Previous Article in Journal
Adaptive Hydrodynamic Cavitation in a Reconfigurable Circular Venturi: Design Framework and Numerical Demonstration of a Parametric Cavitation-Inception Workflow
 
 
Search for Articles:
Title / Keyword
Author / Affiliation / Email
Journal
Article Type
 
 
Advanced Search
 
Section
Special Issue
Volume
Issue
Number
Page
 
Journals
JMMP
Volume 10
Issue 8
10.3390/jmmp10080286
jmmp-logo
Submit to this Journal Review for this Journal Propose a Special Issue
► Article Menu

Article Menu

share Share announcement Help format_quote Cite question_answer Discuss in SciProfiles
first_page
settings
Order Article Reprints
Font Type:
Arial Georgia Verdana
Font Size:
Aa Aa Aa
Line Spacing:
Column Width:
Background:
This is an early access version, the complete PDF, HTML, and XML versions will be available soon.
Article

MaskLenNet: A Query-Based Instance Segmentation and Length Prediction Network for Quantitative Industrial Tool Wear and Breakage Assessment

by
Yi Pan
1,
Kun He
1,
Chen Yin
2,3,
Yanping Zhang
1,
Yong Luo
1,* and
Yulin Wang
4,*
1
China National Petroleum Corporation Engineering Technology Research and Development Company Limited, Beijing 102200, China
2
Department of Data Science, College of Computing, City University of Hong Kong, Kowloon, Hong Kong
3
City University of Hong Kong Shenzhen Research Institute, Shenzhen 518057, China
4
School of Mechanical Engineering, Nanjing University of Science and Technology, Nanjing 210094, China
*
Authors to whom correspondence should be addressed.
J. Manuf. Mater. Process. 2026, 10(8), 286; https://doi.org/10.3390/jmmp10080286
Submission received: 3 July 2026 / Revised: 4 August 2026 / Accepted: 5 August 2026 / Published: 6 August 2026
(This article belongs to the Topic Artificial Intelligence in Smart Industrial Diagnostics and Manufacturing—Third Edition)
Versions Notes

Abstract

Tool wear detection is essential for machining quality control and predictive maintenance, but conventional inspection is often manual, time-consuming, and operator-dependent. Existing learning-based visual methods still face challenges in jointly achieving reliable wear-type recognition, accurate wear-region localization, and quantitative wear-width measurement under shop-floor imaging conditions. To address these issues, this study proposes MaskLenNet, a query-based instance segmentation and length prediction network for solid carbide end-milling tool diagnosis. MaskLenNet combines a Swin Transformer backbone, query-based instance-mask prediction, wear-oriented attention, and a key-point head that directly estimates the maximum wear-land width (VB). Evaluation uses 234 images from 54 physical tools under a tool-disjoint split, so different rotations of one tool cannot occur in both training and evaluation sets. On the held-out test set, MaskLenNet achieves 96.52% matched-instance classification accuracy, 95.75% foreground instance mIoU, and a VB mean absolute error of 0.010214 mm. Relative to BEiT-Base, the gains are 3.04 and 3.60 percentage points in accuracy and mIoU, respectively. These results demonstrate promising performance within the evaluated acquisition system; they do not establish equivalence to microscopy or generalization to other machines, optics, workpiece materials, or sites.
Keywords: tool wear detection; multi-task learning; quantitative wear measurement; channel and spatial attention; predictive maintenance tool wear detection; multi-task learning; quantitative wear measurement; channel and spatial attention; predictive maintenance

Share and Cite

MDPI and ACS Style

Pan, Y.; He, K.; Yin, C.; Zhang, Y.; Luo, Y.; Wang, Y. MaskLenNet: A Query-Based Instance Segmentation and Length Prediction Network for Quantitative Industrial Tool Wear and Breakage Assessment. J. Manuf. Mater. Process. 2026, 10, 286. https://doi.org/10.3390/jmmp10080286

AMA Style

Pan Y, He K, Yin C, Zhang Y, Luo Y, Wang Y. MaskLenNet: A Query-Based Instance Segmentation and Length Prediction Network for Quantitative Industrial Tool Wear and Breakage Assessment. Journal of Manufacturing and Materials Processing. 2026; 10(8):286. https://doi.org/10.3390/jmmp10080286

Chicago/Turabian Style

Pan, Yi, Kun He, Chen Yin, Yanping Zhang, Yong Luo, and Yulin Wang. 2026. "MaskLenNet: A Query-Based Instance Segmentation and Length Prediction Network for Quantitative Industrial Tool Wear and Breakage Assessment" Journal of Manufacturing and Materials Processing 10, no. 8: 286. https://doi.org/10.3390/jmmp10080286

APA Style

Pan, Y., He, K., Yin, C., Zhang, Y., Luo, Y., & Wang, Y. (2026). MaskLenNet: A Query-Based Instance Segmentation and Length Prediction Network for Quantitative Industrial Tool Wear and Breakage Assessment. Journal of Manufacturing and Materials Processing, 10(8), 286. https://doi.org/10.3390/jmmp10080286

Article Metrics

Back to TopTop