A face rockfill dam multi-measuring point deformation safety monitoring method and system based on seepage flow

By constructing a multi-point deformation safety monitoring method for rockfill dams based on seepage flow, and combining seepage flow data preprocessing and machine learning models, the reliability and ambiguity of physical concepts in existing monitoring methods are solved, and real-time safety monitoring of rockfill dam structures is realized.

CN120296841BActive Publication Date: 2026-07-24HUBEI QINGJIANG HYDROPOWER DEV +2
View PDF 0 Cites 0 Cited by

Patent Information

Authority / Receiving Office
CN · China
Patent Type
Patents(China)
Current Assignee / Owner
HUBEI QINGJIANG HYDROPOWER DEV
Filing Date
2025-03-25
Publication Date
2026-07-24

AI Technical Summary

Technical Problem

Existing methods for monitoring deformation of concrete-faced rockfill dams lack reliability, have unclear physical concepts, fail to effectively incorporate changes in seepage flow, and are therefore difficult to monitor structural safety.

Method used

By preprocessing the seepage flow monitoring data, a random forest model is constructed, important factors are screened using the SHAP interpretation method, and a seepage flow calculation model driven by multiple effect factors is established by combining regression analysis or machine learning methods to determine the seepage flow control threshold for safety monitoring.

Benefits of technology

It has achieved integrated monitoring of deformation at multiple measuring points in panel rockfill dams, improving the accuracy and reliability of monitoring, clarifying the physical relationship between seepage flow and deformation, and is highly adaptable with real-time safety assessment capabilities.

✦ Generated by Eureka AI based on patent content.

Smart Images

  • Figure CN120296841B_ABST
    Figure CN120296841B_ABST
Patent Text Reader

Abstract

The application discloses a kind of panel rock-fill dam multi-measuring point deformation safety monitoring method and system based on seepage flow.The method comprises the following steps: preprocessing seepage flow, relevant deformation measuring point and environmental quantity monitoring data; dividing training set and test set, constructing random forest model with relevant deformation measuring point measurement value as input and seepage flow as output; analyzing the model using SHAP interpretation method and selecting important factors; modeling the important factors using regression or machine learning method, constructing multi-effect quantity joint driving seepage flow calculation model and evaluating precision; determining the seepage flow control threshold, inputting multi-measuring point deformation and environmental factors into the model, comparing the calculated value with the threshold, and realizing multi-measuring point deformation safety fusion monitoring.The application improves the accuracy of panel rock-fill dam structure safety monitoring, has clear physical concept, is easy to implement, has high reliability and strong adaptability, and helps to timely grasp the dam safety state and ensure the safe operation of the dam.
Need to check novelty before this filing date? Find Prior Art