Geotechnical material data driving construction modeling method and device based on knowledge migration strategy

By constructing high-fidelity and low-fidelity datasets and combining them with transfer learning techniques, the problem of insufficient generalization ability and prediction accuracy of geotechnical constitutive models in practical engineering was solved, achieving more efficient model training and more accurate stress-strain prediction.

CN121747769APending Publication Date: 2026-03-27WUHAN UNIV
0 Cites 2 Cited by

Patent Information

Application Number
CN202511622451.3
Authority / Receiving Office
CN · China
Patent Type
Applications(China)
Current Assignee / Owner
Filing Date
2025-11-06
Publication Date
2026-03-27

AI Technical Summary

Technical Problem

In existing technologies, constitutive models of geotechnical materials face challenges such as insufficient robustness and small sample size modeling difficulties in practical engineering applications, resulting in insufficient generalization ability and prediction accuracy of data-driven models.

Method used

A knowledge transfer-based strategy is adopted. By constructing high-fidelity and low-fidelity datasets, the constitutive model is first driven by pre-trained data from the low-fidelity dataset, and then fine-tuned by the high-fidelity dataset to form the final geotechnical material data-driven constitutive model.

Benefits of technology

It improves the accuracy of data-driven constitutive models in characterizing and predicting the real stress-strain behavior of geotechnical materials, provides reliable model support, and offers an effective solution for geotechnical engineering mechanics analysis and design.

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

Abstract

The invention relates to the technical field of geotechnical material local modeling, in particular to a geotechnical material data driving local modeling method and device based on a knowledge migration strategy, and the method comprises the steps: building a first mapping data pair based on the stress-strain physical quantity of a test curve sampling point, and building a high-fidelity data set of a geotechnical material; constructing a second mapping data pair based on the stress-strain state of the simulation curve sampling point and the intermediate physical quantity label, and establishing a low-fidelity data set of the geotechnical material; pre-training the target data-driven constitutive model by using the low-fidelity data set to generate an initial geotechnical material data-driven constitutive model; and driving the model to be fine-tuned by using the high-fidelity data set for the initial geotechnical material data, and generating final geotechnical material data to drive the model. Therefore, the problem of insufficient generalization ability and prediction precision of a data-driven model due to limited training data and unpredictability of a stress path in the prior art is solved.
Need to check novelty before this filing date? Find Prior Art