{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,8,8]],"date-time":"2026-08-08T18:38:22Z","timestamp":1786214302715,"version":"3.56.0"},"reference-count":47,"publisher":"MDPI AG","issue":"20","license":[{"start":{"date-parts":[[2023,10,17]],"date-time":"2023-10-17T00:00:00Z","timestamp":1697500800000},"content-version":"vor","delay-in-days":0,"URL":"https:\/\/creativecommons.org\/licenses\/by\/4.0\/"}],"funder":[{"DOI":"10.13039\/501100002347","name":"German Federal Ministry of Education and Research","doi-asserted-by":"publisher","award":["16ME0076"],"award-info":[{"award-number":["16ME0076"]}],"id":[{"id":"10.13039\/501100002347","id-type":"DOI","asserted-by":"publisher"}]}],"content-domain":{"domain":[],"crossmark-restriction":false},"short-container-title":["Sensors"],"abstract":"<jats:p>The increasing demand for customized products is a core driver of novel automation concepts in Industry 4.0. For the case of machining complex free-form workpieces, e.g., in die making and mold making, individualized manufacturing is already the industrial practice. The varying process conditions and demanding machining processes lead to a high relevance of machining domain experts and a low degree of manufacturing flow automation. In order to increase the degree of automation, online process monitoring and the prediction of the quality-related remaining cutting tool life is indispensable. However, the varying process conditions complicate this as the correlation between the sensor signals and tool condition is not directly apparent. Furthermore, machine learning (ML) knowledge is limited on the shop floor, preventing a manual adaption of the models to changing conditions. Therefore, this paper introduces a new method for remaining tool life prediction in individualized production using automated machine learning (AutoML). The method enables the incorporation of machining expert knowledge via the model inputs and outputs. It automatically creates end-to-end ML pipelines based on optimized ensembles of regression and forecasting models. An explainability algorithm visualizes the relevance of the model inputs for the decision making. The method is analyzed and compared to a manual state-of-the-art approach for series production in a comprehensive evaluation using a new milling dataset. The dataset represents gradual tool wear under changing workpieces and process parameters. Our AutoML method outperforms the state-of-the-art approach and the evaluation indicates that a transfer of methods designed for series production to variable process conditions is not easily possible. Overall, the new method optimizes individualized production economically and in terms of resources. Machining experts with limited ML knowledge can leverage their domain knowledge to develop, validate and adapt tool life models.<\/jats:p>","DOI":"10.3390\/s23208523","type":"journal-article","created":{"date-parts":[[2023,10,17]],"date-time":"2023-10-17T08:25:09Z","timestamp":1697531109000},"page":"8523","update-policy":"https:\/\/doi.org\/10.3390\/mdpi_crossmark_policy","source":"Crossref","is-referenced-by-count":11,"title":["Explainable Remaining Tool Life Prediction for Individualized Production Using Automated Machine Learning"],"prefix":"10.3390","volume":"23","author":[{"ORCID":"https:\/\/orcid.org\/0000-0002-2559-6651","authenticated-orcid":false,"given":"Lukas","family":"Krupp","sequence":"first","affiliation":[{"name":"Fraunhofer Institute for Microelectronic Circuits and Systems, 47057 Duisburg, Germany"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0000-0002-2511-4659","authenticated-orcid":false,"given":"Christian","family":"Wiede","sequence":"additional","affiliation":[{"name":"Fraunhofer Institute for Microelectronic Circuits and Systems, 47057 Duisburg, Germany"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Joachim","family":"Friedhoff","sequence":"additional","affiliation":[{"name":"CAX Technologies, University of Applied Sciences Ruhr West, 45407 M\u00fclheim an der Ruhr, Germany"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0000-0002-4882-4223","authenticated-orcid":false,"given":"Anton","family":"Grabmaier","sequence":"additional","affiliation":[{"name":"Fraunhofer Institute for Microelectronic Circuits and Systems, 47057 Duisburg, Germany"},{"name":"Department of Electronic Components and Circuits, University of Duisburg-Essen, 47057 Duisburg, Germany"}],"role":[{"vocabulary":"crossref","role":"author"}]}],"member":"1968","published-online":{"date-parts":[[2023,10,17]]},"reference":[{"key":"ref_1","unstructured":"Boos, W., Kelzenberg, C., Pr\u00fcmmer, M., Goertz, D., Boshof, J., Horstkotte, R., Ochel, T., and L\u00fcrken, C. (2020). Tooling in Germany 2020, WZL of RWTH Aachen, Fraunhofer IPT."},{"key":"ref_2","unstructured":"Boos, W., Arntz, K., Johannsen, L., Pr\u00fcmmer, M., Horstkotte, R., Ganser, P., Venek, T., and Gerretz, V. (2018). Erfolgreich Fr\u00e4sen im Werkzeugbau, Fraunhofer IPT, WBA Aachener Werkzeubau Akademie."},{"key":"ref_3","unstructured":"Davim, J.P. (2008). Machining\u2014Fundamentals and Recent Advances, Springer."},{"key":"ref_4","doi-asserted-by":"crossref","first-page":"539","DOI":"10.1016\/j.procir.2016.11.093","article-title":"Intelligent Tools for Predictive Process Control","volume":"57","author":"Nguyen","year":"2016","journal-title":"Procedia CIRP"},{"key":"ref_5","doi-asserted-by":"crossref","first-page":"79","DOI":"10.1016\/j.promfg.2020.11.015","article-title":"Fundamental investigation on the correlation between surface properties and acceleration data from a sensor integrated milling tool","volume":"52","author":"Eschelbacher","year":"2020","journal-title":"Procedia Manuf."},{"key":"ref_6","doi-asserted-by":"crossref","unstructured":"Denkena, B., Dittrich, M.-A., Lindauer, M., Mainka, J., and St\u00fcrenburg, L. (2020, January 1\u20132). Using AutoML to Optimize Shape Error Prediction in Milling Processes. Proceedings of the 2020 Machining Innovations Conference (2020), Online.","DOI":"10.2139\/ssrn.3724234"},{"key":"ref_7","doi-asserted-by":"crossref","unstructured":"Mohamed, A., Hassan, M., M\u2019Saoubi, R., and Attia, H. (2022). Tool Condition Monitoring for High-Performance Machining Systems-A Review. Sensors, 22.","DOI":"10.3390\/s22062206"},{"key":"ref_8","first-page":"2683","article-title":"Data-Driven Remaining Useful Life Estimation for Milling Process: Sensors, Algorithms, Datasets, and Future Directions","volume":"115","author":"Sayyad","year":"2021","journal-title":"Int. J. Adv. Manuf. Technol."},{"key":"ref_9","doi-asserted-by":"crossref","first-page":"471","DOI":"10.1007\/s00170-014-6013-2","article-title":"Condition-based tool management for small batch production","volume":"74","author":"Denkena","year":"2014","journal-title":"Int. J. Adv. Manuf. Technol."},{"key":"ref_10","unstructured":"Arntz, C., Brandst\u00e4tter, T.C., Dori\u00dfen, J., Frye, M., Krau\u00df, J., Krebs, L., Holst, C., Horstkotte, R., Mende, H., and Schiller, S. (2021). K\u00fcnstliche Intelligenz in der Einzel- und Kleinserienfertigung, Fraunhofer IPT."},{"key":"ref_11","doi-asserted-by":"crossref","unstructured":"Wang, W., Wang, B., Li, N., Lei, Y., and Yan, T. (2021, January 13\u201315). Remaining Useful Life Prediction Based on Multi-channel Attention Bidirectional Long Short-term Memory Network. Proceedings of the 2021 IEEE International Conference on Sensing, Diagnostics, Prognostics, and Control (2021), Weihai, China.","DOI":"10.1109\/SDPC52933.2021.9563596"},{"key":"ref_12","doi-asserted-by":"crossref","first-page":"101924","DOI":"10.1016\/j.rcim.2019.101924","article-title":"In-process tool condition forecasting based on a deep learning method","volume":"64","author":"Sun","year":"2020","journal-title":"Robot.-Comput.-Integr. Manuf."},{"key":"ref_13","unstructured":"Davim, J.P. (2008). Machining\u2014Fundamentals and Recent Advances, Springer."},{"key":"ref_14","unstructured":"Mebrahitom, A.G., Seow, X.Y., Azmir, A., and Tamiru, A.L. (2017, January 3\u20139). Remaining Tool Life Prediction Based on Force Sensors Signal During End Milling of Stavax ESR Steel. Proceedings of the International Mechanical Engineering Congress and Exposition (2017), Tampa, FL, USA."},{"key":"ref_15","doi-asserted-by":"crossref","first-page":"442","DOI":"10.1007\/s42452-021-04427-5","article-title":"Recurrent Neural Networks with Long Term Temporal Dependencies in Machine Tool Wear Diagnosis and Prognosis","volume":"3","author":"Zhang","year":"2021","journal-title":"SN Appl. Sci."},{"key":"ref_16","doi-asserted-by":"crossref","first-page":"161","DOI":"10.1016\/j.jmapro.2016.03.010","article-title":"Tool Life Predictions in Milling using Spindle Power with the Neural Network Technique","volume":"22","author":"Drouillet","year":"2016","journal-title":"J. Manuf. Process."},{"key":"ref_17","doi-asserted-by":"crossref","first-page":"107461","DOI":"10.1016\/j.measurement.2019.107461","article-title":"A Data-driven Model for Milling Tool Remaining Useful Life Prediction with Convolutional and Stacked LSTM Network","volume":"154","author":"An","year":"2020","journal-title":"Measurement"},{"key":"ref_18","first-page":"110255","article-title":"A Review on Deep Learning in Machining and Tool Monitoring: Methods, Opportunities, and Challenges","volume":"9","author":"Nasir","year":"2021","journal-title":"IEEE Access"},{"key":"ref_19","doi-asserted-by":"crossref","first-page":"3583","DOI":"10.1007\/s00170-022-09417-4","article-title":"A Hybrid Remaining Useful Life Prediction Method for Cutting Tool considering the Wear State","volume":"121","author":"Li","year":"2022","journal-title":"Int. J. Adv. Manuf. Technol."},{"key":"ref_20","doi-asserted-by":"crossref","first-page":"5199","DOI":"10.1109\/TII.2021.3118994","article-title":"Online Remaining Useful Life Prediction of Milling Cutters Based on Multisource Data and Feature Learning","volume":"18","author":"Guo","year":"2022","journal-title":"IEEE Trans. Ind. Inform."},{"key":"ref_21","doi-asserted-by":"crossref","first-page":"2565","DOI":"10.1007\/s00170-022-09396-6","article-title":"Prediction of Tool Wear in Sculpture Surface by a new Fusion Method of Temporal Convolutional Network and Self-Attention","volume":"121","author":"Jia","year":"2022","journal-title":"Int. J. Adv. Manuf. Technol."},{"key":"ref_22","doi-asserted-by":"crossref","unstructured":"Liu, Y., Hu, X., and Jin, J. (2019, January 23\u201325). Remaining Useful Life Prediction of Cutting Tools based on Deep Adversarial Transfer Learning. Proceedings of the 2019 8th International Conference on Computing and Pattern Recognition (2019), Beijing China.","DOI":"10.1145\/3373509.3373543"},{"key":"ref_23","unstructured":"Li, X., Lim, B.S., Zhou, J.H., Huang, S., Phua, S.J., Shaw, K.C., and Er, M.J. (October, January 27). Fuzzy Neural Network Modelling for Tool Wear Estimation in Dry Milling Operation. Proceedings of the Annual Conference of the PHM Society (2009), San Diego, CA, USA."},{"key":"ref_24","unstructured":"Goebel, K. (1996). Management of Uncertainty for Sensor Validation, Sensor Fusion and Diagnosis in Sensor Driven Mechanical Systems Using Soft Computing Techniques, UC Berkeley."},{"key":"ref_25","doi-asserted-by":"crossref","first-page":"4715","DOI":"10.1007\/s00170-019-04349-y","article-title":"Tool Remaining Useful Life Prediction Method based on LSTM under Variable Working Conditions","volume":"104","author":"Zhou","year":"2019","journal-title":"Int. J. Adv. Manuf. Technol."},{"key":"ref_26","doi-asserted-by":"crossref","first-page":"JAMDSM0025","DOI":"10.1299\/jamdsm.2023jamdsm0025","article-title":"Tool Life Prediction in End Milling using a Combination of Machining Simulation and Tool Wear Progress Data","volume":"17","author":"Matsumura","year":"2023","journal-title":"J. Adv. Mech. Des. Syst. Manuf."},{"key":"ref_27","doi-asserted-by":"crossref","first-page":"465","DOI":"10.1007\/s11740-021-01086-8","article-title":"Tool Wear and Remaining Useful Life (RUL) Prediction based on Reduced Feature Set and Bayesian Hyperparameter Optimization","volume":"16","author":"Zegarra","year":"2022","journal-title":"Prod. Eng."},{"key":"ref_28","doi-asserted-by":"crossref","first-page":"215","DOI":"10.1016\/j.promfg.2020.10.031","article-title":"Benchmark of Automated Machine Learning with State-of-the-Art Image Segmentation Algorithms for Tool Condition Monitoring","volume":"51","author":"Lutz","year":"2020","journal-title":"Procedia Manuf."},{"key":"ref_29","doi-asserted-by":"crossref","first-page":"401","DOI":"10.1016\/j.procir.2020.04.009","article-title":"Streamlining the development of data-driven industrial applications by automated machine learning","volume":"93","author":"Mayr","year":"2020","journal-title":"Procedia CIRP"},{"key":"ref_30","doi-asserted-by":"crossref","unstructured":"Schmetz, A., Vahl, C., Zhen, Z., Reibert, D., Mayer, S., Zontar, D., Garcke, J., and Brecher, C. (2021, January 13\u201316). Decision Support by Interpretable Machine Learning in Acoustic Emission Based Cutting Tool Wear Prediction. Proceedings of the 2021 IEEE International Conference on Industrial Engineering and Engineering Management (2021), Singapore.","DOI":"10.1109\/IEEM50564.2021.9673044"},{"key":"ref_31","unstructured":"Sotubadi, S.V., Liu, R., and Nguyen, V. (2023, January 12\u201316). Explainable AI for Tool Wear Prediction in Turning. Proceedings of the ASME 2023 18th International Manufacturing Science and Engineering Conference (2023), New Brunswick, NJ, USA."},{"key":"ref_32","doi-asserted-by":"crossref","first-page":"17","DOI":"10.1016\/j.jmsy.2021.10.013","article-title":"Physics-informed Meta Learning for Machining Tool Wear Prediction","volume":"62","author":"Li","year":"2022","journal-title":"J. Manuf. Syst."},{"key":"ref_33","doi-asserted-by":"crossref","first-page":"298","DOI":"10.1016\/j.jmsy.2020.09.005","article-title":"Physics Guided Neural Network for Machining Tool Wear Prediction","volume":"57","author":"Wang","year":"2020","journal-title":"J. Manuf. Syst."},{"key":"ref_34","unstructured":"Schaefer, C. (2013). Signaltechnische Voraussetzungen und Analyseverfahren zur \u00dcberwachung von Pr\u00e4zisions- und Ultrapr\u00e4zisionsbearbeitungsverfahren, WZL of RWTH Aachen."},{"key":"ref_35","doi-asserted-by":"crossref","first-page":"491","DOI":"10.1504\/IJCAET.2018.094343","article-title":"Removed Material Volume Calculations in CNC Milling by Exploiting CAD Functionality","volume":"10","author":"Benardos","year":"2017","journal-title":"Int. J. Comput. Aided Eng. Technol."},{"key":"ref_36","unstructured":"Feurer, M., Klein, A., Eggensperger, K., Springenberg, J.T., Blum, M., and Hutter, F. (2015, January 7\u201312). Efficient and Robust Automated Machine Learning. Proceedings of the 28th International Conference on Neural Information Processing Systems (2015), Montreal, QC, Canada."},{"key":"ref_37","doi-asserted-by":"crossref","unstructured":"Sharma, P., Mirzan, S.R., Bhandari, A., Pimpley, A., Eswaran, A., Srinivasan, S., and Shao, L. (2020, January 3\u20136). Evaluating Tree Explanation Methods for Anomaly Reasoning: A Case Study of SHAP TreeExplainer and TreeInterpreter. Proceedings of the International Conference on Conceptual Modeling (2020), Vienna, Austria.","DOI":"10.1007\/978-3-030-65847-2_4"},{"key":"ref_38","unstructured":"(2023, August 13). CN-0549: IEPE-Compliant, CbM Machine Learning Enablement Platform. Available online: https:\/\/www.analog.com\/en\/design-center\/reference-designs\/circuits-from-the-lab\/cn0549.html#rd-overview."},{"key":"ref_39","unstructured":"(2023, August 13). CN-0532: IEPE-Compatible Interface for Wideband MEMS Accelerometer Sensors. Available online: https:\/\/www.analog.com\/en\/design-center\/reference-designs\/circuits-from-the-lab\/cn0532.html."},{"key":"ref_40","unstructured":"(2023, August 13). CN-0540: 24-Bit Data Acquisition System for IEPE Sensors. Available online: https:\/\/www.analog.com\/en\/design-center\/reference-designs\/circuits-from-the-lab\/cn0540.html."},{"key":"ref_41","first-page":"11936","article-title":"Auto-Sklearn 2.0: Hands-free AutoML via Meta-Learning","volume":"23","author":"Feurer","year":"2022","journal-title":"J. Mach. Learn. Res."},{"key":"ref_42","unstructured":"Vakhrushev, A., Ryzhkov, A., Savchenko, M., Simakov, D., Damdinov, R., and Tuzhilin, T. (2021). LightAutoML: AutoML Solution for a Large Financial Services Ecosystem. arXiv."},{"key":"ref_43","unstructured":"Wang, C., Wu, Q., Weimer, M., and Zhu, E. (2022, January 8\u201311). FLAML: A Fast and Lightweight AutoML Library. Proceedings of the Fourth Conference on Machine Learning and Systems (2021), Online."},{"key":"ref_44","first-page":"5442","article-title":"Darts: User-Friendly Modern Machine Learning for Time Series","volume":"23","author":"Herzen","year":"2022","journal-title":"J. Mach. Learn. Res."},{"key":"ref_45","unstructured":"Liaw, R., Liang, E., Nishihara, R., Moritz, P., Gonzalez, J.E., and Stoica, I. (2018). Tune: A Research Platform for Distributed Model Selection and Training. arXiv."},{"key":"ref_46","unstructured":"Li, L., Jamieson, K., Rostamizadeh, A., Gonina, E., Hardt, M., Recht, B., and Talwalkar, A. (2020, January 24\u201326). A System for Massively Parallel Hyperparameter Tuning. Proceedings of the 3rd Conference on Systems and Machine Learning (2020), Virtual."},{"key":"ref_47","doi-asserted-by":"crossref","unstructured":"Akiba, T., Sano, S., Yanase, T., Ohta, T., and Koyama, M. (2019, January 4\u20138). Optuna: A Next-generation Hyperparameter Optimization Framework. Proceedings of the 25th ACM SIGKDD International Conference on Knowledge Discovery & Data Mining (2019), Anchorage, AK, USA.","DOI":"10.1145\/3292500.3330701"}],"container-title":["Sensors"],"original-title":[],"language":"en","link":[{"URL":"https:\/\/www.mdpi.com\/1424-8220\/23\/20\/8523\/pdf","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2025,10,10]],"date-time":"2025-10-10T21:08:26Z","timestamp":1760130506000},"score":1,"resource":{"primary":{"URL":"https:\/\/www.mdpi.com\/1424-8220\/23\/20\/8523"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2023,10,17]]},"references-count":47,"journal-issue":{"issue":"20","published-online":{"date-parts":[[2023,10]]}},"alternative-id":["s23208523"],"URL":"https:\/\/doi.org\/10.3390\/s23208523","relation":{},"ISSN":["1424-8220"],"issn-type":[{"value":"1424-8220","type":"electronic"}],"subject":[],"published":{"date-parts":[[2023,10,17]]}}}