The motorized spindle is the core component of a CNC grinding machine. During the machining process, the working conditions are complex and variable. The uneven temperature distribution caused by internal and external heat sources in the motorized spindle leads to nonlinear and time-varying thermal deformation, particularly, axial thermal elongation can exceed several tens of micrometers, significantly compromising the grinder’s machining accuracy. To effectively implement thermal error compensation with high accuracy and cost-efficiency, a CNN-BiLSTM-AM based thermal error prediction model for the motorized spindle is proposed, which combines CNN for spatial feature extraction, BiLSTM for capturing long temporal dependencies, and an attention mechanism to enhance feature relevance. The model’s prediction performance and robustness were validated through thermal characteristic experiments under various working conditions. In the predictions for Tests 2 and 3, the maximum residuals between the predicted and measured axial thermal deformation were 1.326 μm and 1.495 μm, with R2 values as high as 0.991 and 0.992, MAEs as low as 0.524 μm and 0.589 μm, and RMSEs of 0.596 μm and 0.691 μm, respectively. All metrics outperformed those of comparative methods. Furthermore, the thermal compensation experiments were performed to verify the model’s practical applicability.
WegenerKBleicherFKrajnikP, et al. Recent developments in grinding machines. CIRP Ann2017; 66(2): 779–802.
2.
SchwenkeHKnappWHaitjemaH, et al. Geometric error measurement and compensation of machines—an update. CIRP Ann2008; 57(2): 660–675.
3.
NiuPChengQChenC, et al. An approach for crucial geometric error analysis and accuracy enhancement of gantry milling machines based on generalized correlation sensitivity. J Manuf Process2024; 119: 401–413.
4.
LyuDZhangJWangJ, et al. R-test-based identification method for geometric errors of rotary axes in a five-axis machine tool with a rotary table and tilting head. Measurement2024; 225: 113932.
5.
YangJAltintasY.A generalized on-line estimation and control of five-axis contouring errors of CNC machine tools. Int J Mach Tools Manuf2015; 88: 9–23.
6.
XiaoYGeGDengM, et al. An unconstrained and non-redundant identification method of geometric errors and compensation of machine tools by X-AX Laserbar. Manuf Lett2024; 41: 31–42.
7.
MayrJJedrzejewskiJUhlmannE, et al. Thermal issues in machine tools. CIRP Ann2012; 61(2): 771–791.
8.
LiGWangZLiZ, et al. Segmented modeling and compensation of thermal error of gear grinding machine spindle based on variable thermal hysteresis. Int J Adv Manuf Technol2023; 126(11): 5107–5121.
9.
LiYBaiYHouZ, et al. Thermal error modeling and compensation of spindle based on gate recurrent unit network. Int J Adv Manuf Technol2023; 128(11): 5519–5528.
10.
YaoXDuZGeG, et al. Dynamic temperature gradient and unfalsified control approach for machine tool thermal error compensation. J Mech Sci Technol2020; 34: 319–331.
11.
HsiehMCMauryaSNLuoWJ, et al. Coolant volume prediction for spindle cooler with adaptive neuro-fuzzy inference system control method. Sens Mater2022; 34: 2447–2466.
12.
LiKYMauryaSNLeeYH, et al. Thermal deformation and economic analysis of a multiobject cooling system for spindles with varied coolant volume control. Int J Adv Manuf Technol2023; 126(3): 1807–1825.
13.
ZhouZDGuiLTanYG, et al. Actualities and development of heavy-duty CNC machine tool thermal error monitoring technology. Chin J Mech Eng2017; 30: 1262–1281.
14.
ReddyTNShanmugarajVVinodP, et al. Real-time thermal error compensation strategy for precision machine tools. Mater Today Proc2020; 22: 2386–2396.
15.
LiYYuMBaiY, et al. A review of thermal error modeling methods for machine tools. Appl Sci2021; 11(11): 5216.
16.
YangYDuZFengX, et al. Real-time thermal modelling approach of a machine tool spindle based on bond graph method. Int J Adv Manuf Technol2021; 113(1): 99–115.
17.
ZhouCQuZHuB, et al. Thermal network model and experimental validation for a motorized spindle including thermal–mechanical coupling effect. Int J Adv Manuf Technol2021; 115(1): 487–501.
18.
XiangSYaoXDuZ, et al. Dynamic linearization modeling approach for spindle thermal errors of machine tools. Mechatronics2018; 53: 215–228.
19.
LiGTangXLiZ, et al. The temperature-sensitive point screening for spindle thermal error modeling based on IBGOA-feature selection. Precis Eng2022; 73: 140–152.
20.
LiYTianHLiuD, et al. Thermal error analysis of five-axis machine tools based on five-point test method. Lubricants2022; 10(6): 122.
21.
ChenCCHungWC. Thermal error modeling of CNC machine tool spindle based on multiple regression and features selection. In: IEEE 3rd Eurasia conference on IOT, communication and engineering (ECICE), Yunlin, Taiwan, 29–31 October, 2021, pp.583–587. IEEE.
22.
TanFYinGZhengK, et al. Thermal error prediction of machine tool spindle using segment fusion LSSVM. Int J Adv Manuf Technol2021; 116(1): 99–114.
23.
LinSWLeeZJChenSC, et al. Parameter determination of support vector machine and feature selection using simulated annealing approach. Appl Soft Comput2008; 8(4): 1505–1512.
24.
Muñoz-ZavalaAEMacías-DíazJEAlba-CuéllarD, et al. A literature review on some trends in artificial neural networks for modeling and simulation with time series. Algorithms2024; 17(2): 76.
25.
ShiZFanJSongL, et al. Nonlinear functional regression by functional deep neural network with kernel embedding. arxiv Preprint. arxiv:2401.02890, 2024.
26.
ShiriFMPerumalTMustaphaN, et al. A comprehensive overview and comparative analysis on deep learning models: CNN, RNN, LSTM, GRU. arxiv Preprint. arxiv:2305.17473, 2023.
27.
FujishimaMNarimatsuKIrinoN, et al. Thermal displacement reduction and compensation of a turning center. CIRP J Manuf Sci Technol2018; 22: 111–115.
28.
LiuJMaCGuiH, et al. Thermally-induced error compensation of spindle system based on long short term memory neural networks. Appl Soft Comput2021; 102: 107094.
29.
FriedrichCGeistAYaqoobMF, et al. Correction of thermal errors in machine tools by a hybrid model approach. Appl Sci2024; 14(2): 671.
30.
StephanTThiyaguVAShridharPK.A deep learning-inspired IoT-enabled hybrid model for predicting structural changes in CNC machines based on thermal behaviour. Int J Grid Utility Comput2024; 15(1): 3–15.
31.
SherstinskyA.Fundamentals of recurrent neural network (RNN) and long short-term memory (LSTM) network. Physica D2020; 404: 132306.
32.
SoydanerD.Attention mechanism in neural networks: where it comes and where it goes. Neural Comput Appl2022; 34(16): 13371–13385.
33.
GuJWangZKuenJ, et al. Recent advances in convolutional neural networks. Pattern Recognit2018; 77: 354–377.
34.
ChengyangWSitongXWanshengX.Spindle thermal error prediction approach based on thermal infrared images: a deep learning method. J Manuf Syst2021; 59: 67–80.
