Highway global traffic state estimation method based on distributed optical fiber sensing and physical information neural network

By constructing a ResUNet network and optimizing the physical constraint loss function, the problems of noise interference and signal coverage in highway traffic state estimation using distributed fiber optic sensing technology are solved, achieving accurate traffic state estimation and data output to support traffic management.

CN122435786APending Publication Date: 2026-07-21HEFEI UNIV OF TECH
View PDF 0 Cites 0 Cited by

Patent Information

Authority / Receiving Office
CN Β· China
Patent Type
Applications(China)
Current Assignee / Owner
HEFEI UNIV OF TECH
Filing Date
2026-04-28
Publication Date
2026-07-21

AI Technical Summary

Technical Problem

Existing distributed fiber optic sensing technology suffers from noise interference and signal coverage problems in highway traffic state estimation, resulting in unclear vehicle trajectories. Furthermore, physical information neural network models cannot effectively capture multi-scale spatiotemporal dependent features, leading to inaccurate traffic state estimation.

Method used

By constructing a ResUNet network, combining distributed fiber optic sensing data, performing gridding and semantic segmentation, optimizing the network using a physical constraint loss function, and extracting multi-scale traffic features, accurate estimation of traffic conditions can be achieved.

Benefits of technology

It improves the accuracy of traffic state estimation and the generalization ability of the model, outputs reliable data that conforms to the physical laws of traffic flow, and supports traffic incident detection and management.

✦ Generated by Eureka AI based on patent content.

Smart Images

  • Figure CN122435786A_ABST
    Figure CN122435786A_ABST
Patent Text Reader

Abstract

The application discloses a kind of based on distributed optical fiber perception and physical information neural network's expressway global traffic state estimation method, comprising:1 by DAS collection expressway vehicle vibration signal and transform into vehicle space-time trajectory chart, each grid flow, speed is calculated after grid operation, the space-time flow chart and space-time speed chart obtained as model input;2 design ResUNet network, configure multi-scale hollow convolution module at network bottleneck layer, expand receptive field;3 LWR continuity constraint, FD basic map constraint, ARZ momentum constraint traffic flow physical law are embedded into loss function, so that the repaired flow and speed information meet the characteristics of real traffic flow, realize traffic space-time chart accurate repair.The application multiplexes existing communication optical fiber, realizes expressway global continuous perception, model has data fitting ability and physical rationality, can accurately output global traffic flow speed, flow state, provides reliable data support for traffic event detection and traffic management use, and engineering practicability is high.
Need to check novelty before this filing date? Find Prior Art