To improve the accuracy of tool wear monitoring in machining, this paper proposes a method based on multi-sensor signal feature fusion and deep neural networks. The proposed method synchronously acquires multi-sensor signals, from which multi-domain features are first extracted. These features are then selected based on the Max-Relevance Min-Redundancy (mRMR) criterion and subsequently fused through weighted averaging to form a fused feature vector. Subsequently, this vector is transformed into an image dataset using the Recurrence Plot (RP) method. On this basis, a Multi-level Convolutional Gated Network model integrated with the Sparrow Search Algorithm (SSA-MLCGN) is designed for tool wear prediction. This model integrates convolutional layers with a Gated Recurrent Unit (GRU), utilizing the convolutional layers to extract features from the recurrence images while employing Dropout to mitigate overfitting. Concurrently, the Sparrow Search Algorithm (SSA) is introduced to optimize the hyperparameters of the GRU, thereby significantly enhancing the model’s prediction accuracy and generalization performance. Finally, ablation studies, single/multi-condition experiments, and noise robustness experiments were conducted on a public dataset, validating the high precision, strong generalization, and industrial applicability of the proposed method.
JavedKGouriveauRLiX, et al. Tool wear monitoring and prognostics challenges: a comparison of connectionist methods toward an adaptive ensemble model. J Intell Manuf2018; 29: 1873–1890.
2.
KuntoğluMSağlamH.Investigation of progressive tool wear for determining of optimized machining parameters in turning. Measurement2019; 140: 427–436.
3.
WangCBaoZZhangP, et al. Tool wear evaluation under minimum quantity lubrication by clustering energy of acoustic emission burst signals. Measurement2019; 138: 256–265.
4.
YangYGuoYHuangZ, et al. Research on the milling tool wear and life prediction by establishing an integrated predictive model. Measurement2019; 145: 178–189.
5.
AbdeltawabAXiZLongjiaZ.Dual-method approach of tool condition monitoring using sensor-based deep learning with vision-based image processing. J Manuf Process2025; 150: 224–256.
6.
LiuQJiangJXiuW, et al. Research progress on precision tool alignment technology in machining. Micromachines2024; 15(10): 1202.
7.
JonesTCaoY.Tool wear prediction based on multisensor data fusion and machine learning. Int J Adv Manuf Technol2025; 137: 5213–5225.
8.
HuangZShaoJGuoW, et al. Tool wear prediction based on multi-information fusion and genetic algorithm-optimized Gaussian process regression in milling. IEEE Trans Instrum Meas2023; 72: 1–16.
9.
MaiaLHAAbrãoAMVasconcelosWL, et al. Enhancing machining efficiency: real-time monitoring of tool wear with acoustic emission and STFT techniques. Lubricants2024; 12(11): 380.
10.
MamedovADincAGulerMA, et al. Tool wear in micromilling: a review. Int J Adv Manuf Technol2025; 137: 47–65.
11.
CaoDLiuWGeJ, et al. Research progress on intelligent monitoring of tool condition based on deep learning. Int J Adv Manuf Technol2024; 134(5–6): 2129–2150.
12.
ZhouYZhiGChenW, et al. A new tool wear condition monitoring method based on deep learning under small samples. Measurement2022; 189: 110622.
13.
TuršičNKlančnikS.Tool condition monitoring using machine tool spindle current and long short-term memory neural network model analysis. Sensors2024; 24(8): 2490.
14.
ZhengYChenBLiuB, et al. Milling cutter wear state identification method based on improved ResNet-34 algorithm. Appl Sci2024; 14(19): 8951.
15.
GuoBZhangQPengQ, et al. Tool health monitoring and prediction via attention-based encoder-decoder with a multi-step mechanism. Int J Adv Manuf Technol2022; 122(2): 685–695.
16.
QinBWangYLiuK, et al. A novel online tool condition monitoring method for milling titanium alloy with consideration of tool wear law. Mech Syst Signal Process2023; 199: 110467.
17.
DongLWangCYangG, et al. An improved ResNet-1d with channel attention for tool wear monitor in smart manufacturing. Sensors2023; 23(3): 1240.
18.
WangSGuangBWangZ, et al. Faulty bearing diagnostic model based on multi-dimensional signal and multi-analysis domain. Electrical Engineering2025; 107(3): 2663–2675.
19.
XiaoZLiDYangC, et al. Fault diagnosis method of special vehicle bearing based on multi-scale feature fusion and transfer adversarial learning. Sensors2024; 24(16): 5181.
20.
WuXZhangCLiY, et al. Researches on tool wear progress in mill-grinding based on the cutting force and acceleration signal. Measurement2023; 218: 113234.
21.
GongZHuoD.Tool condition monitoring in micro milling of brittle materials. Precis Eng2024; 87: 11–22.
22.
WangKWangAWuL, et al. Machine tool wear prediction technology based on multi-sensor information fusion. Sensors2024; 24(8): 2652.
23.
EckmannJ-POliffson KamphorstSRuelleD.Recurrence plots of dynamical systems. Turbulence, Strange Attractors and Chaos, 1995. pp.441–445.
24.
CaoL.Practical method for determining the minimum embedding dimension of a scalar time series. Physica D1997; 110(1-2): 43–50.
25.
FraserAMSwinneyHL.Independent coordinates for strange attractors from mutual information. Phys Rev A1986; 33(2): 1134–1140.
26.
Calderon-UribeULizarraga-MoralesRAGuryevIV.Fault diagnosis in induction motors through infrared thermal images using convolutional neural network feature extraction. Machines2024; 12(8): 497.
27.
HeXJinJJiangY, et al. A lightweight convolutional neural network-based feature extractor for visible images. Comput Vis Image Underst2024; 249: 104157.
28.
LiWFuHHanZ, et al. Intelligent tool wear prediction based on informer encoder and stacked bidirectional gated recurrent unit. Robot Comput Manuf2022; 77: 102368.
29.
LiZXiaoXZhouW, et al. Identification of tool wear status using multi-sensor signals and improved gated recurrent unit. Int J Adv Manuf Technol2025; 137(3–4): 1249–1260.
YueYCaoLLuD, et al. Review and empirical analysis of sparrow search algorithm. Artif Intell Rev2023; 56(10): 10867–10919.
32.
ZhangPLiZZouL, et al. Optimization of grinding process parameters based on BILSTM network and chaos sparrow search algorithm. Proc Inst Mech Eng E J Process Mech Eng2022; 236(4): 1693–1701.
33.
XieWWangJXingC, et al. Variational autoencoder bidirectional long and short-term memory neural network soft-sensor model based on batch training strategy. IEEE Trans Ind Inform2021; 17(8): 5325–5334.
34.
HintonGESrivastavaNKrizhevskyA, et al. Improving neural networks by preventing co-adaptation of feature detectors. arXiv preprint, arXiv:1207.0580, 2012.
HouKLiRLiuX, et al. Swin-fusion: an adaptive multi-source information fusion framework for enhanced tool wear monitoring. J Manuf Syst2025; 79: 435–454.
37.
FuHLiZXiaoX, et al. Multi-source domain generalization tool wear prediction based on wide convolution weighted antagonism. Meas Sci Technol2025; 36(1): 016183.
38.
NieLZhangLXuS, et al. Remaining useful life prediction of milling cutters based on CNN-Bilstm and attention mechanism. Symmetry2022; 14(11): 2243.
39.
ChenYZhengX.Fault diagnosis of wind turbine based on multi-signal CNN-GRU model. Proc Inst Mech Eng J Power Energy2023; 237(5): 1113–1124.
40.
ZhangXLuXLiW, et al. Prediction of the remaining useful life of cutting tool using the Hurst exponent and CNN-LSTM. Int J Adv Manuf Technol2021; 112(7–8): 2277–2299.
41.
ShahMBoradeHDaveV, et al. Utilizing TGAN and ConSinGAN for improved tool wear prediction: a comparative study with ED-LSTM, GRU, and CNN models. Electronics2024; 13(17): 3484.
42.
ShahMVakhariaVChaudhariR, et al. Tool wear prediction in face milling of stainless steel using singular generative adversarial network and LSTM deep learning models. Int J Adv Manuf Technol2022; 121(1–2): 723–736.
