Explainable, minimally simplified intelligent data augmentation methods, systems, and media applicable to fault diagnosis of high-end equipment

By constructing an interpretable encoder and decoder based on a two-layer residual stacking structure, and combining it with the Transformer module to generate high-quality simulated vibration signals, the reliability problem of fault diagnosis under small sample size and class imbalance in high-end equipment was solved, achieving efficient and interpretable data augmentation and fault diagnosis.

CN122020005BActive Publication Date: 2026-06-30NANJING TECH UNIV
5 Cites 0 Cited by

Patent Information

Application Number
CN202610475383.0
Authority / Receiving Office
CN · China
Patent Type
Patents(China)
Current Assignee / Owner
Filing Date
2026-04-13
Publication Date
2026-06-30
Estimated Expiration
2046-04-13

AI Technical Summary

Technical Problem

Under conditions of small sample size, class imbalance, and limited engineering computing power, existing intelligent data augmentation methods for high-end equipment suffer from poor reliability of fault diagnosis models due to uninterpretable generation processes, unstable training, and low sampling efficiency.

Method used

An interpretable encoder and decoder based on a two-layer residual stacking structure are adopted. The encoder and decoder are trained by a joint objective function of reconstruction error and sparse regularization, and the vibration signal is mapped as a low-dimensional interpretable variable to build a simplified data generation model. The Transformer module is used for conditional generation to generate simulated vibration signals to build a balanced training dataset.

Benefits of technology

It improves the interpretability, controllability, and stability of the data augmentation process, enhances the stability and effectiveness of the fault diagnosis model under complex operating conditions, reduces sampling computation overhead, and is suitable for engineering deployment.

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

Abstract

This invention discloses an interpretable, minimally simplified intelligent data augmentation method, system, and medium suitable for fault diagnosis of high-end equipment. The method includes the following steps: acquiring vibration signal data; standardizing the data and dividing it into training and test sets; constructing an interpretable encoder and decoder; training the interpretable encoder and decoder; freezing parameters and mapping the training set to a variable set; constructing a minimally simplified data generation model and training the model using the variable set; sampling to generate new interpretable variables; back-translating simulated vibration signals; mixing these signals with samples from the training set to construct a balanced training dataset; training a classifier; using the classifier to perform fault diagnosis on the test set; and outputting the diagnostic results. This invention solves the problem of poor reliability of fault diagnosis models in existing intelligent data augmentation methods for high-end equipment under conditions of small sample sizes, class imbalance, and limited engineering computing power, due to uninterpretable generation processes, unstable training, and low sampling efficiency.
Need to check novelty before this filing date? Find Prior Art