The processing of grinding data and the prediction of accuracy are extremely complex; this paper proposes a novel prediction method to ensure the machining accuracy of computer numerical control (CNC) grinding machines. It consists of two components, namely the filter decomposition recurrence plot (RP) transformation (FDRP) and the deep inverted residual attention network (DIRAN). A pipeline named FDRP has been designed to address the issues in the processing of data and the shortcomings of RP. Firstly, the displacement signals undergo filtering to preserve essential grinding information while effectively removing noise. Secondly, long-time series signals are decomposed and augmented based on the characteristics of the machining process. Lastly, an RP transformation is applied to one-dimensional time series data, resulting in the generation of images that accurately represent the grinding process. Furthermore, this paper proposes a novel machining accuracy prediction model. The DIRAN uses a multi-layer inverse residual network structure combined with attention mechanism to extract the features of two-dimensional RP, and its performance is better than other typical prediction methods. It can be applied to predict the polar angle of the workpiece in industrial processing and reduce the defect rate.
DeresseNCDeshpandeVTaifaIWR. Experimental investigation of the effects of process parameters on material removal rate using Taguchi method in external cylindrical grinding operation. Eng Sci Technol Int J2020; 23: 405–420.
2.
WuMChenHChangT, et al. Quality evaluation of internal cylindrical grinding process with multiple quality characteristics for gear products. Int J Prod Res2019; 57: 6687–6701.
3.
KishoreKSinhaMKChauhanSR. A comprehensive investigation of surface morphology during grinding of Inconel 625 using conventional grinding wheels. J Manuf Process2023; 97: 87–99.
4.
KishoreKChauhanSRSinhaMK. Application of machine learning techniques in environmentally benign surface grinding of Inconel 625. Tribol Int.2023; 188: 108812.
5.
ZengXXiongWZhangH, et al.Research on the consistency model of roundness error in journal cylindrical grinding with random parameters. Prec Eng2023; 82: 270–280.
6.
FanJYeQ. Research on geometric error modeling and compensation method of CNC precision cylindrical grinding machine based on differential motion theory and Jacobian matrix. Int J Adv Manuf Tech2022; 120: 1805–1819.
7.
SunLRenMHongH, et al.Thermal error reduction based on thermodynamics structure optimization method for an ultra-precision machine tool. Int J Adv Manuf Tech2017; 88: 1267–1277.
8.
HuLZhangHZhaJ, et al.Surface topography of cylindrical precision grinding based on multi-source information fusion. Proc Inst Mech Eng, Part E: J Process Mech Eng2023: 1884556481.
9.
ZhouRYangW. Analytical modeling of machining-induced residual stresses in milling of complex surface. Int J Adv Manuf Tech2019; 105: 565–577.
KlingenbergCOBorgesMAVAntunes JAVJr. Industry 4.0 as a data-driven paradigm: a systematic literature review on technologies. J Manuf Technol Manage2021; 32: 570–592.
12.
FuSWangLWangD, et al.Accurate prediction and compensation of machining error for large components with time-varying characteristics combining physical model and double deep neural networks. J Manuf Process2023; 99: 527–547.
13.
GuoJXiongQChenJ, et al.Study of static thermal deformation modeling based on a hybrid CNN-LSTM model with spatiotemporal correlation. Int J Adv Manuf Tech2022; 119: 2601–2613.
14.
LiBZhaoLYaoY. Multiconditional machining process quality prediction using deep transfer learning network. Adv Manuf2023; 11: 329–341.
15.
LongZZhangXSongD, et al. Motor fault diagnosis using image visual information and bag of words model. IEEE Sens J2021; 21: 21798–21807.
16.
WenLLiXGaoL, et al. A new convolutional neural network-based data-driven fault diagnosis method. IEEE T Ind Electron.2017; 65: 5990–5998.
17.
IslamMMKimJ. Automated bearing fault diagnosis scheme using 2D representation of wavelet packet transform and deep convolutional neural network. Comput Ind2019; 106: 142–153.
18.
MarwanNRomanoMCThielM, et al.Recurrence plots for the analysis of complex systems. Phys Rep2007; 438: 237–329.
19.
ZhouCZhangW. Recurrence plot based damage detection method by integrating T 2 control chart. Entropy-Switz2015; 17: 2624–2641.
20.
RajabiREstebsariA. Deep learning based forecasting of individual residential loads using recurrence plots. In: 2019 IEEE Milan PowerTech 2019, pp.1–5, IEEE.
21.
LiDLiangZRenW, et al.Structural damage identification under nonstationary excitations through recurrence plot and multi-label convolutional neural network. Measurement2021; 186: 110101.
22.
LiuXXiaLShiJ, et al. A fault diagnosis method of rolling bearing based on improved recurrence plot and convolutional neural network. IEEE Sens J2023; 23: 10767–10775.
23.
ZhangYHouYOuYangK, et al. Multi-scale signed recurrence plot based time series classification using inception architectural networks. Pattern Recognit2022; 123: 108385.
24.
Takyi-AninakwaPWangSZhangH, et al. An optimized long short-term memory-weighted fading extended Kalman filtering model with wide temperature adaptation for the state of charge estimation of lithium-ion batteries. Appl Energy2022; 326: 120043.
25.
HaoQShenYWangY, et al.Detection method based on Kalman filter for high speed rail defect AE signal on wheel-rail rolling rig. Nondestruct Test Eva2018; 33: 75–91.
26.
WuQMaYLiD, et al. Denoising algorithm of ground-airborne time-domain electromagnetic method based on variational Bayesian-based adaptive Kalman filter (VBAKF). J Appl Geophys2022; 202: 104674.
27.
NonomuraTShibataHTakakiR. Extended-Kalman-filter-based dynamic mode decomposition for simultaneous system identification and denoising. Plos One2019; 14: e0209836.
28.
ZengXGuoWYangK, et al.Noise reduction and retrieval by modified lidar inversion method combines joint retrieval method and machine learning. Appl Phys B2018; 124: –9.
29.
NeymotinSATalbotZNJungJQ, et al. Tracking recurrence of correlation structure in neuronal recordings. J Neurosci Meth2017; 275: 1–9.
30.
ZbilutJPWebber JrCL. Embeddings and delays as derived from quantification of recurrence plots. Phys Lett A1992; 171: 199–203.
CuiXGoelVKingsburyB. Data augmentation for deep neural network acoustic modeling. IEEE/ACM Trans Audio Speech Lang2015; 23: 1469–1477.
33.
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.
34.
SimonyanKZissermanA. Very deep convolutional networks for large-scale image recognition. Arxiv Preprint Arxiv:1409.1556 2014.
35.
SandlerMHowardAZhuM, et al. Mobilenetv2: inverted residuals and linear bottlenecks. In: Proceedings of the IEEE conference on computer vision and pattern recognition2018, pp.4510–4520.
36.
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.
37.
JiangZHeY. Research on stability prediction of the crankshaft CNC tangential point tracing grinding. Math Probl Eng2015; 2015: 106159. doi:10.1155/2015/106159.
38.
ShaoHXiaMHanG, et al.Intelligent fault diagnosis of rotor-bearing system under varying working conditions with modified transfer convolutional neural network and thermal images. IEEE T Ind Inform2020; 17: 3488–3496.
39.
ShiXQiuGYinC, et al.An improved bearing fault diagnosis scheme based on hierarchical fuzzy entropy and alexnet network. IEEE Access2021; 9: 61710–61720.
40.
LiuZMaoHWuC, et al. A convnet for the 2020s. In:Proceedings of the IEEE/CVF conference on computer vision and pattern recognition, 2022, pp.11976–11986.
