{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,5,29]],"date-time":"2026-05-29T19:05:13Z","timestamp":1780081513641,"version":"3.54.0"},"reference-count":35,"publisher":"Springer Science and Business Media LLC","issue":"1","license":[{"start":{"date-parts":[[2025,11,12]],"date-time":"2025-11-12T00:00:00Z","timestamp":1762905600000},"content-version":"tdm","delay-in-days":0,"URL":"https:\/\/creativecommons.org\/licenses\/by\/4.0"},{"start":{"date-parts":[[2025,11,12]],"date-time":"2025-11-12T00:00:00Z","timestamp":1762905600000},"content-version":"vor","delay-in-days":0,"URL":"https:\/\/creativecommons.org\/licenses\/by\/4.0"}],"funder":[{"DOI":"10.13039\/501100004115","name":"Gottfried Wilhelm Leibniz Universit\u00e4t Hannover","doi-asserted-by":"crossref","id":[{"id":"10.13039\/501100004115","id-type":"DOI","asserted-by":"crossref"}]}],"content-domain":{"domain":["link.springer.com"],"crossmark-restriction":false},"short-container-title":["Sci Rep"],"abstract":"<jats:title>Abstract<\/jats:title>\n                  <jats:p>This paper presents the development of a condition monitoring system for a unique, complex technical system represented by a drop tower. The self-developed drop tower, the Einstein-Elevator, is designed as a research platform for highly reproducible zero gravity conditions. As the Einstein-Elevator is a new and unique system with a low number of data samples, detecting wear and other faulty behavior is a challenging task. However, this is important to foresee and counteract cost and time intensive shutdowns. For this purpose, a condition monitoring system based on a neural network approach using acceleration data has been developed together with a framework. According to the state of the art, first the Einstein-Elevator is presented, followed by the developed six-stage framework for model generation. The framework includes both the pre-processing of sensor data as well as the creation and optimization of a data-driven model for diagnosing faulty operating. Additionally, the results showcase the performance of the convolutional autoencoder, which was trained to accurately reconstruct spectrograms of normal flight samples without anomalies. Subsequently, the model was evaluated based on the size of the reconstruction error that occurred with the implementation of anomalous samples. In order to reduce under- or overfitting and improve the model, data augmentation via cutout-methods has been used and validated. This approach resulted in an improved anomaly detection capability as evidenced by several metrics such as the accuracy (97.22%) or the precision (93.88%). Based on the gained research results, the framework has been implemented for the use at the Einstein-Elevator. The work concludes with an outlook for further model optimizations. The developed condition monitoring system approach for a high dynamic system with very precise quality requirements\/specifications can be transferred to similarly complex technical systems of various applications, which will be part of future work.<\/jats:p>","DOI":"10.1038\/s41598-025-26114-w","type":"journal-article","created":{"date-parts":[[2025,11,12]],"date-time":"2025-11-12T15:28:24Z","timestamp":1762961304000},"update-policy":"https:\/\/doi.org\/10.1007\/springer_crossmark_policy","source":"Crossref","is-referenced-by-count":1,"title":["Convolutional autoencoder based condition monitoring system for unique complex technical systems"],"prefix":"10.1038","volume":"15","author":[{"given":"Emre","family":"Tahtali","sequence":"first","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Marco","family":"Adamscheck","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Ludger","family":"Overmeyer","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Marc Christopher","family":"Wurz","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Christoph","family":"Lotz","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Daniel","family":"Klaas","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]}],"member":"297","published-online":{"date-parts":[[2025,11,12]]},"reference":[{"key":"26114_CR1","unstructured":"Raupert, M., Tahtali, E., Sperling, R., Heidt, A., Lotz, C., & Overmeyer, L. Challenges in the development of the Laser Metal Deposition process for use in microgravity at the Einstein-Elevator. In collaboration with the Technical Information Library. Scientific Society for Laser Technology and Photonics e.V. (WLT). (2023) Available at: https:\/\/www.repo.uni-hannover.de\/handle\/123456789\/15801"},{"issue":"12","key":"26114_CR2","doi-asserted-by":"publisher","first-page":"121001","DOI":"10.1115\/1.4066335","volume":"146","author":"J Raffel","year":"2024","unstructured":"Raffel, J. et al. Ultrasonic levitation as a handling tool for in-space manufacturing processes. J. Manuf. Sci. Eng. 146(12), 121001. https:\/\/doi.org\/10.1115\/1.4066335 (2024).","journal-title":"J. Manuf. Sci. Eng."},{"issue":"3","key":"26114_CR3","doi-asserted-by":"publisher","first-page":"2213","DOI":"10.1109\/JSYST.2019.2905565","volume":"13","author":"W Zhang","year":"2019","unstructured":"Zhang, W., Yang, D. & Wang, H. Data-driven methods for predictive maintenance of industrial equipment: A survey. IEEE Syst. J. 13(3), 2213\u20132227. https:\/\/doi.org\/10.1109\/JSYST.2019.2905565 (2019).","journal-title":"IEEE Syst. J."},{"issue":"10","key":"26114_CR4","doi-asserted-by":"publisher","first-page":"851","DOI":"10.3390\/machines10100851","volume":"10","author":"G Xiang","year":"2022","unstructured":"Xiang, G., Miao, J., Cui, L. & Hu, X. Intelligent fault diagnosis for inertial measurement unit through deep residual convolutional neural network and short-time fourier transform. Machines 10(10), 851. https:\/\/doi.org\/10.3390\/machines10100851 (2022).","journal-title":"Machines"},{"issue":"1\u20134","key":"26114_CR5","doi-asserted-by":"publisher","first-page":"297","DOI":"10.1007\/s00170-009-2482-0","volume":"50","author":"Y Peng","year":"2010","unstructured":"Peng, Y., Dong, M. & Zuo, M. J. Current status of machine prognostics in condition-based maintenance: A review. Int. J. Adv. Manuf. Technol. 50(1\u20134), 297\u2013313. https:\/\/doi.org\/10.1007\/s00170-009-2482-0 (2010).","journal-title":"Int. J. Adv. Manuf. Technol."},{"issue":"4","key":"26114_CR6","doi-asserted-by":"publisher","first-page":"27","DOI":"10.1109\/MIS.2022.3167561","volume":"37","author":"J Gama","year":"2022","unstructured":"Gama, J., Ribeiro, R. P. & Veloso, B. Data-driven predictive maintenance. IEEE Intell. Syst. 37(4), 27\u201329. https:\/\/doi.org\/10.1109\/MIS.2022.3167561 (2022).","journal-title":"IEEE Intell. Syst."},{"issue":"7","key":"26114_CR7","doi-asserted-by":"publisher","first-page":"1483","DOI":"10.1016\/j.ymssp.2005.09.012","volume":"20","author":"AK Jardine","year":"2006","unstructured":"Jardine, A. K., Lin, D. & Banjevic, D. A review on machinery diagnostics and prognostics implementing condition-based maintenance. Mech. Syst. Signal Process. 20(7), 1483\u20131510. https:\/\/doi.org\/10.1016\/j.ymssp.2005.09.012 (2006).","journal-title":"Mech. Syst. Signal Process."},{"issue":"11","key":"26114_CR8","doi-asserted-by":"publisher","first-page":"27","DOI":"10.1145\/240455.240464","volume":"39","author":"U Fayyad","year":"1996","unstructured":"Fayyad, U., Piatetsky-Shapiro, G. & Smyth, P. The KDD process for extracting useful knowledge from volumes of data. Commun. ACM 39(11), 27\u201334. https:\/\/doi.org\/10.1145\/240455.240464 (1996).","journal-title":"Commun. ACM"},{"key":"26114_CR9","doi-asserted-by":"publisher","DOI":"10.3390\/app12030972","author":"M Tiboni","year":"2022","unstructured":"Tiboni, M., Remino, C., Bussola, R. & Amici, C. A review on vibration-based condition monitoring of rotating machinery. Appl. Sci. https:\/\/doi.org\/10.3390\/app12030972 (2022).","journal-title":"Appl. Sci."},{"issue":"1","key":"26114_CR10","doi-asserted-by":"publisher","first-page":"33","DOI":"10.1002\/wics.2","volume":"1","author":"S Morgenthaler","year":"2009","unstructured":"Morgenthaler, S. Exploratory data analysis. Wiley Interdiscip. Rev. Comput. Stat. 1(1), 33\u201344. https:\/\/doi.org\/10.1002\/wics.2 (2009).","journal-title":"Wiley Interdiscip. Rev. Comput. Stat."},{"issue":"1","key":"26114_CR11","doi-asserted-by":"publisher","first-page":"1","DOI":"10.1186\/s41044-016-0014-0","volume":"1","author":"S Garc\u00eda","year":"2016","unstructured":"Garc\u00eda, S., Ram\u00edrez-Gallego, S., Luengo, J., Ben\u00edtez, J. M. & Herrera, F. Big data preprocessing: Methods and prospects. Big Data Anal. 1(1), 1\u201322. https:\/\/doi.org\/10.1186\/s41044-016-0014-0 (2016).","journal-title":"Big Data Anal."},{"issue":"11","key":"26114_CR12","doi-asserted-by":"publisher","first-page":"7067","DOI":"10.1109\/TIE.2016.2582729","volume":"63","author":"T Ince","year":"2016","unstructured":"Ince, T., Kiranyaz, S., Eren, L., Askar, M. & Gabbouj, M. Real-time motor fault detection by 1-D convolutional neural networks. IEEE Trans. Industr. Electron. 63(11), 7067\u20137075. https:\/\/doi.org\/10.1109\/TIE.2016.2582729 (2016).","journal-title":"IEEE Trans. Industr. Electron."},{"key":"26114_CR13","volume-title":"Data preparation for data mining","author":"D Pyle","year":"1999","unstructured":"Pyle, D. Data preparation for data mining (Morgan Kaufmann, 1999)."},{"issue":"4","key":"26114_CR14","doi-asserted-by":"publisher","first-page":"585","DOI":"10.1007\/s11831-015-9145-0","volume":"23","author":"D Goyal","year":"2016","unstructured":"Goyal, D. & Pabla, B. S. The vibration monitoring methods and signal processing Techniques for structural health monitoring: A review. Arch. Comput. Methods Eng. 23(4), 585\u2013594. https:\/\/doi.org\/10.1007\/s11831-015-9145-0 (2016).","journal-title":"Arch. Comput. Methods Eng."},{"issue":"1","key":"26114_CR15","doi-asserted-by":"publisher","first-page":"135","DOI":"10.1016\/j.cie.2012.02.002","volume":"63","author":"R Ahmad","year":"2012","unstructured":"Ahmad, R. & Kamaruddin, S. An overview of time-based and condition-based maintenance in industrial application. Comput. Ind. Eng. 63(1), 135\u2013149. https:\/\/doi.org\/10.1016\/j.cie.2012.02.002 (2012).","journal-title":"Comput. Ind. Eng."},{"key":"26114_CR16","doi-asserted-by":"publisher","first-page":"70","DOI":"10.1016\/j.ymssp.2018.05.050","volume":"110","author":"R Zhao","year":"2019","unstructured":"Zhao, R. et al. Deep learning and its applications to machine health monitoring: A survey. Mech. Syst. Signal Process. 110, 70\u2013101. https:\/\/doi.org\/10.1016\/j.ymssp.2018.05.050 (2019).","journal-title":"Mech. Syst. Signal Process."},{"issue":"5786","key":"26114_CR17","doi-asserted-by":"publisher","first-page":"504","DOI":"10.1126\/science.1127647","volume":"313","author":"GE Hinton","year":"2006","unstructured":"Hinton, G. E. & Salakhutdinov, R. R. Reducing the dimensionality of data with neural networks. Science 313(5786), 504\u2013507. https:\/\/doi.org\/10.1126\/science.1127647 (2006).","journal-title":"Science"},{"key":"26114_CR18","doi-asserted-by":"publisher","first-page":"58722","DOI":"10.1109\/ACCESS.2024.3390186","volume":"12","author":"S Al-Otaibi","year":"2024","unstructured":"Al-Otaibi, S. et al. Dual attention convolutional autoencoder for diagnosis of Alzheimer\u2019s disorder in patients using neuroimaging and MRI features. IEEE Access 12, 58722\u201358739. https:\/\/doi.org\/10.1109\/ACCESS.2024.3390186 (2024).","journal-title":"IEEE Access"},{"key":"26114_CR19","doi-asserted-by":"publisher","first-page":"104169","DOI":"10.1016\/j.compind.2024.104169","volume":"164","author":"F Lu","year":"2025","unstructured":"Lu, F. et al. Prior knowledge embedding convolutional autoencoder: A single-source domain generalized fault diagnosis framework under small samples. Comput. Ind. 164, 104169. https:\/\/doi.org\/10.1016\/j.compind.2024.104169 (2025).","journal-title":"Comput. Ind."},{"key":"26114_CR20","doi-asserted-by":"publisher","first-page":"362","DOI":"10.3390\/machines12060362","volume":"12","author":"D Wu","year":"2024","unstructured":"Wu, D., Chen, Da. & Yu, G. New health indicator construction and fault detection network for rolling bearings via convolutional auto-encoder and contrast learning. Machines 12, 362. https:\/\/doi.org\/10.3390\/machines12060362 (2024).","journal-title":"Machines"},{"key":"26114_CR21","doi-asserted-by":"publisher","first-page":"V119","DOI":"10.1190\/geo2018-0699.1","volume":"85","author":"Y Wang","year":"2020","unstructured":"Wang, Y., Wang, B., Tu, N. & Geng, J. Seismic trace interpolation for irregularly spatial sampled data using convolutional autoencoder. Geophysics 85, V119\u2013V130. https:\/\/doi.org\/10.1190\/geo2018-0699.1 (2020).","journal-title":"Geophysics"},{"key":"26114_CR22","doi-asserted-by":"publisher","unstructured":"Cubuk, E. D., Zoph, B., Shlens, J., & Le, Q. V. (2020). Randaugment: Practical automated data augmentation with a reduced search space. In Proceedings of the IEEE\/CVF Conference on Computer Vision and Pattern Recognition Workshops (pp. 702\u2013703). https:\/\/doi.org\/10.48550\/arXiv.1909.13719","DOI":"10.48550\/arXiv.1909.13719"},{"key":"26114_CR23","doi-asserted-by":"publisher","unstructured":"Hansen, L., Diesel, J. & Heinrich, M. P., Regularized Landmark Detection with CAEs for Human Pose Estimation in the Operating Room, Bildverarbeitung f\u00fcr die Medizin 2019 (eds H. Handels et al.) 178\u2013183 (Springer, 2019). https:\/\/doi.org\/10.1007\/978-3-658-25326-4_38","DOI":"10.1007\/978-3-658-25326-4_38"},{"key":"26114_CR24","doi-asserted-by":"publisher","first-page":"3947","DOI":"10.1007\/s10462-019-09784-7","volume":"53","author":"R Moradi","year":"2020","unstructured":"Moradi, R., Berangi, R. & Minaei, B. A survey of regularization strategies for deep models. Artif. Intell. Rev. 53, 3947\u20133986. https:\/\/doi.org\/10.1007\/s10462-019-09784-7 (2020).","journal-title":"Artif. Intell. Rev."},{"key":"26114_CR25","doi-asserted-by":"publisher","DOI":"10.1007\/s11831-025-10260-5","author":"ID Mienye","year":"2025","unstructured":"Mienye, I. D. & Swart, T. G. Deep autoencoder neural networks: A comprehensive review and new perspectives. Arch. Computat. Methods Eng. https:\/\/doi.org\/10.1007\/s11831-025-10260-5 (2025).","journal-title":"Arch. Computat. Methods Eng."},{"key":"26114_CR26","doi-asserted-by":"publisher","first-page":"107751","DOI":"10.1016\/j.asoc.2021.107751","volume":"112","author":"M Thill","year":"2021","unstructured":"Thill, M., Konen, W., Wang, H. & B\u00e4ck, T. Temporal convolutional autoencoder for unsupervised anomaly detection in time series. Appl. Soft Comput. 112, 107751. https:\/\/doi.org\/10.1016\/j.asoc.2021.107751 (2021).","journal-title":"Appl. Soft Comput."},{"key":"26114_CR27","doi-asserted-by":"publisher","first-page":"190","DOI":"10.3390\/s25010190","volume":"25","author":"F Wang","year":"2025","unstructured":"Wang, F. et al. A survey of deep anomaly detection in multivariate time series: Taxonomy, applications, and directions. Sensors 25, 190. https:\/\/doi.org\/10.3390\/s25010190 (2025).","journal-title":"Sensors"},{"key":"26114_CR28","unstructured":"Boniol, P., Liu, Q., Huang, M., Palpanas, T., & Paparrizos, J. (2024). Dive into Time-Series Anomaly Detection: A Decade Review. https:\/\/arxiv.org\/pdf\/2412.20512"},{"key":"26114_CR29","doi-asserted-by":"publisher","unstructured":"Lotz, C. (2022). Untersuchungen zu Einflussfaktoren auf die Qualit\u00e4t von Experimenten unter Mikrogravitation im Einstein-Elevator [Dissertation]. Gottfried Wilhelm Leibniz University Hannover; TEWISS - Technik und Wissen GmbH. https:\/\/doi.org\/10.15488\/11713","DOI":"10.15488\/11713"},{"issue":"2","key":"26114_CR30","doi-asserted-by":"publisher","first-page":"1","DOI":"10.1007\/s12217-021-09878","volume":"33","author":"B Reitz","year":"2021","unstructured":"Reitz, B. et al. Additive manufacturing under lunar gravity and microgravity. Microgravity Sci. Technol. 33(2), 1\u201312. https:\/\/doi.org\/10.1007\/s12217-021-09878 (2021).","journal-title":"Microgravity Sci. Technol."},{"issue":"1","key":"26114_CR31","doi-asserted-by":"publisher","first-page":"19366","DOI":"10.1038\/s41598-023-46483-4","volume":"13","author":"R Sperling","year":"2023","unstructured":"Sperling, R., Raupert, M., Lotz, C. & Overmeyer, L. Simulative validation of a novel experiment carrier for the Einstein-Elevator. Sci. Rep. 13(1), 19366. https:\/\/doi.org\/10.1038\/s41598-023-46483-4 (2023).","journal-title":"Sci. Rep."},{"issue":"8","key":"26114_CR32","doi-asserted-by":"publisher","first-page":"1967","DOI":"10.1016\/j.asr.2018.01.010","volume":"61","author":"C Lotz","year":"2018","unstructured":"Lotz, C., Wessarges, Y., Hermsdorf, J., Ertmer, W. & Overmeyer, L. Novel active driven drop tower facility for microgravity experiments investigating production technologies on the example of substrate-free additive manufacturing. Adv. Space Res. 61(8), 1967\u20131974. https:\/\/doi.org\/10.1016\/j.asr.2018.01.010 (2018).","journal-title":"Adv. Space Res."},{"issue":"3","key":"26114_CR33","doi-asserted-by":"publisher","first-page":"1","DOI":"10.1145\/1541880.1541882","volume":"41","author":"V Chandola","year":"2009","unstructured":"Chandola, V., Banerjee, A. & Kumar, V. Anomaly detection: A survey. ACM Comput. Surv. 41(3), 1\u201358. https:\/\/doi.org\/10.1145\/1541880.1541882 (2009).","journal-title":"ACM Comput. Surv."},{"key":"26114_CR34","doi-asserted-by":"publisher","unstructured":"Devries, T., & Taylor, G. W. (2017). Improved regularization of convolutional neural networks with cutout. Preprint at https:\/\/arxiv.org\/abs\/1708.04552. https:\/\/doi.org\/10.48550\/arXiv.1708.04552","DOI":"10.48550\/arXiv.1708.04552"},{"key":"26114_CR35","doi-asserted-by":"publisher","unstructured":"Park, D. S., Chan, W., Zhang, Y., Chiu, C.-C., Zoph, B., Cubuk, E. D., & Le, Q. V. (2019). Specaugment: A simple data augmentation method for automatic speech recognition. Preprint at https:\/\/arxiv.org\/abs\/1904.08779. https:\/\/doi.org\/10.21437\/Interspeech.2019-2680","DOI":"10.21437\/Interspeech.2019-2680"}],"container-title":["Scientific Reports"],"original-title":[],"language":"en","link":[{"URL":"https:\/\/www.nature.com\/articles\/s41598-025-26114-w.pdf","content-type":"application\/pdf","content-version":"vor","intended-application":"text-mining"},{"URL":"https:\/\/www.nature.com\/articles\/s41598-025-26114-w","content-type":"text\/html","content-version":"vor","intended-application":"text-mining"},{"URL":"https:\/\/www.nature.com\/articles\/s41598-025-26114-w.pdf","content-type":"application\/pdf","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2025,11,17]],"date-time":"2025-11-17T04:19:41Z","timestamp":1763353181000},"score":1,"resource":{"primary":{"URL":"https:\/\/www.nature.com\/articles\/s41598-025-26114-w"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2025,11,12]]},"references-count":35,"journal-issue":{"issue":"1","published-online":{"date-parts":[[2025,12]]}},"alternative-id":["26114"],"URL":"https:\/\/doi.org\/10.1038\/s41598-025-26114-w","relation":{},"ISSN":["2045-2322"],"issn-type":[{"value":"2045-2322","type":"electronic"}],"subject":[],"published":{"date-parts":[[2025,11,12]]},"assertion":[{"value":"20 June 2025","order":1,"name":"received","label":"Received","group":{"name":"ArticleHistory","label":"Article History"}},{"value":"27 October 2025","order":2,"name":"accepted","label":"Accepted","group":{"name":"ArticleHistory","label":"Article History"}},{"value":"12 November 2025","order":3,"name":"first_online","label":"First Online","group":{"name":"ArticleHistory","label":"Article History"}},{"order":1,"name":"Ethics","group":{"name":"EthicsHeading","label":"Declarations"}},{"value":"The authors declare no competing interests.","order":2,"name":"Ethics","group":{"name":"EthicsHeading","label":"Competing interests"}},{"value":"Special Unit\n                      g\n                      \u2009=\u2009Earth\u2019s gravity (1\u00a0\n                      g\n                      \u2009=\u20099.81\u00a0m\/s\n                      2\n                      ). It is written in italics to avoid confusion with the unit gram (\u201cg\u201d, not written in italics).","order":3,"name":"Ethics","group":{"name":"EthicsHeading","label":"Author\u2019s Statement"}}],"article-number":"39582"}}