Semi-supervised fatigue test condition monitoring method based on adaptive confidence active learning

Through a semi-supervised method of adaptive confidence active learning, long short-term memory networks and active learning mechanisms are used to screen low-confidence samples for manual labeling, which solves the problems of high labeling cost and poor adaptability of traditional monitoring methods and realizes efficient and low-cost equipment status monitoring.

CN120448981BActive Publication Date: 2025-09-16JILIN UNIVERSITY
2 Cites 0 Cited by

Patent Information

Application Number
CN202510953471.2
Authority / Receiving Office
CN · China
Patent Type
Patents(China)
Current Assignee / Owner
Filing Date
2025-07-11
Publication Date
2025-09-16
Estimated Expiration
2045-07-11

AI Technical Summary

Technical Problem

Traditional equipment condition monitoring methods require a large amount of labeled data for training, which has high labeling costs and poor adaptability in different environments or working conditions. Semi-supervised methods are limited by the quality and representativeness of a small amount of labeled data.

Method used

A semi-supervised fatigue test state monitoring method based on adaptive confidence active learning is adopted. A state recognition model is constructed through a long short-term memory network. Combined with the active learning mechanism of adaptive confidence, low-confidence samples are screened for manual labeling and retraining, which reduces the labeling cost and improves the adaptability of the model.

Benefits of technology

It significantly reduces labeling costs, improves monitoring accuracy and the ability to adapt to complex working conditions, realizes adaptive evaluation of equipment operating status, and avoids economic losses and R&D interruptions caused by untimely monitoring.

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

Abstract

The present invention relates to a semi-supervised fatigue test state monitoring method based on adaptive confidence active learning, which belongs to the field of equipment state monitoring technology and solves the problems of high labeling cost and poor adaptability to working conditions in traditional monitoring methods. First, a data set consisting of fatigue test state monitoring data is constructed and divided into an initial training set, an active learning set and a validation set. Then, an LSTM is used to construct a state recognition model, and the initial training set is used for pre-training. After pre-training, an active learning model is constructed by adding a Softmax function, and the confidence of the active learning set samples is calculated. Samples below the threshold are screened out, and a retraining set is formed after manual labeling. The retraining set is used to train the state recognition model and adjust hyperparameters, and finally the model is evaluated on the validation set. By integrating active learning with adaptive confidence and a semi-supervised learning mechanism, the present invention significantly reduces the dependence on labeled data, has lower labeling costs, and has strong adaptability to complex working conditions.
Need to check novelty before this filing date? Find Prior Art