Abstract
Monitoring systems for machines, plants, materials, and equipment are increasingly used in production processes. These online condition monitoring systems can detect damage or excessive loads at an early stage and can drastically reduce or prevent long downtimes of plants and machines as well as high repair and maintenance costs. This paper depicts a method for online crack detection with pattern recognition and computer vision methods for specimens joined by self-pierce riveting under cyclic load in fatigue tests (laboratory application) (Giese et al. Early stage crack detection in mechanically joined steel/aluminium joints by condition monitoring; 2020).
In this context a parameter-free detection of significant frequencies during the test procedure was developed. To achieve this goal, the vibration data is recorded by a triaxial structure-borne sound sensor during the test. The evaluation is used for online crack detection, so that an early shutdown of the testing machine and thus a meaningful result over the life cycle of a mechanically joined joint is guaranteed.
For this purpose, time series are described in the frequency domain at each function value by a novel feature vector. The characteristics used are independent of external test parameters, such as the test frequency or force level. This makes it possible to change test parameters without additional algorithmic effort and without expert knowledge.
This is a preview of subscription content, log in via an institution to check access.
Access this chapter
Tax calculation will be finalised at checkout
Purchases are for personal use only
Similar content being viewed by others
References
Kolerus, J., Wassermann, J.: Condition Monitoring of Machines—The Textbook and Workbook for the Practitioner, 7th edn. Expert Verlag, Renningen (2017) (in German)
Giese P., Hein D., Meschut G., Gollnick M., Herfert D.: Early stage crack detection in mechanically joined steel/aluminium joints by condition monitoring. Materials Testing 62/9 (2020)
Gollnick, M., Herfert, D., Heimann, J.: Automatic modal parameter identification with methods of artificial intelligence. Proc. IMAC. 38, (2020)
Leurs W., Deblauwe F., Lembregts F.: Modal parameter estimation based on complex mode indicator functions, LMS Intl. Leuven, Belgium. In: Proceedings of 11th International Modal Analysis Conference, pp. 1035–1041 (1993)
Allemang R.J., Brown D.L.: A complete review of the complex mode indicator function (CMIF) with Applications. In: Proceedings of ISMA2006 Int. conference on noise and vibration engineering, Sep 2006, pp. 3209–3246 (2006)
Schölkopf, B., Smola, A.: Learning with Kernels: Support Vector Machines, Regularization, Optimization, and Beyond (Adaptive Computation and Machine Learning). MIT Press, Cambridge, MA (2002)
Kecman, V., Huang, T.-M., Vogt, M.: Iterative single data algorithm for training kernel machines from huge data sets: theory and performance. In: Wang, L. (ed.) Support Vector Machines: Theory and Applications, pp. 255–274. Springer-Verlag, Berlin (2005)
Acknowledgments
The research results presented and used originate from the IGF research project 19700N of the Society for the Advancement of Applied Computer Science (GFaI) and the “Forschungsvereinigung Stahlanwendung” (FOSTA), which was funded by the “Arbeitsgemeinschaft industrieller Forschungsvereinigungen” (AiF) within the framework of the program for the promotion of industrial research (IGF) by the Federal Ministry of Economics, Mittelstand and Energy (BMWi) based on a resolution of the German Bundestag.
Author information
Authors and Affiliations
Corresponding author
Editor information
Editors and Affiliations
Rights and permissions
Copyright information
© 2022 The Society for Experimental Mechanics, Inc.
About this paper
Cite this paper
Gollnick, M., Giese, P., Herfert, D. (2022). Feature Based Monitoring Application for Automatic Crack Detection Using WaveImage. In: Dilworth, B.J., Mains, M. (eds) Topics in Modal Analysis & Testing, Volume 8. Conference Proceedings of the Society for Experimental Mechanics Series. Springer, Cham. https://doi.org/10.1007/978-3-030-75996-4_2
Download citation
DOI: https://doi.org/10.1007/978-3-030-75996-4_2
Published:
Publisher Name: Springer, Cham
Print ISBN: 978-3-030-75995-7
Online ISBN: 978-3-030-75996-4
eBook Packages: EngineeringEngineering (R0)