Signal feature extraction is the initial stage of original data processing in tool damage monitoring. The quality of the extracted feature values will have a significant impact on the recognition accuracy. In this paper, aiming at the shortcomings of insufficient and inaccurate feature extraction of traditional feature extraction methods, a staged feature extraction method based on sawing vibration noise characteristics is proposed. According to the sawing vibration noise characteristics, the whole sawing process is divided into six sawing stages, and the feature values of each sawing stage and the entire signal stage are extracted. A sensitive feature screening method based on feature value change rate is proposed to screen out more sensitive feature values to circular saw blade damage. Finally, establish a circular saw blade damage classification recognition model based on CNN and conduct training and testing. The test results show that compared with the traditional feature extraction method, the accuracy of model recognition is significantly improved after using the feature extraction and screening method proposed in this paper. The results prove the superiority of the feature extraction and screening methods proposed in this paper in improving the accuracy of model recognition.
ChenYShiJHuJ, et al. (2025) Simulation data driven time–frequency fusion 1D convolutional neural network with multiscale attention for bearing fault diagnosis. Measurement Science and Technology36(3): 035109. https://doi.org/10.1088/1361-6501/adb329. IOP Publishing.
2.
ChengYGaiXGuanR, et al. (2023) Tool wear intelligent monitoring techniques in cutting: a review. Journal of Mechanical Science and Technology37(1): 289–303. https://doi.org/10.1007/s12206-022-1229-9
3.
FengSWangZJiangW, et al. (2023) A time-series driven mechanical system state description method and its application in condition monitoring. IEEE Sensors Journal23(9): 9677–9684. https://doi.org/10.1109/jsen.2023.3260921
4.
GülÖKorkmazM (2025) Measurement and optimization of wood dust and noise levels in table saw operations using response surface methodology. Bioresources20(4): 884–900. North Carolina State University.
5.
GuoMTuXAbbasS, et al. (2024) Time-frequency analysis-based impulse feature extraction method for quantitative evaluation of milling tool wear. Structural Health Monitoring23(3): 1766–1778. https://doi.org/10.1177/14759217231192003
6.
HanGPengYChenX, et al. (2025) A method for vibration analysis of machine tools under variable cutting excitation based on modal participation ratio. Journal of Vibration Engineering & Technologies13(5): 269. https://doi.org/10.1007/s42417-025-01818-5
JiaNGuoLZhangY, et al. (2025) Multi-physical field coupling simulation and experimental study on the radiation characteristics of sawing noise from circular saw blades in woodworking. Forests16(3): 442–464. https://doi.org/10.3390/f16030442. MDPI AG.
9.
LiXLiuXYueC, et al. (2022) Systematic review on tool breakage monitoring techniques in machining operations. International Journal of Machine Tools and Manufacture176: 103882. https://doi.org/10.1016/j.ijmachtools.2022.103882
10.
LiuM-KTsengY-HTranM-Q (2019) Tool wear monitoring and prediction based on sound signal. The International Journal of Advanced Manufacturing Technology103(9–12): 3361–3373. https://doi.org/10.1007/s00170-019-03686-2
11.
LopesWNJuniorPOCAguiarPR, et al. (2021) An efficient short-time fourier transform algorithm for grinding wheel condition monitoring through acoustic emission. The International Journal of Advanced Manufacturing Technology113(1–2): 585–603. https://doi.org/10.1007/s00170-020-06476-3
12.
MihaiISergiuRBogdanB, et al. (2025) Integration of ANN and RSM to optimize the sawing process of wood by circular saw blades. Applied Sciences15(18): 10206–10227. MDPI AG.
13.
Miric-MilosavljevicMSvrzicSNikolićZ, et al. (2024) Signal processing and machine learning as a tool for identifying idling noises of different circular saw blades. Bioresources19(1): 1744–1756. https://doi.org/10.15376/biores.19.1.1744-1756. North Carolina State University.
14.
MohanrajTTamilvananA (2022) Decision support system for tool condition monitoring in milling process using artificial neural network. Journal of Engineering Research10(4): 142–155. https://doi.org/10.36909/jer.9621
15.
WangLLiXShiB, et al. (2022) Analysis and selection of eigenvalues of vibration signals in cutting tool milling. Advances in Mechanical Engineering14(1): 16878140221075197. https://doi.org/10.1177/16878140221075197
16.
WangCWangXZengC (2023) Saw blade wear identification based on data enhancement and feature fusion. IEEE Access11: 123677–123687. https://doi.org/10.1109/access.2023.3329830
17.
WangHWangYNiP, et al. (2025) Defect measurement method of circular saw blade based on machine vision. The International Journal of Advanced Manufacturing Technology137(3–4): 2091–2107. https://doi.org/10.1007/s00170-025-15226-2
18.
YangJYuXHuC, et al. (2025) Hybrid global and local neural network with lightweight multiscale fusion for tool wear prediction. IEEE Transactions on Instrumentation and Measurement74: 1–15. https://doi.org/10.1109/tim.2025.3579834
19.
YedurkarDPSchlechTSauseMGR (2025) A systematic review on smart and predictive maintenance in tool condition monitoring. IEEE Access13: 106246–106286. https://doi.org/10.1109/access.2025.3579204
20.
YingSSunYFuC, et al. (2022) Grey wolf optimization based support vector machine model for tool wear recognition in fir-tree slot broaching of aircraft turbine discs. Journal of Mechanical Science and Technology36(12): 6261–6273. https://doi.org/10.1007/s12206-022-1139-x
21.
ZhangXGaoYGuoZ, et al. (2023) Physical model-based tool wear and breakage monitoring in milling process. Mechanical Systems and Signal Processing184: 109641. https://doi.org/10.1016/j.ymssp.2022.109641
22.
ZhangCWangJCaoY, et al. (2024) Tool wear status monitoring under laser-ultrasonic compound cutting based on acoustic emission and deep learning. Journal of Mechanical Science and Technology38(5): 2411–2421. https://doi.org/10.1007/s12206-024-0419-z
23.
ZhouCGuoKSunJ (2021) Sound singularity analysis for milling tool condition monitoring towards sustainable manufacturing. Mechanical Systems and Signal Processing157: 107738. https://doi.org/10.1016/j.ymssp.2021.107738
