Fast Automatized Parameter Adaption Process of CNC Milling Machines Under the Use of Perception Based Artificial Intelligence

S. Feldmann, M. Schmiedt, J. Jung, J. M. Schlosser, T. Stempfle, C. Rathmann, W. Rimkus

Abstract


This paper concerns unpublished results obtained from the SIMKI (2020) R&D project at the Department of Mechanical Engineering at Aalen University of Applied Science, Germany. The following text generally discusses the development results of the AI- based CNC parameter identification and optimisation tool AICNC. The identification tool supports the AI-based optimisation of milling machine process parameters when using unknown material compositions. The process parameters are determined by a specific test pattern designed to be automatically analysed in real-time by a pre- trained perception-based deep learning algorithm. The tool provides the advantage of obtaining real-time quality information due to AI- based quality assessment and the automated identification of material- dependent milling process parameter sets, even for unknown processing material.

Keywords


Artificial Intelligence · CNC-Milling · Image Processing · Parameter Prediction · Process Optimisation

References


Sáenz de Argandona E., Aztiria A., Garcia C., AranaN., Izaguirre A., Fillatreau P. ’Forming processes control by means of artificial intelligence techniques’. Journal of Robotics and Computer-Integrated Manufacturing,2008, doi: 10.1016/j.rcim.2008.03.014.

Europäische Kommission, ’Mitteilung der Kommission an das Europäische Parlament, den Europäischen Rat, den Europäischen Wirtschafts- und Sozialausschuss und den Ausschuss der Regionen: Green Deal der Europäischen Union’, Brüssel, 2019.

Romano P., ’European Manufacture of the Future, role of research and education for E European leadership’, MANUFUTURE 2003 Conference, Italy, 2003.

Schlosser J. M., Schneider R., Rimkus W., Kelsch R., Gerstner F., Harrison D. K., Grant R. J., ’Material and simulation modelling of a crash beam performance – a comparison study showing the potential for weight savings using warm-formed ultra-high strength aluminium alloys’, Journal of Physics, 2017, Vol. 896, pp. 12091, DOI 10.1088/17426596/896/1/012091

Feldmann S., Kempter G., Esslinger R., Tran H. T., ’Support of Image- Based Quality Assessment in Discrete Production Scenarios through AI- Based Decision Support’, 13th International Conference on Advancements in Computational Sciences, ICACTE, 2020, ISBN: 978-1- 4503-7732-4

Iandola F. N., Han S., Moskewicz M. W., Ashraf K., Dally W. J., Keutzer K., ’SqueezeNet: AlexNet-level accuracy with 50x fewer parameters and ¡0.5MB model size, 2016, arXiv:1602.07

[Online]. Available at: https://www.wirtschaft-digital-bw.de/ki-made-in- bw/innovationswettbewerb-ki-fuer-kmu/simki-echtzeitdatenerfassung- und-parameterkorrektur, 2020

8. [Online] x-technik IT und Medien GmbH, ’DMU 65 monoBLOCK CNC universal milling machine’. [Online]. Available at: https: // https://www.zerspanungstechnik.com/bericht/horizontal- bearbeitungszentren/dmu-65-h-monoblock_mit-bearbeitungszentrum- maximal-flexibel-in-der-massenproduktion_2022-01-01, accessed in November 2022.

Hoffmann Group, Fraunhofer-Institut für Werkzeugmaschinen und Umformtechnik, ’Zerspanungshandbuch: Bohren, Gewinde, Senken, Reiben, Sägen, Fräsen, Drehen, Spanen, Präzisions-schleifen’, 2. Aufl. München: Hoffmann Group, 2014, ISBN: 3-00-016882-6

Landola, Forrest N., et al. "SqueezeNet: AlexNet-level accuracy with 50x fewer parameters and 0.5 MB model size." arXiv preprint arXiv:1602.07360 (2016).

Kingma, Diederik P., and Jimmy Ba. "Adam: A method for stochastic optimisation." arXiv preprint arXiv:1412.6980 (2014).

Rong W., Li Z., Zhang W., Sun L., An improved Canny edge detection algorithm, IEEE International Conference on Mechatronics and Automation, 2016, doi: 10.1109/ICMA.2014.6885761

Russakovsky, O., Deng, J., Su, H., et al. ’ImageNet LargeScale Visual Recognition Challenge’, International Journal of Computer Vision (IJCV). Vol 115, Issue 3, 2015, arXiv:1409.0575v3

Feldmann, M. Schmiedt, J. M. Schlosser, W. Rimkus, T. Stempfle, C. Rathmann, ’Recursive quality optimisation of a smart forming tool under the use of perception-based hybrid datasets for training of a Deep Neural Network’, Journal of Discover Artificial Intelligence, 2022, doi: 10.1007/s44163-022-00034-4


Full Text: PDF

Refbacks

  • There are currently no refbacks.


Creative Commons License
This work is licensed under a Creative Commons Attribution 3.0 License.

IT in Innovation IT in Business IT in Engineering IT in Health IT in Science IT in Design IT in Fashion

IT in Industry @ http://www.it-in-industry.com . ISSN (Online): 2203-1731; ISSN (Print): 2204-0595