Incremental learning based method for gear fault diagnosis of a transmission system

By using incremental learning methods and optimizing model parameters with generalized entropy index and attention distillation loss, the problems of new fault identification and catastrophic forgetting in gear fault diagnosis of transmission systems are solved. This enables effective diagnosis of streaming data and memorization of old fault features, thereby improving the state monitoring capability of mechanical systems.

CN120063715BActive Publication Date: 2026-06-09XI AN JIAOTONG UNIV
View PDF 3 Cites 0 Cited by

Patent Information

Authority / Receiving Office
CN · China
Patent Type
Patents(China)
Current Assignee / Owner
XI AN JIAOTONG UNIV
Filing Date
2025-01-22
Publication Date
2026-06-09

AI Technical Summary

Technical Problem

Existing intelligent diagnostic methods assume that the number of fault categories remains constant during deployment, making it impossible to effectively identify new faults. Furthermore, there is a catastrophic forgetting phenomenon in incremental learning, which causes the model to lose its ability to diagnose old faults.

Method used

An incremental learning-based approach is adopted to monitor emerging faults using the generalized entropy index. Attention distillation loss and task distillation loss are designed during the incremental training phase to optimize model parameters, alleviate catastrophic forgetting, and achieve diagnostic model updates for streaming data.

Benefits of technology

It enables continuous diagnosis of gear faults in the transmission system, improves the accuracy and reliability of condition monitoring, and ensures the service safety of mechanical systems.

✦ Generated by Eureka AI based on patent content.

Smart Images

  • Figure CN120063715B_ABST
    Figure CN120063715B_ABST
Patent Text Reader

Abstract

The application provides a drive system gear fault diagnosis method based on incremental learning, which comprises the following steps: first, using a sensor to collect drive system monitoring data and constructing an incremental data set, which is divided into fault diagnosis tasks of different stages; constructing an initial model and training the model based on initial fault data; defining a generalized entropy index to determine whether the fault is a new fault in the test stage; when new fault category data appears, a small amount of samples are randomly selected from old class data and fused with new class data to construct a training set; in order to avoid the forgetting of the model to the old class fault data, knowledge distillation is performed on the attention weight and the old class prediction output during training; when the generalized entropy index continues to judge that an unknown fault appears, the network training step is repeated to update the model, and finally the incremental learning of the fault mode is realized. The application can realize the continuous updating of the fault diagnosis model for the streaming data, improve the state monitoring capability of the drive system, and provide protection for the service safety of the mechanical system.
Need to check novelty before this filing date? Find Prior Art