Pavement performance prediction method driven by multi-source data

By employing a multi-source data-driven approach, spatiotemporal alignment and uncertainty quantification techniques, combined with a Bayesian neural network model and dynamic feedback mechanism, the challenge of multi-source data fusion was solved, enabling highly reliable prediction of pavement performance and precise maintenance decisions.

CN122087568APending Publication Date: 2026-05-26CHINA HIGHWAY ENG CONSULTING GRP CO LTD +1
1 Cites 0 Cited by

Patent Information

Application Number
CN202610128084.X
Authority / Receiving Office
CN · China
Patent Type
Applications(China)
Current Assignee / Owner
Filing Date
2026-01-29
Publication Date
2026-05-26

AI Technical Summary

Technical Problem

Existing pavement performance prediction methods fail to effectively integrate multi-source data, resulting in insufficient robustness of prediction results, making it difficult to support accurate maintenance decisions, and often leading to resource waste or deterioration of road conditions.

Method used

A multi-source data-driven approach is adopted, which processes multi-source data through spatiotemporal alignment and uncertainty quantification, uses a Bayesian neural network model to predict pavement performance, outputs probabilistic prediction results, and combines Monte Carlo simulation and dynamic feedback mechanism to optimize maintenance timing.

Benefits of technology

It improves the reliability and accuracy of pavement performance prediction, reduces the risk of maintenance misjudgment, realizes refined simulation and prediction of the future evolution of pavement performance, and supports differentiated precision maintenance strategies.

✦ Generated by Eureka AI based on patent content.
Patent Text Reader

Abstract

The invention provides a pavement performance prediction method driven by multi-source data, and relates to the technical field of road engineering and traffic infrastructure management, and the method comprises the steps: collecting multi-source data of a target road section, the multi-source data comprising time sequence remote sensing data, GIS spatial data and field detection data; performing preprocessing and fusion on the multi-source data to generate a fusion data sequence in time-space alignment, and performing uncertainty quantization on the fusion data sequence; inputting the fused data sequence into a pavement performance attenuation prediction model to obtain a pavement performance prediction sequence output by the model; calculating the pavement maintenance opportunity of the target road section based on the pavement performance prediction sequence; wherein the pavement performance attenuation prediction model is obtained based on historical multi-source data training, and is used for representing the correlation between the pavement performance and the multi-source data, and outputting a prediction result in a probability form.
Need to check novelty before this filing date? Find Prior Art