaults to $\beta_\mathrm{obs}$ when available and $\beta_\mathrm{sim}$ otherwise. All three remain above the target threshold ($\beta = 3.0$) throughout the monitoring window.
  • Figure 3: Simulated shockwave speeds from the LWR traffic flow model compared against observed proxies inferred from abrupt density and speed transitions. The model reproduces the timing and relative magnitude of major stop--go event; high-amplitude spikes in the observed signal are attributed to measurement variability rather than physical wave speeds.
  • Figure 4: Probability distribution of fatigue scores from Monte Carlo simulation under stochastic traffic demand, with threshold markers at fatigue scores of 50 (safe) and 70 (monitor). The distribution characterizes the range of structural demand outcomes across randomized traffic realizations.