Cutting tools play a vital role in CNC machining processes. Effective tool wear prediction is essential for lowering machining costs and boosting productivity. The current mainstream research is to mine the spatiotemporal correlation between sensor data and tool wear degree using deep learning combinatorial models of CNN and RNN. However, most of the combined models tend to ignore the problem of feature interference when mining spatial and temporal features, leading to a decrease in prediction accuracy. To address the above issues, three sets of complete life cycle milling experiments were conducted on 40Cr quenched and tempered steel to collect three-axis cutting force signals fed into the parallel model for prediction. The experimental results show that the mean absolute error (MAE), root mean square error (RMSE), and coefficient of determination (R2) of this method, which reaches 4.668, 5.979, and 0.935 in the average of three test sets, respectively, are better than the comparison model. Finally, the transferability of the proposed model under different working conditions is verified on a public dataset using a transfer learning method.
ChengMJiaoLYanP, et al. Intelligent tool wear monitoring and multi-step prediction based on deep learning model. J Manuf Syst2022; 62: 286–300.
2.
AydınMKarakuzuCUçarM, et al. Prediction of surface roughness and cutting zone temperature in dry turning processes of AISI304 stainless steel using ANFIS with PSO learning. Int J Adv Manuf Technol2013; 67: 957–967.
3.
XueJChengYZhaiW, et al. Research on multi-step ahead prediction method for tool wear based on MSTCN-SBiGRU-MHA. Adv Eng Inform2025; 65: 103219.
4.
AydinM.Prediction of cutting speed interval of diamond-coated tools with residual stress. Mater Manuf Process2017; 32(2): 145–150.
5.
ZhouLWangH.Multi-task model of adaptive multi-scale feature fusion and adaptive mixture-of-experts for equipment remaining useful life prediction and fault diagnosis. Expert Syst Appl2025; 272: 126807.
6.
AdisheshaPLawrenceK DMathewJ.The multi-sensor-based measurement of machining signals and data fusion to develop predictive tool wear models for TiAlN-PVD coated carbide inserts during end milling of Inconel 617. Proc IMechE, Part B: J Engineering Manufacture2024; 238(6-7): 886–903.
7.
StavropoulosPPapacharalampopoulosAVasiliadisE, et al. Tool wear predictability estimation in milling based on multi-sensorial data. Int J Adv Manuf Technol2016; 82: 509–521.
8.
StavropoulosPPapacharalampopoulosASouflasT.Indirect online tool wear monitoring and model-based identification of process-related signal. Adv Mech Eng2020; 12(5): 1687814020919209.
9.
SunJWangDLiuZ, et al. Tool digital twin based on knowledge embedding for precision CNC machine tools: wear prediction for collaborative multi-tool. J Manuf Syst2025; 80: 157–175.
10.
YangCShiYXinH, et al. Tool wear prediction model based on wear influence factor. Int J Adv Manuf Technol2023; 129(3-4): 1829–1844.
11.
ChengYGaiXJinY, et al. A new method based on a WOA-optimized support vector machine to predict the tool wear. Int J Adv Manuf Technol2022; 121(9-10): 6439–6452.
12.
PapacharalampopoulosAAlexopoulosKCattiP, et al. Learning more with less data in manufacturing: the case of turning tool wear assessment through active and transfer learning. Processes2024; 12(6): 1262.
13.
WeiWCongRLiY, et al. Prediction of tool wear based on GA-BP neural network. Proc IMechE, Part B: J Engineering Manufacture2022; 236(12): 1564–1573.
14.
ShiJZhangYSunY, et al. Tool life prediction of dicing saw based on PSO-BP neural network. Int J Adv Manuf Technol2022; 123(11): 4399–4412.
15.
Tchoketch-KebirSDraiR.Predicting the remaining useful life of a tool material using acoustic emission signals. Int J Adv Manuf Technol2025; 136: 4877–4895.
16.
ChenSYinZZhengL, et al. Study of an ISSA-XGBoost model for milling tool wear prediction under variable working conditions. Int J Adv Manuf Technol2024; 133: 2761–2774.
17.
LiWZhangXWangS, et al. Distributed deep learning enabled prediction on cutting tool wear and remaining useful life. Proc IMechE, Part B: J Engineering Manufacture2023; 237(14): 2203–2213.
18.
HuangQWuDHuangH, et al. Tool wear prediction based on a multi-scale convolutional neural network with attention fusion. Information2022; 13(10): 504.
19.
ManwarAVargheseABagriS, et al. Online tool condition monitoring in micromilling using LSTM. J Intell Manuf2025; 36: 935–955.
20.
QinBWangYLiuK, et al. A tool wear monitoring approach based on triplet long short-term memory neural networks. Proc IMechE, Part B: J Engineering Manufacture2024; 238(11): 1610–1619.
21.
BabuMSRaoTB.Development of an in-process cutting tool life prediction system using bidirectional long short-term memory network. J Fail Anal Prev2023; 23(2): 837–845.
22.
CheZPengCLiaoTW, et al. Improving milling tool wear prediction through a hybrid NCA-SMA-GRU deep learning model. Expert Syst Appl2024; 255: 124556.
23.
LiXQinXWuJ, et al. Tool wear prediction based on convolutional bidirectional LSTM model with improved particle swarm optimization. Int J Adv Manuf Technol2022; 123(11-12): 4025–4039.
24.
WuSLiYLiW, et al. Tool remaining useful life prediction considering wear state based on hybrid attention network. Proc IMechE, Part B: J Engineering Manufacture2024; 238(6-7): 837–850.
25.
LiBLiJWuX, et al. Gated recurrent unit and temporal convolutional network with soft thresholding and attention mechanism for tool wear prediction. Measurement2025; 240: 115546.
26.
ChengYZhouSLuM, et al. Tool wear prediction method based on dual-attention mechanism network. Int J Comput Integr Manuf2024; 37: 1–16.
27.
GeYTeoHHMoeyLK.Monitoring tool wearing: a hybrid algorithm integrating residual structures and stacked Bilstm. Int J Adv Manuf Technol2024; 132(7): 3237–3250.
28.
QinYLiJZhangC, et al. A dual-stage attention model for tool wear prediction in dry milling operation. Entropy2022; 24(12): 1733.
29.
DuanJZhangXShiT.A hybrid attention-based paralleled deep learning model for tool wear prediction. Expert Syst Appl2023; 211: 118548.
30.
YangJWuJLiX, et al. Tool wear prediction based on parallel dual-channel adaptive feature fusion. Int J Adv Manuf Technol2023; 128(1-2): 145–165.
31.
LiBLuZJinX, et al. Tool wear prediction in milling CFRP with different fiber orientations based on multi-channel 1DCNN-LSTM. J Intell Manuf2024; 35(6): 2547–2566.
32.
LiuXLiuSLiX, et al. Intelligent tool wear monitoring based on parallel residual and stacked bidirectional long short-term memory network. J Manuf Syst2021; 60: 608–619.
33.
GuanRChengYJinY, et al. Research on tool wear prediction for milling high strength steel based on DenseNet-ResNet-GRU. J Mech Sci Technol2024; 38(7): 3585–3596.
34.
HeKZhangXRenS, et al. Deep residual learning for image recognition. In: Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition,2016, pp.770–778. Las Vegas, NV: Institute of Electrical and Electronics Engineers.
ZPanMZhouHCaoJ, et al. Water level prediction model based on GRU and CNN. IEEE Access2020; 8: 60090–60100.
37.
DuanYLiuYWangY, et al. (2023). Improved BIGRU model and its application in stock price forecasting. Electronics2023; 12(12): 2718.
38.
HuJShenLSunG.Squeeze-and-excitation networks. In: Proceedings of the IEEE conference on computer vision and pattern recognition, 2018, pp.7132–7141. Salt Lake City, UT: Institute of Electrical and Electronics Engineers.
39.
WangQWuBZhuP, et al. ECA-Net: Efficient channel attention for deep convolutional neural networks. In: Proceedings of the IEEE/CVF conference on computer vision and pattern recognition, 2020, pp.11534–11542. Seattle, WA: Institute of Electrical and Electronics Engineers.
