Abstract
Large-size gear profile grinder is extremely important for high-accuracy machining of large-scale and high-performance gears. A lot of heat is generated during the service process, leading to thermal errors of large-size gear profile grinder. In recent years, the data-based modeling and prediction methods have been widely used in manufacturing systems to control thermal errors. However, a limited bandwidth and latency characteristic of industrial Internet has brought serious challenges to the real-time and efficient processing of a large-volume data. To solve the above problems, a digital twin system of thermal error control is proposed for large-size gear profile grinders. The theoretical-based modeling method is used to prove the memory behavior, and then the feasibility of applying gated recurrent unit (GRU) to thermal error control is demonstrated due to its strong long-term memorizing capability. Then the hyper-parameters of GRU model is optimized by an improved bat algorithm (IBA), and the self-learning IBA-GRU error model is proposed. Finally, a digital twin system of thermal error control is established based on a new haze-cloud computing architecture to improve the executing efficiency, and the self-learning IBA-GRU error control model is embedded into the digital twin system. With the implementation of the digital twin system, the reduced percentages for the maximum tooth profile tilt deviations of \(f_{H\alpha l}\) and \(f_{H\alpha r}\) for the left and right tooth flanks are 58.43% and 64.16%, respectively, and the reduced percentages for the maximum total tooth profile deviations of \(F_{\alpha l}\) and \(F_{\alpha r}\) for the left and right tooth flanks are 28.78% and 34.53%, respectively. The saved ratio of the transferred data is up to 76.30% in 5 months. The executing efficiency of the digital twin system with IBA-GRU as control model is higher than that with other models and architectures.
Similar content being viewed by others
Abbreviations
- c :
-
Specific heat capacity
- ρ :
-
Density
- \(Q_{{\text{v}}}\) :
-
Internal heat source
- \(T\) :
-
Temperature
- \(t\) :
-
Time
- \(x\), \(y\), \(z\) :
-
Coordinates
- \(M_{0}\) :
-
Lubricating friction torque
- \(M_{1}\) :
-
Load friction torque
- \(v\) :
-
Kinematic viscosity of lubricant
- \(d_{m}\) :
-
Pitch diameter of bearings
- \(P_{1}\) :
-
Comprehensive load
- \(f_{1}\) :
-
Coefficient related to bearing type and lubricating method
- \(A_{c}\) :
-
Actual contact surface
- \(A\) :
-
Nominal contact surface
- \(A_{v}\) :
-
Area of the non-contact area
- \(k_{1}\),\(k_{2}\), and \(k_{f}\) :
-
Thermal conductivity
- \(L_{g}\) :
-
Thickness of uncontacted space
- \(p\) :
-
Contact pressure between the contact surfaces
- \(G\), \(Lu\), and \(D\) :
-
Fractal parameters of joint surface
- \(H\) :
-
Hardness of softer material in the two contact parts
- \(E\) :
-
Equivalent elastic modulus of the two contact materials
- \(k_{x}\) and \(k_{y}\) :
-
Ratio coefficients
- \(A_{i}\) :
-
Loudness
- \(v_{i}^{t}\) and \(x_{i}^{t}\) :
-
The velocity and position at the time of \(t\)
- \(f_{i}\) :
-
Pulse frequency of the bat \(i\)
- \(\overline{A}^{t}\) :
-
Average loudness at time of \(t\) for bat \(i\)
- \(r_{t}\) :
-
Reset gate
- \(z_{t}\) :
-
Update gate
- \(h_{t - 1}\) :
-
The previous hidden state
- \(v_{k}\) :
-
Velocity of the bat at the time of \(k\)
- \(b\) :
-
Constant pulse frequency
- \(\varepsilon_{x}\), \(\varepsilon_{y}\), and \(\varepsilon_{z}\) :
-
Deformation components
- \(\sigma_{x}\), \(\sigma_{y}\), and \(\sigma_{z}\) :
-
Stress components
- \(E\) :
-
Elastic modulus
- \(\mu\) :
-
Poisson’s ratio
- \(M\) :
-
Total friction torque
- \(n\) :
-
Rotational speed
- \(h\) :
-
Convective coefficient
- \(\lambda\) :
-
Thermal conductivity of air
- \(\Pr\) :
-
Prandtl Number
- \(d\) :
-
Equivalent diameter of spindle;
- \(v\) :
-
Kinematic viscosity of air
- \(x^{*}\) :
-
Current global optimal position
- \(f_{\max }\) and \(f_{\min }\) :
-
Upper and lower limits of the pulse frequency
- \(\alpha\) :
-
Attenuation coefficient of pulse loudness
- \(\gamma\) :
-
Increase coefficient of pulse frequency
- J :
-
Minimization function of the structural risk
- \(\omega\) :
-
Weight vector
- \(\xi_{i}\) :
-
Error variable
- \(\gamma\) :
-
Adjustable parameters
- \(x_{i}\) :
-
Input variable
- \(y_{i}\) :
-
Objective value
- \(\varphi \left( \cdot \right)\) :
-
Mapping function
- b :
-
Deviation
- \(h_{t}\) :
-
New memory content
- \(\alpha_{i}\), \(\beta_{i}\), and \(\eta_{i}\) :
-
Lagrangian coefficients
- \(b_{1}\), \(b_{2}\), and \(b_{3}\) :
-
Deviations
- \(K(x,x_{i} )\) :
-
Kernel function
- \(x_{t}\) :
-
Current input
- \(x_{k}\) :
-
Position of the bat at the time of \(k\)
- \(p\) :
-
Current global optimal position
- \(a\), \(c\) and \(d\) :
-
Weight coefficients
References
Avallone EA, Baumeister T, Sadegh A (2006) Marks’ standard handbook for mechanical engineers (standard handbook for mechanical engineers). Mcgraw-Hill Professional, New York
Bellavista P, Berrocal J, Corradi A, Das SK, Luca F, Zanni A (2019) A Survey on fog computing for the Internet of Things. Pervasive Mob Comput 52:71–99
Bello SA, Oyedele LO, Akinade OO, Bilal M, Delgado JMD, Akanbi LA, Ajayi AO, Owolabi HA (2021) Cloud computing in construction industry: Use cases, benefits and challenges. Automat Constr 122:103441
Bi L, Tao F, Zhang P, Nee AYC (2020) Opportunistic maintenance for multi-unit series systems based on gated recurrent units prediction model. CIRP Ann-Manuf Technol 69(1):25–28
Chen B, Wan J, Antonio C, Li D, Abbas H, Zhang Q (2018) Edge computing in IoT-based manufacturing. IEEE Commun Mag 56(9):103–109
Chiang CJ, Fong ZH, Tseng JT (2009) Computerized simulation of thread form grinding process. Mech Mach Theory 44(4):685–696
Ding H, Tang J, Zhong J (2016) Accurate nonlinear modeling and computing of grinding machine settings modification considering spatial geometric errors for hypoid gears. Mech Mach Theory 99:155–175
Guo H, Fuentes-Aznar A (2020) Compensation of errors of alignment caused by shaft deflections in face-gear drives generated by shaper cutters. Mech Mach Theory 144:103667
Guo H, Chen S, Mohamed K, Qu T, Wang S, Li J (2021) A digital twin-based flexible cellular manufacturing for optimization of air conditioner line. J Manuf Syst 58:65–78
Habibi M, Arezoo B, Nojedeh MV (2011) Tool deflection and geometrical error compensation by tool path modification. Int J Mach Tool Manuf 51:439–449
Haidar M, Ishibashi A, Sonoda K (1999) Minimization of effect of CBN wheel wear on ground gear errors. Int J Mach Tool Manuf 39(4):607–626
Harris TA (1984) Rolling bearing analysis. Wiley, New York
Hu P, Dhelim S, Ning H, Qiu T (2017) Survey on fog computing: architecture, key technologies, applications and open issues. J Netw Comput Appl 98:27–42
ISO 1328-1 (2013) Cylindrical gears-ISO system of flank tolerance classification—part 1: definitions and allowable values of deviations relevant to flanks of gear teeth. ISO copyright office, Geneva
ISO 230-3 (2007) Test code for machine tools part 3: determination of thermal effects. ISO copyright office, Geneva
Jauro F, Chiroma H, Gital A, Almutairi M, Abdulhamid SM, Abawajy JH (2020) Deep learning architectures in emerging cloud computing architectures: recent development, challenges and next research trend. Appl Soft Comput 96:106582
Kizaki T, Katsuma T, Ochi M, Fukui R (2019) Direct observation and analysis of heat generation at the grit-workpiece interaction zone in a continuous generating gear grinding. CIRP Ann-Manuf Technol 68(1):417–422
Kruszyński B, Midera S, Kaczmarek J, Ezoe S (1998) Forces in generating gear grinding-theoretical and experimental approach. CIRP Ann-Manuf Technol 47(1):287–290
Leng J, Liu Q, Ye S, Jing J, Wang Y, Zhang C, Zhang D, Chen X (2020) Digital twin-driven rapid reconfiguration of the automated manufacturing system via an open architecture model. Robot CIM-Int Manuf 63:101895
Li T, Pan C (2009) On grinding manufacture technique and tooth contact and stress analysis of ring-involute spherical gears. Mech Mach Theory 44(10):1807–1825
Liang YC, Li WD, Lou P, Hu JM (2020) Thermal error prediction for heavy-duty CNC machines enabled by long short-term memory networks and fog-cloud architecture. J Manuf Syst. https://doi.org/10.1016/j.jmsy.2020.10.008
Liu J, Ma C, Wang S, Wang S, Yang B, Shi H (2018a) Thermal-structure interaction characteristics of a high-speed spindle- bearing system. Int J Mach Tool Manuf 137:42–57
Liu Y, Wan M, Xiao Q, Zhang W (2018b) Identification and compensation of geometric errors of rotary axes in five-axis machine tools through constructing equivalent rotary axis. Int J Mech Sci 152:211–227
Liu J, Ma C, Wang S (2020a) Data-driven thermal error compensation of linear x-axis of worm gear machines with error mechanism modeling. Mech Mach Theory 153:104009
Liu J, Ma C, Wang S (2020b) Data-driven thermally-induced error compensation method of high-speed and precision five-axis machine tools. Mech Syst Signal Process 138:106538
Liu L, Luo S, Guo F, Tan S (2020c) Multi-point shortest path planning based on an Improved Discrete Bat Algorithm. Appl Soft Comput 95:106498
Liu Q, Leng J, Yan D, Zhang D, Wei L, Yu A, Zhao R, Zhang H, Chen X (2020d) Digital twin-based designing of the configuration, motion, control, and optimization model of a flow-type smart manufacturing system. J Manuf Syst 58:52–64
Liu J, Ma C, Gui H, Wang S (2021) Thermally-induced error compensation of spindle system based on long short term memory neural networks. Appl Soft Comput 102(2):107094
Lu Y, Liu C, Wang I, Huang H, Xu X (2020) Digital Twin-driven smart manufacturing: Connotation, reference model, applications and research issues. Robot CIM-Int Manuf 61:101837
Ma C, Mei X, Yang J, Zhao L, Shi H (2015a) Thermal characteristics analysis and experimental study on the high-speed spindle system. Int J Adv Manuf Tech 79(1–4):469–489
Ma C, Yang J, Zhao L, Mei X, Shi H (2015b) Simulation and experimental study on the thermally induced deformations of high-speed spindle system. Appl Therm Eng 86:251–268
Ma C, Zhao L, Shi H, Mei X, Yang J (2017a) Experimental and simulation study on the thermal characteristics of the high-speed spindle system. Proc Inst Mech Eng Part C J Mech Eng Sci 231(6):1072–1093
Ma C, Zhao L, Mei X, Shi H, Yang J (2017b) Thermal error compensation of high-speed spindle system based on a modified BP neural network. Int J Adv Manuf Tech 89:3071–3085
Ma C, Zhao L, Mei X, Shi H, Yang J (2017c) Thermal error compensation based on genetic algorithm and artificial neural network of the shaft in the high-speed spindle system. Proc Inst Mech Eng Part B J Eng Manuf 231(5):753–767
Mayr J, Jedrzejewski J, Uhlmann E, Donmez M, Knapp W, Härtig F, Wendt K, Moriwaki T, Shore P, Schmitt R, Brecher C, Würz T, Wegener K (2012) Thermal issues in machine tools. CIRP Ann-Manuf Technol 61(2):771–791
Mayr J, Blaser P, Ryser A, Hernandez-Becerro P (2018) An adaptive self-learning compensation approach for thermal errors on 5-axis machine tools handling an arbitrary set of sample rates. CIRP Ann-Manuf Technol 67(1):551–554
Ramesh R, Mannan MA, Poo AN, Keerthi SS (2003) Thermal error measurement and modelling in machine tools. Part II. Hybrid Bayesian Network—support vector machine model. Int J Mach Tool Manuf 43(4):405–419
Rauf HT, Malik S, Shoaib U, Irfan MN, Lali MI (2020) Adaptive inertia weight Bat algorithm with Sugeno-Function fuzzy search. Appl Soft Comput 90:106159
Rego R, Löpenhaus C, Gomes J, Klocke F (2018) Residual stress interaction on gear manufacturing. J Mater Process Techol 252:249–258
Shukri S, Sayyed R, Hudaib A, Mirjalili S (2021) Enhanced multi-verse optimizer for task scheduling in cloud computing environments. Expert Syst Appl 168:114230
Tao F, Qi Q, Liu A, Kusiak A (2018) Data-driven smart manufacturing. J Manuf Syst 48:157–169
Tao F, Zhang Y, Cheng Y, Ren J, Wang D, Qi Q, Li P (2020) Digital twin and blockchain enhanced smart manufacturing service collaboration and management. J Manuf Syst. https://doi.org/10.1016/j.jmsy.2020.11.008
Wan A, Song L, Xu J, Liu S, Chen K (2018) Calibration and compensation of machine tool volumetric error using a laser tracker. Int J Mach Tool Manuf 124:126–133
Wang P, Luo M (2021) A digital twin-based big data virtual and real fusion learning reference framework supported by industrial internet towards smart manufacturing. J Manuf Syst 58:16–32
Wu D, Xi L, Hebert S, Gentzsch W, Terpenny J (2017) Democratizing digital design and manufacturing using high performance cloud computing: performance evaluation and benchmarking. J Manuf Syst 43:316–326
Xia C, Wang S, Ma C, Wang S, Xiao Y (2019) Crucial geometric error compensation towards gear grinding accuracy enhancement based on simplified actual inverse kinematic model. Int J Mech Sci 169:105319
Xia K, Sacco C, Kirkpatrick M, Saidy C, Harik R (2021a) A digital twin to train deep reinforcement learning agent for smart manufacturing plants: environment, interfaces and intelligence. J Manuf Syst 58:210–230
Xia C, Wang S, Wang S, Ma C, Xu K (2021b) Geometric error identification and compensation for rotary worktable of gear profile grinding machines based on single-axis motion measurement and actual inverse kinematic model. Mech Mach Theory 155:104042
Xiang W, Li F, Wang J, Tang B (2018) Quantum weighted gated recurrent unit neural network and its application in performance degradation trend prediction of rotating machinery. Neurocomputing 313:85–95
Xu X (2012) From cloud computing to cloud manufacturing. Robot CIM-Int Manuf 28(1):75–86
Yang X (2012) Bat algorithm for multi-objective optimisation. Int J Bio-Inspired Comput 3(5):267-274(8)
Yang H, Ni J (2005) Dynamic neural network modeling for nonlinear, nonstationary machine tool thermally induced error. Int J Mach Tool Manuf 45(4–5):455–465
You H, Ye P, Wang J, Deng X (2003) Design and application of CBN shape grinding wheel for gears. Int J Mach Tool Manuf 43(12):1269–1277
Yue X, Zhang H (2020) Modified hybrid bat algorithm with genetic crossover operation and smart inertia weight for multilevel image segmentation. Appl Soft Comput 90:106157
Zhao F, Zhang C, Yang G, Chen C (2016) Online machining error estimation method of numerical control gear grinding machine tool based on data analysis of internal sensors. Mech Syst Signal Process 81:515–526
Zhao D, Bi Y, Ke Y (2018) An efficient error compensation method for coordinated CNC five-axis machine tools. Int J Mach Tool Manuf 123:105–115
Zimmermann N, Lang S, Blaser P, Mayr J (2020) Adaptive input selection for thermal error compensation models. CIRP Ann-Manuf Technol 69(1):485–488
Acknowledgements
This research was supported by the National Natural Science Foundation of China (51905057), the Natural Science Foundation Project of Chongqing, Chongqing Science and Technology Commission (cstc2019jcyj-msxmX0050), the Fundamental Research Funds for the Central Universities (2020CDJQY-A036), the Venture & Innovation Support Program for Chongqing Overseas Returnees (cx2019054), and State Key Laboratory for Manufacturing Systems Engineering (sklms2020016).
Author information
Authors and Affiliations
Corresponding author
Ethics declarations
Conflict of interest
We declare that we have no financial and personal relationships with other people or organizations that can inappropriately influence our work; there is no professional or other personal interest of any nature or kind in any product or company that could be construed as influencing the position presented in, or the review of, the manuscript. Jialan Liu and Hongquan Gui contributed equally to this manuscript.
Additional information
Publisher's Note
Springer Nature remains neutral with regard to jurisdictional claims in published maps and institutional affiliations.
Rights and permissions
About this article
Cite this article
Liu, J., Gui, H. & Ma, C. Digital twin system of thermal error control for a large-size gear profile grinder enabled by gated recurrent unit. J Ambient Intell Human Comput 14, 1269–1295 (2023). https://doi.org/10.1007/s12652-021-03378-4
Received:
Accepted:
Published:
Issue Date:
DOI: https://doi.org/10.1007/s12652-021-03378-4