Automatic generation of fine-grained traffic load spectrum via fusion of weigh-in-motion and vehicle spatial–temporal information

Accurate measurement of traffic loads is critical in bridge assessments, but current methods are not sufficient for refined analysis of bridge structures. The authors propose a data fusion method to generate fine-grained traffic load spectra using weigh-in-motion data, vehicle spatial-temporal data, and data on passing vehicles. The method is tested on an interchange viaduct in Shaanxi, China. The average biases of the longitudinal and transverse locations of moving vehicles, identified using the method, are 1.31 and 0.14 meters, respectively. The accuracy in these directions improved by 19% and 56%, respectively, compared a video identification method based on deep learning. The accuracy of the axle number identification is nearly 100%. Also, an automatically generated, very accurate, fine-grained traffic load spectrum is shown. The method can be applied in other scenarios for analysis and prediction of bridge performance under traffic loads.

Language

  • English

Media Info

Subject/Index Terms

Filing Info

  • Accession Number: 01843681
  • Record Type: Publication
  • Files: TRIS
  • Created Date: Apr 25 2022 10:07AM