Abstract
Uncontrolled environmental conditions often impact manufacturing processes and lead to product quality fluctuations. For machine tools, thermal influences are a major limitation to the volumetric performance. Climate controls for the shop floor, and machines, or thermally stable structural designs are economically not feasible, promoting control-based compensation as a possible solution. Since the relationship between disturbing quantities and effects are complex and specific to each machine, appropriate modelling is a critical requirement. The authors describe an approach for developing hybrid models, superposing white-box model knowledge, and machine learning. The overall effort can be optimized by combining and balancing different modelling methods, like designing the physical model part and training intelligent algorithms. A general model structure allows a continuous integration of different white-box and black-box model components. The authors integrate self-developed smart sensors into a demonstrator machine tool to test and validate the performance of the approach.
Zusammenfassung
Unregulierte Umgebungszustände beeinflussen Fertigungsprozesse oftmals negativ und führen zu Qualitätsschwankungen in Prozesserzeugnissen. Im Falle von Werkzeugmaschinen sind thermische Verlagerungen für einen kritischen Anteil des gesamtvolumetrischen Fehlers verantwortlich. Eine vollständige Vermeidung thermischer Einflüsse oder eine Desensibilisierung von Maschinen darauf durch rein konstruktive Maßnahmen sind wirtschaftlich nicht umsetzbar. Eine steuerungstechnische Kompensation dieser Störeinflüsse hingegen kann dieses Defizit ausgleichen. Aufgrund komplexer und maschinenspezifischer Wirkzusammenhänge ist eine effiziente Modellbildung essenziell. Die Autoren beschreiben einen Ansatz für eine hybride Modellbildung, bei der White-Box-Wissen und maschinelles Lernen sich gegenseitig ergänzen. Durch die Kombination und Anwendung verschiedener Modellansätze, wie dem Erstellen physikalisch motivierter Modellanteile oder dem Training selbstlernender Algorithmen, kann der Gesamtmodellierungsaufwand optimiert werden. Eine generalisierte Modellstruktur erlaubt die kontinuierliche Integration verschiedener White-Box und Black-Box Modellkomponenten. Die Autoren integrieren selbstentwickelte Smart-Sensors in eine Demonstratormaschine um den beschriebenen Ansatz zu validieren.
Funding source: Deutsche Forschungsgemeinschaft
Award Identifier / Grant number: 1856/74-1
Award Identifier / Grant number: EXC-2023
Award Identifier / Grant number: 390621612
Funding statement: Funded by the Deutsche Forschungsgemeinschaft (DFG, German Research Foundation) under 1856/74-1 and Germany’s Excellence Strategy – EXC-2023 Internet of Production – 390621612.
About the authors
Brief Biographical History:
2016 – Degree in Mechanical Engineering (M. Sc. RWTH)
2016 – Research Associate at the Laboratory for Machine Tools and Production Engineering (WZL | RWTH)
2018 – Team Leader for Large-Scale Metrology
“Enhancing laser step diagonal measurement by multiple sensors for fast machine tool calibration” Journal of Machine Engineering, 2018, Vol. 18, No. 2, 64–73
„Fast Machine Tool Calibration using a single Laser Tracker“ Laser Metrology and Machine Performance XIII 2019
Brief Biographical History:
2018 – Degree in Mechanical Engineering (M. Sc. RWTH)
2018 – Research Associate at the Laboratory for Machine Tools and Production Engineering (WZL | RWTH)
Brief Biographical History:
2017 – Master’s degree in mechanical engineering – LabMetro/UFSC
2018 – PhD candidate at Federal University of Santa Catarina, Brazil (LabMetro/UFSC)
2019 – Researcher at Institute SENAI of Innovation – Embedded Systems
“Defect classification in shearography images using convolutional neural networks” In: 2018 International Joint Conference on Neural Networks (IJCNN), 2018, Rio de Janeiro. 2018 International Joint Conference on Neural Networks (IJCNN), 2018. p. 1
“Impact damage characterization in CFRP plates using PCA and MEEMD decomposition methods in optical lock-in thermography phase images”. In: Optical Measurement Systems for Industrial Inspection XI, 2019, Munich. Optical Measurement Systems for Industrial Inspection XI, 2019. v. XI. p. 93.
Brief Biographical History:
1989 – Degree in Electrical Engineering (RWTH)
1997 – Joined MAN Nutzfahrzeuge AG, various leading positions
2004 – Professor, Chair for Production Metrology and Quality Management (WZL | RWTH Aachen)
2005 – Board of Directors, Fraunhofer Institute for Production Technology (IPT)
“Advances in Large-Scale Metrology – Review and future trends“, CIRP Annals, 2016, Vol. 65, No. 2, 643–665
“Sensor information as a service – component of networked production”, J. Sens. Sens. Syst., 2018, Vol. 7, 389–402
International Academy for Production Engineering (CIRP)
Institute of Electrical and Electronics Engineering (IEEE)
German Association for Quality (DGQ)
References
1. Schmitt R, Peterek M (2015) Traceable Measurements on Machine Tools – Thermal Influences on Machine Tool Structure and Measurement Uncertainty. Procedia CIRP 33:576–80.10.1016/j.procir.2015.06.087Search in Google Scholar
2. Lin Y, Shen Y (2003) Modelling of Five-Axis Machine Tool Metrology Models Using the Matrix Summation Approach. Int J Adv Manuf Technol 21(4):243–8.10.1007/s001700300028Search in Google Scholar
3. Okafor AC, Ertekin YM (2000) Derivation of machine tool error models and error compensation procedure for three axes vertical machining center using rigid body kinematics. International Journal of Machine Tools and Manufacture 40(8):1199–213.10.1016/S0890-6955(99)00105-4Search in Google Scholar
4. ISO (2012) Test code for machine tools – Part 1: Geometric accuracy of machines operating under no-load or quasi-static conditions (230-1:2012). 3rd ed.Search in Google Scholar
5. Kreng VB, Liu CR, Chu CN (1994) A kinematic model for machine tool accuracy characterisation. Int J Adv Manuf Technol 9(2):79–86.10.1007/BF01750414Search in Google Scholar
6. Donmez MA, Blomquist DS, Hocken RJ, Liu CR, Barash MM (1986) A general methodology for machine tool accuracy enhancement by error compensation. Precision Engineering 8(4):187–96.10.1016/0141-6359(86)90059-0Search in Google Scholar
7. Abbé E (1890) Messapparate für physiker. Zeitschrift für Instrumentenkunde 10:446–7.Search in Google Scholar
8. Bryan JB (1979) The Abbé principle revisited: An updated interpretation.10.1016/0141-6359(79)90037-0Search in Google Scholar
9. Mayr J (2010) Beurteilung und Kompensation des Temperaturgangs von Werkzeugmaschinen. Zugl.: Zürich, Eidgenöss. Techn. Hochsch., Diss., 2009. VDI-Verl., Düsseldorf.Search in Google Scholar
10. Spur G, Fischer H (1970) Thermal Behaviour of Machine Tools. Advances in Machine Tool Design and Research 1969. Elsevier, pp. 147–60.10.1016/B978-0-08-015661-3.50013-8Search in Google Scholar
11. Bryan J (1990) International Status of Thermal Error Research (1990). CIRP Annals 39(2):645–56.10.1016/S0007-8506(07)63001-7Search in Google Scholar
12. 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 Annals – Manufacturing Technology 61:771–91.10.1016/j.cirp.2012.05.008Search in Google Scholar
13. Nelle G (1987) Length measuring apparatus with temperature compensation. Dr Johannes Heidenhain GmbH.Search in Google Scholar
14. Wennemer M (2018) Methode zur messtechnischen Analyse und Charakterisierung volumetrischer thermo-elastischer Verlagerungen von Werkzeugmaschinen. 1st ed. Apprimus Wissenschaftsverlag, Aachen.Search in Google Scholar
15. Ziegert JC, Kalle P (1994) Error compensation in machine tools: A neural network approach. J Intell Manuf 5(3):143–51.10.1007/BF00123919Search in Google Scholar
16. Weck M, McKeown P, Bonse R, Herbst U (1995) Reduction and Compensation of Thermal Errors in Machine Tools. CIRP Annals 44(2):589–98.10.1016/S0007-8506(07)60506-XSearch in Google Scholar
17. Chen J-S (1996) Neural network-based modelling and error compensation of thermally-induced spindle errors. Int J Adv Manuf Technol 12(4):303–8.10.1007/BF01239617Search in Google Scholar
18. Zhang X, Yang L, Lou P, Jiang X, Li Z (2019) Thermal Error Modeling for Heavy Duty CNC Machine Tool Based on Convolution Neural Network. 2019 IEEE 3rd Information Technology, Networking, Electronic and Automation Control Conference (ITNEC). IEEE, pp. 665–9.10.1109/ITNEC.2019.8728998Search in Google Scholar
19. Chen T-C, Chang C-J, Hung J-P, Lee R-M, Wang C-C (2016) Real-Time Compensation for Thermal Errors of the Milling Machine. Applied Sciences 6(4):101.10.3390/app6040101Search in Google Scholar
20. Maekawa S (2018) Machine learning device for machine tool and thermal displacement compensation device. FANUC Corp.Search in Google Scholar
21. Hada K, Iijima K (2018) Thermal Displacement Compensation System. FANUC CORP (20190099849).Search in Google Scholar
22. Mourtzis D, Vlachou E, Milas N, Xanthopoulos N (2016) A Cloud-based Approach for Maintenance of Machine Tools and Equipment Based on Shop-floor Monitoring. Procedia CIRP 41:655–60.10.1016/j.procir.2015.12.069Search in Google Scholar
23. Brecher C, Klocke F, Schmitt R, Schuh G, (Eds.) (2017) Internet of Production für agile Unternehmen: AWK Aachener Werkzeugmaschinen-Kolloquium 2017, 18. bis 19 Mai. 1st ed. Apprimus Verlag, Aachen.Search in Google Scholar
24. Ibaraki S, Knapp W (2012) Indirect Measurement of Volumetric Accuracy for Three-Axis and Five-Axis Machine Tools: A Review. ETH Zurich.10.20965/ijat.2012.p0110Search in Google Scholar
25. Schwenke H, Knapp W, Haitjema H, Weckenmann A, Schmitt R, Delbressine F (2008) Geometric error measurement and compensation of machines – An update. CIRP Annals 57(2):660–75.10.1016/j.cirp.2008.09.008Search in Google Scholar
26. Montavon B, Dahlem P, Schmitt R (2019) Fast Machine Tool Calibration using a Single Laser Tracker.Search in Google Scholar
27. Mutilba U, Gomez-Acedo E, Kortaberria G, Olarra A, Yagüe-Fabra JA (2017) Traceability of On-Machine Tool Measurement: A Review. Sensors (Basel, Switzerland) 17(7).10.3390/s17071605Search in Google Scholar PubMed PubMed Central
28. Chen Y-T, Lin W-C, Liu C-S (2017) Design and experimental verification of novel six-degree-of freedom geometric error measurement system for linear stage. Optics and Lasers in Engineering 92:94–104.10.1016/j.optlaseng.2016.10.026Search in Google Scholar
29. Gao Z, Hu J, Zhu Y, Duan G (2013) A new 6-degree-of-freedom measurement method of X-Y stages based on additional information. Precision Engineering 37(3):606–20.10.1016/j.precisioneng.2013.01.006Search in Google Scholar
30. Li X, Gao W, Muto H, Shimizu Y, Ito S, Dian S (2013) A six-degree-of-freedom surface encoder for precision positioning of a planar motion stage. Precision Engineering 37(3):771–81.10.1016/j.precisioneng.2013.03.005Search in Google Scholar
31. Montavon B, Dahlem P (2018) Modelling Machine Tools using Structure Integrated Sensors for Fast Calibration. JMMP 2:14.10.3390/jmmp2010014Search in Google Scholar
32. Potdar A (2015) Application of multi sensor data fusion based on Principal Component Analysis and Artificial Neural Network for machine tool thermal monitoring. Unpublished.Search in Google Scholar
33. Baum C, Brecher C, Klatte M, Lee TH, Tzanetos F (2018) Thermally induced volumetric error compensation by means of integral deformation sensors. Procedia CIRP 72:1148–53.10.1016/j.procir.2018.03.045Search in Google Scholar
34. Szipka K, Archenti A, Vogl GW, Donmez MA (2019) Identification of machine tool squareness errors via inertial measurements. CIRP Annals 68(1):547–50.10.1016/j.cirp.2019.04.070Search in Google Scholar PubMed PubMed Central
35. Vogl GW, Donmez MA, Archenti A (2016) Diagnostics for geometric performance of machine tool linear axes. CIRP Annals 65(1):377–80.10.1016/j.cirp.2016.04.117Search in Google Scholar PubMed PubMed Central
36. VDW German Machine Tool Builder’s Association All major control suppliers support umati.Search in Google Scholar
37. Ohlenforst M, Jantzen M, Schmitt RH (2018) Verfahren und System zur in-process-Berechnung einer dreidimensionalen Temperaturverteilung. Rheinisch-Westfälische Technische Hochschule (RWTH) Aachen.Search in Google Scholar
38. Zech M, Thurner K (2015) Interferometric Displacement Sensor For Integration Into Machine Tools And Semiconductor Lithography Systems. ATTOCUBE SYSTEMS AG(WO/2015/165587).Search in Google Scholar
39. Siemens Funktionsbeschreibung VCS “Volumetric Compensation System”.Search in Google Scholar
40. Flore J (2016) Optimierung der Genauigkeit fünfachsiger Werkzeugmaschinen. 1st ed. Apprimus Wissenschaftsverlag, Aachen.Search in Google Scholar
41. Reitermanová Z (2010) Data Splitting. in Šafránková J (Ed.). 19th Annual Conference of Doctoral Students, WDS’10 “Week of Doctoral Students 2010”, Charles University, Faculty of Mathematics and Physics, Prague, Czech Republic, June 1, 2010 to June 4, 2010: [proceedings of contributed papers]. Matfyzpress, Praha, pp. 31–6.Search in Google Scholar
42. Picard RR, Cook RD (1984) Cross-Validation of Regression Models. Journal of the American Statistical Association 79(387):575–83.10.1080/01621459.1984.10478083Search in Google Scholar
43. Claesen M, Moor BD (2015) Hyperparameter Search in Machine Learning. CoRR abs/1502.02127.Search in Google Scholar
44. Stone M (1974) Cross-Validatory Choice and Assessment of Statistical Predictions. Journal of the Royal Statistical Society. Series B (Methodological) 36(2):111–47.10.1111/j.2517-6161.1974.tb00994.xSearch in Google Scholar
45. Arlot S, Celisse A (2010) A survey of cross-validation procedures for model selection. Statist Surv 4:40–79.10.1214/09-SS054Search in Google Scholar
46. Pedregosa F, Varoquaux G, Gramfort A, Michel V, Thirion B, Grisel O, Blondel M, Prettenhofer P, Weiss R, Dubourg V, Vanderplas J, Passos A, Cournapeau D, Brucher M, Perrot M, Duchesnay E (2011) Scikit-learn: Machine Learning in Python. Journal of Machine Learning Research 12:2825–30.Search in Google Scholar
47. Buitinck L, Louppe G, Blondel M, Pedregosa F, Mueller A, Grisel O, Niculae V, Prettenhofer P, Gramfort A, Grobler J, Layton R, VanderPlas J, Joly A, Holt B, Varoquaux G (2013) API design for machine learning software: Experiences from the scikit-learn project. ECML PKDD Workshop: Languages for Data Mining and Machine Learning, pp. 108–22.Search in Google Scholar
48. Altman NS (1992) An Introduction to Kernel and Nearest-Neighbor Nonparametric Regression. The American Statistician 46(3):175–85.Search in Google Scholar
49. Chen GH, Shah D (2017) Explaining the Success of Nearest Neighbor Methods in Prediction. FNT in Machine Learning 10(5–6):337–588.10.1561/9781680834550Search in Google Scholar
© 2020 Walter de Gruyter GmbH, Berlin/Boston
