Have a personal or library account? Click to login
Research on Tool Wear State Recognition Method Based on Multi-Scale Feature Extraction and Deep Residual Network Fusion Cover

Research on Tool Wear State Recognition Method Based on Multi-Scale Feature Extraction and Deep Residual Network Fusion

Open Access
|Jan 2026

Figures & Tables

Fig. 1.

Tool wear curve.
Tool wear curve.

Fig. 2.

Experimental and signal acquisition equipment. (a) Experimental machine tool and cutting test site; (b) Super depth-of-field microscope, vibration signal acquisition equipment, and test tool.
Experimental and signal acquisition equipment. (a) Experimental machine tool and cutting test site; (b) Super depth-of-field microscope, vibration signal acquisition equipment, and test tool.

Fig. 3.

Data collection and preprocessing.
Data collection and preprocessing.

Fig. 4.

The vibration signals and their CWT at different stages of tool wear.
The vibration signals and their CWT at different stages of tool wear.

Fig. 5.

Basic block in ResNet network.
Basic block in ResNet network.

Fig. 6.

Overall framework of the proposed methodology.
Overall framework of the proposed methodology.

Fig. 7.

Overview of a Multi-scale ResNet-based model for tool wear condition recognition.
Overview of a Multi-scale ResNet-based model for tool wear condition recognition.

Fig. 8.

Confusion matrix (a) CNN–SVM; (b) Transformer; (c) ResNet; (d) Multi-scale ResNet.
Confusion matrix (a) CNN–SVM; (b) Transformer; (c) ResNet; (d) Multi-scale ResNet.

Fig. 9.

Recognition results of the four models.
Recognition results of the four models.

Tool wear status classification_

Tool wear [mm]Tool wear statusTime [min]
[0, 0.0675)Initial wear[0, 9)
[0.0675, 0.245)Normal wear[9, 23.5)
[0.245, +∞)Severe wear[23.5, 29]

Comparison of experimental results with other models_

Models Accuracy [%]Recall [%]Precision [%]F1 score [%]
CNN–SVM[5]Initial wear--90.983.387.0
Normal wear--86.893.990.2
Severe wear--100.095.597.7
Average90.692.690.991.6
Transformer[6]Initial wear--78.876.477.6
Normal wear--84.986.585.7
Severe wear--100.0100.0100.0
Average86.087.987.787.8
ResNetInitial wear--78.883.881.3
Normal wear--90.687.388.9
Severe wear--100.0100.0100.0
Average88.889.890.490.0
Multi-scale ResNetInitial wear--90.087.188.5
Normal wear--92.494.293.3
Severe wear--100.0100.0100.0
Average93.394.293.894.0
Language: English
Page range: 14 - 23
Submitted on: May 19, 2025
|
Accepted on: Nov 12, 2025
|
Published on: Jan 5, 2026
In partnership with: Paradigm Publishing Services
Publication frequency: Volume open

© 2026 Erliang Liu, Cong Liu, Yuhang Du, Baiwei Zhu, Limin Shi, published by Slovak Academy of Sciences, Institute of Measurement Science
This work is licensed under the Creative Commons Attribution-NonCommercial-NoDerivatives 4.0 License.