Abstract
The heat generated due to internal and external rotating components, electrical parts, and varying ambient temperatures can cause thermal deformations and significantly impact the precision of machine tools (MTs). Thermal error is crucial in industrial processes, corresponding to approximately 60–70% of MT errors. Accordingly, developing an accurate thermal error prediction model for MTs is essential for their high precision. Therefore, this study proposes an artificial neural network (ANN) model to predict the thermal deformation of a high-speed spindle. However, an important feature for the development of a reliable prediction model is the optimization of the input parameters such that the model generates accurate predictions. Hence, the development of an algorithm to determine the optimal input parameters is essential. Therefore, a genetic algorithm (GA)-based optimization model is also developed in this study to select the optimal input combinations (supply coolant temperature, coolant temperature difference between the inlet and outlet of the spindle, and supply coolant flow rate) for different spindle speeds ranging from 10,000 to 24,000 rpm in increments of 2000 rpm. The R2 values of the ANN prediction model are in the range of 0.94 to 0.98 for different spindle speeds. Furthermore, the optimized input parameters are used in single- and dual-spindle systems to verify the accuracy of the developed model as per ISO 230-3. For a single-spindle system, the thermal deformation prediction accuracy of the developed model is in the range of 96.26 to 98.82% and within 1.04 μm compared with the experimental findings. Moreover, when applied to a dual-spindle system, the model’s accuracy is improved by 7.31% compared with that of the variable coolant volume (VCV) method. The maximum deviation of the dual-spindle system can be controlled to within 2.52 μm using the optimized input parameters for a single-spindle system without further optimizing the parameters. The results show that the proposed input attribute optimization (IAO) model can also be adopted for dual-spindle systems to achieve greater prediction accuracy and precision of the machining process, and one industrial cooler can be used for multiple spindles of the same type. In dual-spindle systems operating at different spindle speeds, the power consumption could be reduced by 11% to 34%, and the total lifetime CO2 emissions could be reduced from 72,981 to 52,595.5 kg. These substantial reductions in energy consumption and CO2 emissions highlight the potential of dual-spindle systems to contribute to sustainable manufacturing.
Graphical abstract
Similar content being viewed by others
Data availability
Data will be made available on request.
Abbreviations
- ANN:
-
Artificial neural network
- GA:
-
Genetic algorithm
- ISO:
-
International Organization for Standardization
- MT:
-
Machine tool
- VCV:
-
Variable coolant volume
- IAO:
-
Input attribute optimization
- CCV:
-
Constant coolant volume
- PID:
-
Proportional–integral–derivative
- FEM:
-
Finite element method
- FDEM:
-
Finite difference element method
- AI:
-
Artificial intelligence
- BR:
-
Bayesian regularization
- BP:
-
Backpropagation
- IPSO:
-
Improved particle swarm optimization
- SOM:
-
Self-organizing feature map
- FFNN:
-
Feedforward neural network
- MA:
-
Moving average
- LR:
-
Linear regression
- AR:
-
Autoregression
- SGNN:
-
Serial gray neural network
- PGNN:
-
Parallel gray neural network
- BAS:
-
Beetle antennae search
- ANFIS:
-
Adaptive neuro-fuzzy inference system
- SVD-AUKF:
-
Singular value decomposition-adaptive unscented Kalman filter
- LASSO:
-
Least absolute shrinkage and selection operator
- XGBoost:
-
Extreme Gradient Boosting
- RF:
-
Random forest
- SA-PSO-SVR:
-
Simulated annealing-particle swarm optimization and support vector regression
- GPR:
-
Gaussian process regression
- MSE:
-
Mean squared error
- RWS:
-
Roulette wheel selection
- WOA:
-
Whale optimization algorithm
- BOA:
-
Butterfly optimization algorithm
- GS:
-
Gravitational search
- IPO:
-
Inclined planes system optimization
- ∆Y :
-
Overall uncertainty
- ∆x n :
-
Individual variable uncertainty
- H j :
-
jth neuron in the hidden layer
- i :
-
Index of neurons in the input layer
- j :
-
Index of neurons in the hidden layer
- k :
-
Index of neurons in the output layer
- f :
-
Transfer function
- a j :
-
Threshold value of the jth neuron in the hidden layer
- b k :
-
Threshold value of the kth neuron in the output layer
- Q ij :
-
Weight between the ith and jth neurons
- Q ik :
-
Weight between the jth and kth neurons
- O k :
-
kth neuron in the output layer
- e k :
-
Error between the predicted and desired outputs
- P k :
-
Predicted output
- Y k :
-
Desired output
- N :
-
Number of samples
- P i :
-
Selection probability of the ith individual
- f i :
-
Fitness value of the ith individual
- f j :
-
Fitness value of the jth individual
- n :
-
Total number of individuals
- δ z :
-
Thermal deformation along the Z-axis
- m :
-
Axis direction
- t :
-
Index of heat sources
- l :
-
Total number of deformational components
- δ zt :
-
Thermal deformation along the Z-axis due to the tth heat source
- ε :
-
Strain
- ε zt :
-
Strain along the Z-axis due to the temperature change of the tth heat source
- ∆T t :
-
Temperature difference between the initial and steady states for the tth heat source
- ∆T base :
-
Change in the temperature of the base
- ∆T sp :
-
Change in the temperature of the spindle
- ∆T m :
-
Change in the temperature of the motor
- ∆T c :
-
Change in the temperature of the coolant
- ε z ,base :
-
Strain along the Z-axis due to the temperature change of the base
- ε z ,sp :
-
Strain along the Z-axis due to the temperature change of the spindle
- ε z ,m :
-
Strain along the Z-axis due to the temperature change of the motor
- ε z ,m,sp :
-
Strain along the Z-axis due to the temperature changes of the motor and spindle
- α :
-
Thermal expansion coefficient
- L :
-
Length of a system component
- A :
-
Accuracy
- AI :
-
Accuracy improvement
- Number of inputs:
-
3
- Number of hidden layers:
-
14
- Number of output layers:
-
1
- Max. number of epochs:
-
1000
- Learning rate:
-
0.1
- Accuracy:
-
0.001
- Population size:
-
38
- Number of generations:
-
100
- Crossover rate:
-
0.2
- Mutation rate:
-
0.1
References
Chiang, W. M., Luo, W. J., & Wang, F.-J. (2018). Temperature control scheme using hot-gas bypass for a machine tool oil cooler. Journal of Mechanical Science and Technology, 32, 1391. https://doi.org/10.1007/s12206-018-0242-5
Cui, L. Y., Zhang, D. W., Gao, W. G., Qi, X. Y., & Shen, Y. (2011). Thermal errors simulation and modeling of motorized spindle (pp. 1305–1309). Trans Tech Publications. https://doi.org/10.4028/www.scientific.net/AMR.154-155.1305
Denkena, B., Bergmann, B., & Klemme, H. (2020). Cooling of motor spindles—A review. The International Journal of Advanced Manufacturing Technology, 110, 3273–3294. https://doi.org/10.1007/s00170-020-06069-0
Fang, B., Gu, T., Ye, D., & Luo, T. (2016). An improved thermo-mechanical model for vertical machining center. The International Journal of Advanced Manufacturing Technology, 87, 2581–2592. https://doi.org/10.1007/s00170-016-8651-z
Filipovic, V., Nedic, N., & Stojanovic, V. (2011). Robuste Identifikation von pneumatischen Servo-Aktuatoren in der realen Situationen. Forschung im Ingenieurwesen, 75, 183–196. https://doi.org/10.1007/s10010-011-0144-5
Fu, G., Zhou, L., Zheng, Y., Caijiang, L., Wang, X., & Xie, L. (2022). Improved unscented Kalman filter algorithm-based rapid identification of thermal errors of machine tool spindle for shortening thermal equilibrium time. Measurement, 195, 111121. https://doi.org/10.1016/j.measurement.2022.111121
Grama, S. N., Mathur, A., & Badhe, A. N. (2018). A model-based cooling strategy for motorized spindle to reduce thermal errors. International Journal of Machine Tools and Manufacture, 132, 3–16. https://doi.org/10.1016/j.ijmachtools.2018.04.004
Hao, W., Hongtao, Z., Qianjian, G., Xiushan, W., & Jianguo, Y. (2008). Thermal error optimization modeling and real-time compensation on a CNC turning center. Journal of Materials Processing Technology, 207, 172–179. https://doi.org/10.1016/j.jmatprotec.2007.12.067
He, P., Wen, J., Stojanovic, V., Liu, F., & Luan, X. (2022). Finite-time control of discrete-time semi-Markov jump linear systems: A self-triggered MPC approach. Journal of the Franklin Institute, 359(13), 6939–6957. https://doi.org/10.1016/j.jfranklin.2022.06.043
Holkup, T., Cao, H., Koláˇr, P., Altintas, Y., & Zelený, J. (2010). Thermo-mechanical model of spindles. CIRP Annals, 59, 365–368. https://doi.org/10.1016/j.cirp.2010.03.021
Hsieh, M. C., Maurya, S. N., Luo, W. J., Li, K. Y., Hao, L., & Bhuyar, P. (2022). Coolant volume prediction for spindle cooler with adaptiveneuro-fuzzy inference system control method. Sensors & Materials, 34, 2447–2466. https://doi.org/10.18494/SAM3794
Jedrzejewski, J., Kowal, Z., Kwasny, W., & Modrzycki, W. (2005). High-speed precise machine tools spindle units improving. Journal of Materials Processing Technology, 162, 615–621. https://doi.org/10.1016/j.jmatprotec.2005.02.149
Kang, Y., Chang, C. W., Huang, Y., Hsu, C. L., & Nieh, I. F. (2007). Modification of a neural network utilizing hybrid filters for the compensation of thermal deformation in machine tools. International Journal of Machine Tools and Manufacture, 47, 376–387. https://doi.org/10.1016/j.ijmachtools.2006.03.007
Kine, S., & McClintock, F. (1953). Describing uncertainties in single-sample experiments. Mechanical Engineering, 75, 3–8.
Kosarac, A., Mladjenovic, C., Zeljkovic, M., Tabakovic, S., & Knezev, M. (2022). Neural-network-based approaches for optimization of machining parameters using small dataset. Materials, 15, 700. https://doi.org/10.3390/ma15030700
Li, B., Tian, X., & Zhang, M. (2019). Thermal error modeling of machine tool spindle based on the improved algorithm optimized BP neural network. The International Journal of Advanced Manufacturing Technology, 105, 1497–1505. https://doi.org/10.1007/s00170-019-04375-w
Li, K. Y., Liao, M. C., & Maurya, S. N. (2022). Linear axial error signal measurement and processing method of a machine tool for accuracy compensation improvement. Sensors & Materials, 34, 4137. https://doi.org/10.18494/SAM4152
Li, K. Y., Luo, W. J., Hong, X. H., Wei, S. J., & Tsai, P. H. (2020). Enhancement of machining accuracy utilizing varied cooling oil volume for machine tool spindle. IEEE Access, 8, 28988–29003. https://doi.org/10.1109/ACCESS.2020.2972580
Li, K. Y., Luo, W. J., Huang, J. Z., Chan, Y. C., & Faridah, D. (2017). Operational temperature effect on positioning accuracy of a single-axial moving carrier. Applied Sciences, 7, 420. https://doi.org/10.3390/app7040420
Li, K.-Y., Luo, W.-J., & Wei, S.-J. (2020). Machining accuracy enhancement of a machine tool by a cooling channel design for a built-in spindle. Applied Sciences, 10(11), 3991. https://doi.org/10.3390/app10113991
Li, K. Y., Luo, W. J., Yang, M. H., Hong, X. H., Luo, S. J., & Chen, C. N. (2019). Effect of supply cooling oil temperature in structural cooling channels on the positioning accuracy of machine tools. Journal of Mechanics, 35, 887–900. https://doi.org/10.1017/jmech.2019.29
Li, K. Y., Luo, W. J., Zeng, Y. R., & Huang, I. H. (2020). Increase in accuracy of a built-in spindle by adaptive cooling control with varied coolant volume and temperature. Sensors & Materials, 32, 3689–3706. https://doi.org/10.18494/SAM.2020.3104
Li, K. Y., Maurya, S. N., Lee, Y. H., Luo, W. J., Chen, C. N., & Wellid, I. (2023). Thermal deformation and economic analysis of a multiobject cooling system for spindles with varied coolant volume control. The International Journal of Advanced Manufacturing Technology, 126, 1807–1825. https://doi.org/10.1007/s00170-023-10988-z
Li, Z., Zhu, B., Dai, Y., Zhu, W., Wang, Q., & Wang, B. (2021). Research on thermal error modeling of motorized spindle based on BP neural network optimized by beetle antennae search algorithm. Machines, 9, 286. https://doi.org/10.3390/machines9110286
Li, Z., Zhu, B., Dai, Y., Zhu, W., Wang, Q., & Wang, B. (2022). Thermal error modeling of motorized spindle based on Elman neural network optimized by sparrow search algorithm. The International Journal of Advanced Manufacturing Technology, 121, 349–366. https://doi.org/10.1007/s00170-022-09260-7
Lippmann, R. (1987). An introduction to computing with neural nets. IEEE ASSP Magazine, 4, 4–22. https://doi.org/10.1109/MASSP.1987.1165576
Liu, B., Jin, W., Lu, A., Liu, K., Wang, C., & Mi, G. (2020). Optimal design for dual laser beam butt welding process parameter using artificial neural networks and genetic algorithm for SUS316L austenitic stainless steel. Optics & Laser Technology, 125, 106027. https://doi.org/10.1016/j.optlastec.2019.106027
Liu, Y. L., Nisa, E. C., Kuan, Y. D., Luo, W. J., & Feng, C. C. (2023). Combining deep neural network with genetic algorithm for axial flow fan design and development. Processes, 11, 122. https://doi.org/10.3390/pr11010122
Liu, Z., Pan, M., Zhang, A., Zhao, Y., Yang, Y., & Ma, C. (2015). Thermal characteristic analysis of high-speed motorized spindle system based on thermal contact resistance and thermal-conduction resistance. The International Journal of Advanced Manufacturing Technology, 76, 1913–1926. https://doi.org/10.1007/s00170-014-6350-1
Lo, Y. C., Hu, Y. C., & Chang, P. Z. (2018). Parameter estimation of the thermal network model of a machine tool spindle by self-made bluetooth temperature sensor module. Sensors, 18, 656. https://doi.org/10.3390/s18020656
Luo, W.-J., Chen, K.-S., Chun-Min, Y., & Hsu, T.-H. (2020). The fuzzy process quality evaluation model for the stb quality characteristic of machining. Applied Sciences, 10(22), 8272. https://doi.org/10.3390/app10228272
Lv, C., Liu, Z. Y., Liu, Z. J., & Yu, Z. M. (2015). Application of generalized radial basis function neural network to thermal error modeling. Optics and Precision Engineering, 23, 1705–1713. https://doi.org/10.3788/OPE.20152306.1705
Maurya, S. N., Li, K. Y., Luo, W. J., & Kao, S. Y. (2022). Effect of coolant temperature on the thermal compensation of a machine tool. Machines, 10(12), 1201. https://doi.org/10.3390/machines10121201
Mayr, J., Jedrzejewski, J., Uhlmann, E., AlkanDonmez, M., Knapp, W., Härtig, F., Wendt, K., Moriwaki, T., Shore, P., Schmitt, R., Brecher, C., Wurz, T., & Wegener, K. (2012). Thermal issues in machine tools. CIRP Annals-Manufacturing Technology, 61, 771–791. https://doi.org/10.1016/j.cirp.2012.05.008
Mayr, J., Sascha, W., & Konrad W. (2007). Comparing the thermo-machanical-behavior of machine tool frame designs using a FDM-FEA simulation approach. In: Proceedings of: the twenty-second annual meeting. American Society for Precision Engineering, (pp. 17–20). http://hdl.handle.net/20.500.11850/4983
Ramesh, R., Mannan, M. A., & Poo, A. N. (2000). Error compensation in machine tools—A review: Part II: Thermal errors. International Journal of Machine Tools and Manufacture, 40, 1257–1284. https://doi.org/10.1016/S0890-6955(00)00010-9
Stojanović, V. (2023). Fault-tolerant control of a hydraulic servo actuator via adaptive dynamic programming. Mathematical Modelling and Control. https://doi.org/10.3934/mmc.2023016
Uhlmann, E., & Hu, J. (2012). Thermal modelling of a high speed motor spindle. Procedia CIRP, 1, 313–318. https://doi.org/10.1016/j.procir.2012.04.056
Wei, X., Ye, H., Miao, E., & Pan, Q. (2022). Thermal error modeling and compensation based on Gaussian process regression for CNC machine tools. Precision Engineering, 77, 65–76. https://doi.org/10.1016/j.precisioneng.2022.05.008
Yan, K., Hong, J., Zhang, J., Mi, W., & Wu, W. (2016). Thermal-deformation coupling in thermal network for transient analysis of spindle-bearing system. International Journal of Thermal Sciences, 104, 1–12. https://doi.org/10.1016/j.ijthermalsci.2015.12.007
Yang, Y., Du, Z., Feng, X., & Yang, J. (2021). Real-time thermal modeling approach of a machine tool spindle based on bond graph method. The International Journal of Advanced Manufacturing Technology, 113, 99–115. https://doi.org/10.1007/s00170-021-06611-8
Yang, Z., Sun, M., Li, W., & Liang, W. (2011). Modified Elman network for thermal deformation compensation modeling in machine tools. The International Journal of Advanced Manufacturing Technology, 54, 669–676. https://doi.org/10.1007/s00170-010-2961-3
Ye, H., Wei, X., Zhuang, X., & Miao, E. (2022). An improved robust thermal error prediction approach for CNC machine tools. Machines, 10(8), 624. https://doi.org/10.3390/machines10080624
Yeh, H.-C., Yang, R.-J., & Luo, W.-J. (2011). Analysis of traveling-wave electro-osmotic pumping with double-sided electrode arrays. Physical Review E, 83(5), 056326. https://doi.org/10.1103/physreve.83.056326
Yu, C.-M., Luo, W.-J., Hsu, T.-H., & Lai, K.-K. (2020). Two-tailed fuzzy hypothesis testing for unilateral specification process quality index. Mathematics, 8(12), 2129. https://doi.org/10.3390/math8122129
Zhang, Q., Song, X., Song, S., & Stojanovic, V. (2023). Finite-time sliding mode control for singularly perturbed PDE systems. Journal of the Franklin Institute, 360(2), 841–861. https://doi.org/10.1016/j.jfranklin.2022.11.037
Zhang, Y., Yang, J., & Jiang, H. (2012). Machine tool thermal error modeling and prediction by grey neural network. The International Journal of Advanced Manufacturing Technology, 59, 1065–1072. https://doi.org/10.1007/s00170-011-3564-3
Zhou, C., Qu, Z., Hu, B., & Li, S. (2021). Thermal network model and experimental validation for a motorized spindle including thermal-mechanical coupling effect. The International Journal of Advanced Manufacturing Technology, 115, 487–501. https://doi.org/10.1007/s00170-021-07221-0
Zhou, Z., Dai, Y., Wang, G., Li, S., Pang, J., & Zhan, S. (2022). Thermal displacement prediction model of SVR high-speed motorized spindle based on SA-PSO optimization. Case Studies in Thermal Engineering, 40, 102551. https://doi.org/10.1016/j.csite.2022.102551
Zhu, M., Yang, Y., Feng, X., Zhengchun, D., & Yang, J. (2023). Robust modeling method for thermal error of CNC machine tools based on random forest algorithm. Journal of Intelligent Manufacturing, 34(4), 2013–2026. https://doi.org/10.1007/s10845-021-01894-w
Zivkovic, A., Zeljkovic, M., Tabakovic, S., & Milojevic, Z. (2015). Mathematical modeling and experimental testing of high-speed spindle behavior. The International Journal of Advanced Manufacturing Technology, 77, 1071–1086. https://doi.org/10.1007/s00170-014-6519-7
Funding
This work was supported by the National Science and Technology Council (Ministry of Science and Technology), Taiwan, under Grant MOST 109-2622-E-167-015.
Author information
Authors and Affiliations
Contributions
Material preparation, data collection, and analysis were performed by Swami Nath Maurya and Win-Jet Luo. Swami Nath Maurya and Win-Jet Luo wrote the first draft of the manuscript; review and editing were done by Swami Nath Maurya, Win-Jet Luo, and Bivas Panigrahi, and all the authors commented on the current version of the manuscript. All the authors have read and approved the final manuscript.
Corresponding author
Ethics declarations
Competing interests
The authors declare no competing interests.
Additional information
Publisher's Note
Springer Nature remains neutral with regard to jurisdictional claims in published maps and institutional affiliations.
Supplementary Information
Below is the link to the electronic supplementary material.
Rights and permissions
Springer Nature or its licensor (e.g. a society or other partner) holds exclusive rights to this article under a publishing agreement with the author(s) or other rightsholder(s); author self-archiving of the accepted manuscript version of this article is solely governed by the terms of such publishing agreement and applicable law.
About this article
Cite this article
Maurya, S.N., Luo, WJ., Panigrahi, B. et al. Input attribute optimization for thermal deformation of machine-tool spindles using artificial intelligence. J Intell Manuf (2024). https://doi.org/10.1007/s10845-024-02350-1
Received:
Accepted:
Published:
DOI: https://doi.org/10.1007/s10845-024-02350-1