Search research articles

ABOUT JoVE

Overview Leadership Blog JoVE Help Center

AUTHORS

Publishing Process Editorial Board Scope & Policies Peer Review FAQ Submit

LIBRARIANS

Testimonials Subscriptions Access Resources Library Advisory Board FAQ

RESEARCH

JoVE Journal Methods Collections JoVE Encyclopedia of Experiments Archive

EDUCATION

JoVE Core JoVE Business JoVE Science Education JoVE Lab Manual Faculty Resource Center Faculty Site

Terms & Conditions of Use

Search research articles

Related Experiment Videos

Adapted Oversampling-based Multi-layer Support Vector Machines for interpretable multi-class imbalance fault

Tao Chen¹, Yage Yuan¹, Jianan Wei²

¹Key Laboratory of Advanced Manufacturing Technology, Ministry of Education, Guizhou University, Guiyang, Guizhou 550025, China.

ISA Transactions

|June 23, 2026

Summary

Related Concept Videos

Multi-input and Multi-variable systems

Multi-input and Multi-variable systems

Cruise control systems in cars are designed as multi-input systems to maintain a driver's desired speed while compensating for external disturbances such as changes in terrain. The block diagram for a cruise control system typically includes two main inputs: the desired speed set by the driver and any external disturbances, such as the incline of the road. By adjusting the engine throttle, the system maintains the vehicle's speed as close to the desired value as possible.
In the absence of...

You might also read

Related Articles

Articles linked to this work by shared authors, journal, and citation graph.

Sort by

Same author

Mettl3-mediated FOXO1 mRNA translation inhibits myoblast differentiation and fusion through the MyoD1-Myomaker/Myomixer axis and the ubiquitin-proteasome system.

International journal of biological macromolecules·2026

Same author

Genomic characteristics of a <i>Streptococcus suis</i> of ST353 resulting in severe endophthalmitis with bilateral deafness.

Infectious diseases & immunity·2026

Same author

Research progress on MOF-based materials for the detection and protection against mustard gas and its simulants.

Analytical methods : advancing methods and applications·2026

Same author

Isolation and Characterization of Infection-Competent Monkeypox Virus Clade Ib Strains in Environmental Samples of First-Confirmed Mpox Clusters in China.

Journal of medical virology·2026

Same author

Physics-informed neural network-based simulation of pulmonary arterial hemodynamics abnormalities.

Biomedizinische Technik. Biomedical engineering·2026

Same author

A two-dimensional superatomic B<sub>6</sub>O<sub>2</sub> monolayer for photocatalytic water splitting.

Physical chemistry chemical physics : PCCP·2026

Same journal

Stackelberg differential game-based fuzzy adaptive hierarchical optimal control for a nonlinear system with unknown dynamics.

ISA transactions·2026

Same journal

Composite fault-tolerant predictive control strategy for PMSM demagnetization faults.

ISA transactions·2026

Same journal

Bias-compensated Q-learning for optimal tracking control under denial-of-service attacks.

ISA transactions·2026

Same journal

Motion prediction for leader manipulator of teleoperation system with large time delay based on inverse optimal control.

ISA transactions·2026

Same journal

Neural network parameter identification-based prescribed-time adaptive control for morphing glide aircraft.

ISA transactions·2026

Same journal

Nonlinear system-guided continuous-time generalization for cross-aircraft engine state monitoring.

ISA transactions·2026

See all related articles

This summary is machine-generated.

This study introduces an Adapted Oversampling-based Multi-layer Support Vector Machines (AM-SVMs) framework for intelligent fault diagnosis. AM-SVMs effectively handles imbalanced data, improving diagnostic accuracy and robustness in intelligent manufacturing.

Area of Science:

Engineering
Machine Learning
Data Science

Background:

Intelligent fault diagnosis for high-end equipment faces challenges with small-sample, imbalanced, and noisy data.
Existing data augmentation methods often produce low-quality samples and are sensitive to hyperparameters.

Purpose of the Study:

To propose an interpretable fault diagnosis framework, AM-SVMs, that addresses limitations of current methods for imbalanced data.
To enhance the accuracy and robustness of fault diagnosis models in intelligent manufacturing.

Main Methods:

Developed an Adapted Oversampling-based Multi-layer Support Vector Machines (AM-SVMs) framework.
Integrated a Multi-mechanism Adaptive Oversampling Technique (MAOTE) with a multi-layer LSSVM architecture.
Employed a Newton-Raphson-inspired mechanism for adaptive oversampling and classifier-feedback for interpretability.

Keywords:

Adaptive oversampling Fault diagnosis Multi-class imbalanced Multi-layer classifier

Related Experiment Videos

Main Results:

AM-SVMs demonstrated superior performance compared to ten data augmentation and eight multi-class classification methods.
The framework achieved higher diagnostic accuracy and robustness on bearing datasets.
Generated samples showed improved distributional consistency and interpretability with real data.

Conclusions:

The proposed AM-SVMs framework offers an effective solution for imbalanced fault diagnosis in intelligent manufacturing.
The adaptive oversampling and interpretable design contribute to robust and generalizable diagnostic models.