Data-driven indirect punch wear monitoring in sheet-metal stamping processes

Journal of Intelligent Manufacturing - Trang 1-15 - 2023
Martin Unterberg1, Marco Becker1, Philipp Niemietz1, Thomas Bergs1,2
1Laboratory for Machine Tools and Production Engineering (WZL), RWTH Aachen University, Aachen, Germany
2Fraunhofer Institute for Production Technology IPT, Aachen, Germany

Tóm tắt

The wear state of the punch in sheet-metal stamping processes cannot be directly observed, necessitating the use of indirect methods to infer its condition. Past research approaches utilized a plethora of machine learning models to infer the punch wear state from suitable process signals, but have been limited by the lack of industrial-grade process setups and sample sizes as well as their insufficient interpretability. This work seeks to address these limitations by proposing the sheared surface of the scrap web as a proxy for the punch wear and modeling its quality from acoustic emission signals. The experimental work was carried out in an industrial-grade fine blanking process setting. Evaluation of the model performances suggests that the utilized regression models are capable of modeling the relationship between acoustic emission signal features and sheared surface quality of the scrap webs. Subsequent model inference suggests adhesive wear on the punch as a root cause for the sheared surface impairment of the scrap webs. This work represents the most extensive modeling effort on indirect punch wear monitoring in sheet-metal stamping both from a model prediction and model inference perspective known to the authors.

Tài liệu tham khảo

Asahi, S., Karadogan, C., Tamura, S., Hayamizu, S., & Liewald, M. (2021). Process data based estimation of tool wear on punching machines using TCN-autoencoder from raw time-series information. IOP Conference Series: Materials Science and Engineering, 1157(1), 012078. https://doi.org/10.1088/1757-899X/1157/1/012078

Baccar, D., & Söffker, D. (2015). Wear detection by means of wavelet-based acoustic emission analysis. Mechanical Systems and Signal Processing, 60–61, 198–207. https://doi.org/10.1016/j.ymssp.2015.02.012

Barandas, M., et al. (2020). TSFEL: Time series feature extraction library. SoftwareX, 11, 100456. https://doi.org/10.1016/j.softx.2020.100456

Behrens, B.-A., Bouguecha, A., Vucetic, M., & Chugreev, A. (2016). Advanced wear simulation for bulk metal forming processes. MATEC Web of Conferences, 80, 04003. https://doi.org/10.1051/matecconf/20168004003

Chen, T., & Guestrin, C. (2016). Xgboost: A scalable tree boosting system. In Proceedings of the 22nd ACM SIGKDD international conference on knowledge discovery and data mining (pp. 785–794). ACM. https://doi.org/10.1145/2939672.2939785.

DIN EN 1330-9:2017-10. (2017). Non-destructive testing - terminology - part 9: testing (German version). https://doi.org/10.31030/2607064

Groover, M. (2010). Fundamentals of modern manufacturing: Materials, processes, and systems (4th ed.). Wiley.

Klocke, F. (2014). Manufacturing processes 4: Forming. Springer.

Kollment, W., O’Leary, P., Harker, M., Klünsner, T., & Eck, S. (2018). Force and acoustic emission measurements for condition monitoring of fine blanking tools. In 2018 IEEE international instrumentation and measurement technology conference (pp. 1–6). IEEE. https://doi.org/10.1109/I2MTC.2018.8409569.

Kubik, C., Knauer, S., & Groche, P. (2022). Smart sheet metal forming: importance of data acquisition, preprocessing and transformation on the performance of a multiclass support vector machine for predicting wear states during blanking. Journal of Intelligent Manufacturing, 33(1), 259–282. https://doi.org/10.1007/s10845-021-01789-w

Lundberg, S., et al. (2020). From local explanations to global understanding with explainable AI for trees. Nature Machine Intelligence, 2(1), 56–67. https://doi.org/10.1038/s42256-019-0138-9

Lundberg, S., & Lee, S.-I. (2017). A unified approach to interpreting model predictions. In Proceedings of the 31st international conference on neural information processing systems (pp. 4768–4777). Curran Associates Inc.

Niemietz, P., Kornely, M., Trauth, D., & Bergs, T. (2022). Relating wear stages in sheet metal forming based on short-and long-term force signal variations. Journal of Intelligent Manufacturing, 33(7), 2143–2155. https://doi.org/10.1007/s10845-022-01979-0

Niemietz, P., Unterberg, M., Trauth, D., & Bergs, T. (2021). Autoencoder based wear assessment in sheet metal forming. IOP Conference Series: Materials Science and Engineering, 1157(1), 012082. https://doi.org/10.1088/1757-899X/1157/1/012082

Shanbhag, V., Rolfe, B., & Pereira, M. (2020). Investigation of galling wear using acoustic emission frequency characteristics. Lubricants, 8(3), 25. https://doi.org/10.3390/lubricants8030025

Shwartz-Ziv, R., & Armon, A. (2022). Tabular data: Deep learning is not all you need. Information Fusion, 81, 84–90. https://doi.org/10.1016/j.inffus.2021.11.011

Tibshirani, R. (1996). Regression shrinkage and selection via the lasso. Journal of the Royal Statistical Society, Series B, 58(1), 267–288. https://doi.org/10.1111/j.2517-6161.1996.tb02080.x

Unterberg, M., et al. (2021). Wear monitoring in fine blanking processes using feature based analysis of acoustic emission signals. Procedia CIRP, 104, 164–169. https://doi.org/10.1016/j.procir.2021.11.028

Voigts, H. O. (2021). Feinschneiden mit Hartmetallstempeln: Fine blanking with cemented carbide punches. Apprimus.

XGBoost parameters: xgboost 1.7.2 documentation. Retrieved January 4, 2023, from https://xgboost.readthedocs.io/en/stable/parameter.html

Yeh, C.-C. M., et al. (2016). Matrix profile I: All pairs similarity joins for time series: A unifying view that includes motifs, discords and shapelets. In 2016 IEEE 16th international conference on data mining (pp. 1317–1322). IEEE. https://doi.org/10.1109/ICDM.2016.0179.

Thông tin
Thông tin xuất bản

Journal of Intelligent Manufacturing

1-15

Thông tin tác giả