Stress detection method and system based on multi-modal Gaussian kernel adaptive fusion

Through the multimodal Gaussian core adaptive fusion method, the problems of insufficient nonlinear modeling capabilities and poor robustness in the non-destructive detection of ferromagnetic materials are solved, and high-precision and strong adaptive stress detection are achieved, which improves the stability and accuracy of the model.

CN120470306APending Publication Date: 2025-08-12NANCHANG HANGKONG UNIVERSITY
0 Cites 2 Cited by

Patent Information

Application Number
CN202510553297.2
Authority / Receiving Office
CN · China
Patent Type
Applications(China)
Current Assignee / Owner
Filing Date
2025-04-29
Publication Date
2025-08-12

AI Technical Summary

Technical Problem

The existing non-destructive detection technology of ferromagnetic materials is difficult to adapt to the nonlinear coupling effect under complex working conditions, resulting in high error rate, missed detection rate and low repetition rate of stress inspection results. The traditional model is poorly robust, parameter optimization is easily trapped in local optimization, and the modeling of a single sensor is susceptible to environmental interference, and the prediction results are unstable.

Method used

The multimodal Gaussian core adaptive fusion method is adopted, and the multi-dimensional feature spectrum matrix is extracted and normalized by obtaining the time series of magnetic Buckhausen noise and magnetic acoustic emission signals, and a multi-dimensional feature spectrum matrix is extracted and normalized. A multi-modal Gaussian core adaptive fusion model is constructed. Combined with the L-BFGS-B algorithm optimization parameters, feature dimensionality reduction and adaptive adjustment mean and variance are introduced, a multi-level verification framework is constructed, and the optimal model is dynamically screened.

Benefits of technology

It improves the stability and accuracy of the stress prediction model, enhances the generalization ability under non-ideal operating conditions, breaks through the local optimal bottleneck of traditional models, and realizes the monitoring needs of high accuracy and strong adaptability.

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

Abstract

The invention discloses a stress detection method and system based on multi-modal Gaussian kernel adaptive fusion. The method comprises the following steps: acquiring time sequence signals of magnetic Barkhausen noise MBN and magnetoacoustic emission signals MAE; extracting a multi-dimensional characteristic spectrum matrix, and normalizing the multi-dimensional characteristic spectrum matrix to obtain a characteristic sample; constructing a multi-modal Gaussian kernel adaptive fusion model according to the multi-modal Gaussian kernel product fusion function, and outputting a stress predicted value Z by using the multi-modal Gaussian kernel adaptive fusion model; and quantitatively evaluating the prediction effect of the multi-modal Gaussian kernel adaptive fusion model by using the evaluation function. According to the method, two sensing features of magnetic Barkhausen and magnetoacoustic emission are fused, a feature selection and fusion network architecture based on principal component analysis is constructed, an evaluation method and a model are constructed through a classification machine learning algorithm, and high-robustness, high-precision and high-repeatability detection and prediction of ferromagnetic construction stress are realized.
Need to check novelty before this filing date? Find Prior Art