Micro-milling is employed for the precise machining of small components with intricate characteristics, and the quality of micro-milling is significantly influenced by the uncertainty surrounding tool wear. Monitoring the wear status of micro-milling tools holds great significance in enhancing machining efficiency and sustainability. In this work, wear monitoring of micro-milling tools method was proposed based on Improved Siamese Neural Network. The Improved Siamese Neural Network used two different global feature extraction networks. The features were input into the t improved Siamese neural network model for similarity score calculation and anomaly detection, which improves the detection accuracy of the abnormal state of micro-milling tool wear. In addition, Generative Adversarial Network (GAN) data augmentation is used to address the issue of abnormal data imbalance during the data preparation stage. The experiments show that the classification accuracy and the precision of the model on the micro-milling tool wear dataset is 92.15% and 93.32% respectively, indicating that the model has good stability and effectiveness.
BhatNNDuttaSPalSK, et al. Tool condition classification in turning process using hidden Markov model based on texture analysis of machined surface images. Measurement2016; 90: 500–509.
2.
LiWLiuT. Time varying and condition adaptive hidden Markov model for tool wear state estimation and remaining useful life prediction in micro-milling. Mech Syst Signal Process2019; 131: 689–702.
3.
YuJLiangSTangD, et al. A weighted hidden Markov model approach for continuous-state tool wear monitoring and tool life prediction. Int J Adv Manuf Technol2017; 91: 201–211.
4.
LiNGebraeelNLeiY, et al. Remaining useful life prediction based on a multi-sensor data fusion model. Reliab Eng Syst Saf2021; 208: 107249. DOI: 10.1016/j.ress.2020.
5.
SunHPanJZhangJ, et al. Non-linear Wiener process–based cutting tool remaining useful life prediction considering measurement variability. Int J Adv Manuf Technol2020; 107: 4493–4502.
6.
ElangovanMRamachandranKISugumaranV. Studies on Bayes classifier for condition monitoring of single point carbide tipped tool based on statistical and histogram features. Expert Syst Appl2010; 37: 2059–2065.
7.
MosallamAMedjaherKZerhouniN. Data-driven prognostic method based on Bayesian approaches for direct remaining useful life prediction. J Intell Manuf2016; 27: 1037–1048.
8.
Tobon-MejiaDAMedjaherKZerhouniN. CNC machine tool's wear diagnostic and prognostic by using dynamic Bayesian networks. Mech Syst Signal Process2012; 28: 167–182.
9.
ChenDLiZHeZ. Research on fault detection of Tennessee Eastman process based on PCA. In: 2013 25th Chinese control and decision conference (CCDC), 25–27 May 2013, pp.1078–1081. New York: IEEE.
10.
GaoQJiaZ. An application study of the improved PCA method in the TE process fault detection. In: 2010 IEEE international conference on intelligent computing and intelligent systems, 29–31 October 2010, pp.706–709. New York: IEEE.
11.
JinQKhursheedS. A wavelet theory about online wavelets denoising based on Moving Window and Principal Component Analysis (PCA). In: 2013 International conference on wavelet analysis and pattern recognition, 14–17 July 2013, pp.56–61. New York: IEEE.
12.
XiaoqiangZXinmingWWuY. An improved FVS-KPCA method of fault detection on TE process. In: 2012 Third international conference on digital manufacturing & automation, 31 July–2 August 2012, pp.186–189. New York: IEEE.
13.
YangYYaweiZQingY, et al. The study of TE process based on the improved PCA method. In: 2008 3rd IEEE conference on industrial electronics and applications, 3–5 June 2008, pp.1215–1217. New York: IEEE.
14.
LiLQiYLiY, et al. Fault monitoring of TE based on improved multiscale principal component analysis. In: Proceeding of the 11th world congress on intelligent control and automation, 29 June–4 July 2014, pp.4504–4509. New York: IEEE.
15.
KongDChenYLiN, et al. Tool wear monitoring based on kernel principal component analysis and v-support vector regression. Int J Adv Manuf Technol2017; 89: 175–190.
16.
MadhusudanaCKKumarHNarendranathS. Fault diagnosis of face milling tool using decision tree and sound signal. Mater Today Proc2018; 5: 12035–12044.
17.
QuDZhengWWangB, et al. Nondestructive acquisition of the micro-mechanical properties of high-speed-dry milled micro-thin walled structures based on surface traits. Chin J Aeronaut2021; 34: 438–451.
18.
RavikumarSRamachandranKI. Tool wear monitoring of multipoint cutting tool using sound signal features signals with machine learning techniques. Mater Today Proc2018; 5: 25720–25729.
19.
WangGFYangYWZhangYC, et al. Vibration sensor based tool condition monitoring using ν support vector machine and locality preserving projection. Sens Actuators A Phys2014; 209: 24–32.
20.
LuCWangZZhouB. Intelligent fault diagnosis of rolling bearing using hierarchical convolutional network based health state classification. Adv Eng Inform2017; 32: 139–151.
21.
JanssensOSlavkovikjVVervischB, et al. Convolutional neural network based fault detection for rotating machinery. J Sound Vib2016; 377: 331–345.
22.
TangQYangMYangY. ST-LSTM: A deep learning approach combined spatio-temporal features for short-term forecast in rail transit. J Adv Transport2019; 2019: 1–8.
23.
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.
24.
KarimFMajumdarSDarabiH, et al. LSTM fully convolutional networks for time series classification. IEEE Access2018; 6: 1662–1669.
25.
XuPDuRZhangZ. Predicting pipeline leakage in petrochemical system through GAN and LSTM. Knowl Based Syst2019; 175: 50–61.
26.
GomesMCBritoLCBaccidaSilvaM, et al. Tool wear monitoring in micromilling using support vector machine with vibration and sound sensors. Precis Eng2021; 67: 137–151.
27.
ZhangXYuTXuP, et al. In-process stochastic tool wear identification and its application to the improved cutting force modeling of micro milling. Mech Syst Signal Process2022; 164: 108233.
28.
HaiboHYangBGarciaEA, et al. ADASYN: adaptive synthetic sampling approach for imbalanced learning. In: 2008 IEEE International joint conference on neural networks (IEEE World Congress on Computational Intelligence), 1–8 June 2008, pp.1322–1328. New York: IEEE.
29.
GulrajaniIAhmedFArjovskyM, et al. Improved training of wasserstein gans. Curran Associates Inc.Proceedings of the 31st International Conference on Neural Information Processing Systems. Long Beach, CA, 2017, pp. 5769–5779.
30.
ArjovskyMChintalaSBottouL. Wasserstein generative adversarial networks. In: International conference on machine learning, 2017, pp.214–223. PMLR.
31.
ZhangJZengYStarlyB. Recurrent neural networks with long term temporal dependencies in machine tool wear diagnosis and prognosis. Appl Sci2021; 3: 1–13.
32.
DuanJDuanJZhouH, et al. Multi-frequency-band deep CNN model for tool wear prediction. Meas Sci Technol2021; 32: 065009.
33.
LuoHZhangZLuoM, et al. A comparative study of force models in monitoring the flank wear using the cutting force coefficients. Proc IMechE, Part C: J Mechanical Engineering Science2022. 0(0). doi:10.1177/09544062221111706
34.
LiuHLiuZJiaW, et al. A novel transformer-based neural network model for tool wear estimation. Meas Sci Technol2020; 31: 065106.
35.
DewiCChenR-CLiuY-T, et al. Synthetic data generation using DCGAN for improved traffic sign recognition. Neural Comput Appl2022; 34: 21465–21480.
