Building structure dynamic anomaly detection method combined with physical information

By combining the SDAD-Net anomaly detection model with physical information, a steady-state reference and consistency constraints are constructed, which solves the problems of false alarms and false negatives in the detection of dynamic anomalies in building structures in the existing technology, and realizes reliable and robust detection under complex working conditions.

CN121902283BActive Publication Date: 2026-06-16SICHUAN QIHUI NEW MATERIALS CO LTD
View PDF 2 Cites 0 Cited by

Patent Information

Authority / Receiving Office
CN · China
Patent Type
Patents(China)
Current Assignee / Owner
SICHUAN QIHUI NEW MATERIALS CO LTD
Filing Date
2026-03-25
Publication Date
2026-06-16

AI Technical Summary

Technical Problem

Existing methods for detecting dynamic anomalies in building structures are unable to distinguish between normal response changes caused by environmental disturbances and real anomalies caused by structural performance degradation under complex working conditions. They lack physical interpretability, are prone to false alarms or missed alarms, and are difficult to meet the reliability and safety requirements of engineering applications.

Method used

The SDAD-Net anomaly detection model is adopted. By combining physical information with diffusion, multi-scale and judgment modules, steady-state reference, directional impact, consistency constraint and mass conservation diffusion are constructed to achieve accurate amplification and propagation suppression of the dynamic response of building structure, reduce environmental noise interference and improve the reliability and robustness of anomaly detection.

Benefits of technology

It effectively improves the detection accuracy and reliability of dynamic anomalies in building structures, can accurately identify anomalies of structural performance degradation under complex working conditions, reduces false alarms and false negatives, and provides interpretable detection results.

✦ Generated by Eureka AI based on patent content.

Smart Images

  • Figure CN121902283B_ABST
    Figure CN121902283B_ABST
Patent Text Reader

Abstract

The application provides a building structure dynamic anomaly detection method combined with physical information, relates to the field of anomaly detection, and aims at high-dimensional and strongly coupled building structure dynamic data. The SDAD-Net anomaly detection model is composed of a diffusion module, a multi-scale module and a judgment module. The diffusion module realizes accurate amplification and propagation suppression of real abnormal disturbance in the building structure dynamic response. The multi-scale module models time segmentation and cross-scale alignment of long-term historical sequences, and systematically describes evolution characteristics of the building structure dynamic response on different time scales. The judgment module completes building structure dynamic anomaly determination through time propagation modeling and difference measurement.
Need to check novelty before this filing date? Find Prior Art