Gear Target Detection and Fault Diagnosis System Based on Hierarchical Annotation Training

Huang, Haojie; Liang, Qixin; Wu, Rui; Yang, Dan; Wang, Jiaorao; Zheng, Rong; Xu, Zhezhuang

doi:10.3390/machines13100893

This is an early access version, the complete PDF, HTML, and XML versions will be available soon.

Open AccessArticle

Gear Target Detection and Fault Diagnosis System Based on Hierarchical Annotation Training

by

Haojie Huang

^1,2,*,

Qixin Liang

¹

,

Rui Wu

¹,

Dan Yang

³,

Jiaorao Wang

⁴,

Rong Zheng

⁵ and

Zhezhuang Xu

^1,2

¹

College of Electrical Engineering and Automation, Fuzhou University, Fuzhou 350000, China

²

The Key Laboratory of Industrial Automation Control Technology and Information Processing, Education Department of Fujian Province, Fuzhou 350000, China

³

School of Information and Electrical Engineering, Hunan University of Science and Technology, Xiangtan 411201, China

⁴

Division of Industrial Data Science, School of Data Science, Lingnan University, Hong Kong, China

⁵

IAP (Fujian) Technology Co., Ltd., Fuzhou 350116, China

^*

Author to whom correspondence should be addressed.

Machines 2025, 13(10), 893; https://doi.org/10.3390/machines13100893

Submission received: 1 September 2025 / Revised: 27 September 2025 / Accepted: 28 September 2025 / Published: 30 September 2025

(This article belongs to the Section Machines Testing and Maintenance)

Download Versions Notes

Abstract

Gears are the core components of transmission systems, and their health status is critical to the safety and stability of the entire system. In order to efficiently identify the typical fault types such as missing teeth and broken teeth in gears, this paper collects a rich sample under complex backgrounds from different shooting angles and lighting conditions. Then a hierarchical approach is used to describe gear faults on the image. The gear samples are first segmented for image extraction and then finely labeled for gear fault regions. In addition, imbalanced datasets are produced to simulate the environment with fewer fault samples in the actual industrial process. Finally, a semi-supervised learning framework is trained based on the above method and applied in actual environment. The experimental results show that the model performs well in gear target detection and fault diagnosis, demonstrating the effectiveness of the proposed method.

Keywords: target detection; fault diagnosis; convolutional neural networks; hierarchical annotation; semi-supervised learning

Share and Cite

MDPI and ACS Style

Huang, H.; Liang, Q.; Wu, R.; Yang, D.; Wang, J.; Zheng, R.; Xu, Z. Gear Target Detection and Fault Diagnosis System Based on Hierarchical Annotation Training. Machines 2025, 13, 893. https://doi.org/10.3390/machines13100893

AMA Style

Huang H, Liang Q, Wu R, Yang D, Wang J, Zheng R, Xu Z. Gear Target Detection and Fault Diagnosis System Based on Hierarchical Annotation Training. Machines. 2025; 13(10):893. https://doi.org/10.3390/machines13100893

Chicago/Turabian Style

Huang, Haojie, Qixin Liang, Rui Wu, Dan Yang, Jiaorao Wang, Rong Zheng, and Zhezhuang Xu. 2025. "Gear Target Detection and Fault Diagnosis System Based on Hierarchical Annotation Training" Machines 13, no. 10: 893. https://doi.org/10.3390/machines13100893

APA Style

Huang, H., Liang, Q., Wu, R., Yang, D., Wang, J., Zheng, R., & Xu, Z. (2025). Gear Target Detection and Fault Diagnosis System Based on Hierarchical Annotation Training. Machines, 13(10), 893. https://doi.org/10.3390/machines13100893

Note that from the first issue of 2016, this journal uses article numbers instead of page numbers. See further details here.

Article Menu

Gear Target Detection and Fault Diagnosis System Based on Hierarchical Annotation Training

Abstract

Share and Cite

Article Metrics

Article Access Statistics

Further Information

Guidelines

MDPI Initiatives

Follow MDPI