Weitere Kapitel dieses Buchs durch Wischen aufrufen
Situation faced: All mechanical and mechatronic devices are subject to wear, tear and breakdown. Failure of such devices can cause significant costs, e.g., in automotive factories. Established predictive maintenance approaches usually require deep integration with the specific machine. Such approaches are not practically feasible because of technical, legal and financial restrictions. A non-intrusive, lightweight and generic solution approach is desired.
Action taken: A solution concept was developed which, at its heart, is based on deep learning algorithms that monitor sound sequences captured from a microphone, analyze them and return classification results for use in further steps of a control loop, such as planning actions and execution steps. We named this approach the ‘Sound Detective’ and it was evaluated by retrofitting a coffee machine using simple microphones to capture production sounds. The sound sequences are subsequently analyzed using neural networks developed in Keras and TensorFlow. During prototyping, multiple kinds of neural networks and architectures were tested and the experiment was realized with two different kinds of coffee machines to validate the generalizability of the solution to different platforms.
Results achieved: The prototype can analyze sounds produced by a mechanical machine and classify different states. The technical realization relies on cheap commodity hardware and open-source software, demonstrating the applicability of existing technologies and the feasibility of the implementation. Especially, it was described that the proposed approach can be applied to solve predictive maintenance tasks.
Lessons learned: The present work demonstrates the feasibility of the Sound Detective’s reference architecture and discusses challenges and learnings during implementation. Specifically, key learnings include the importance of data quality, preprocessing and consistency, influences of the experimental setup on real-world prediction performance and the relevance of microcomputers, the target hardware and type of the programming language for complex analyses.
Bitte loggen Sie sich ein, um Zugang zu diesem Inhalt zu erhalten
Sie möchten Zugang zu diesem Inhalt erhalten? Dann informieren Sie sich jetzt über unsere Produkte:
Dr. Ing. h.c. F. Porsche AG – Porsche Deutschland (2018) Dr. Ing. h.c. F. Porsche AG – Porsche Deutschland. Available at: http://www.porsche.de. Accessed 31 Jan 2018
Goodfellow I, Bengio Y, Courville A, Bengio Y (2016) Deep learning, vol 1. MIT Press, Cambridge
Gubbi J, Buyya R, Marusic S, Palaniswami M (2013) Internet of Things (IoT): a vision, architectural elements and future directions. Future Gener Comput Syst 29(7):1645–1660 CrossRef
Hashemian HM, Bean WC (2011) State-of-the-art predictive maintenance techniques. IEEE Trans Instrum Meas 60(10):3480–3492 CrossRef
Keras.io (2018) Keras Documentation. Available at: https://keras.io/. Accessed 31 Jan 2018
LeCun Y, Bengio Y, Hinton G (2015) Deep learning. Nature 521(7553):436–444 CrossRef
Librosa.github.io (2018) LibROSA—librosa 0.5.1 documentation. Available at: http://librosa.github.io/librosa/index.html. Accessed 31 Jan 2018
Mhp.com (2018) MHP – a Porsche company. Available at: http://www.mhp.com Accessed 31 Jan 2018
Mobley RK (2002) An introduction to predictive maintenance. Butterworth-Heinemann, Amsterdam
Mqtt.org (2018) MQTT. Available at: http://mqtt.org/. Accessed 31 Jan 2018
Piczak KJ (2015) Environmental sound classification with convolutional neural networks. In: 2015 I.E. 25th international workshop on Machine learning for signal processing (MLSP), September 2015 (pp. 1–6). IEEE
Srivastava N, Hinton G, Krizhevsky A, Sutskever I, Salakhutdinov R (2014) Dropout: a simple way to prevent neural networks from overfitting. J Mach Learn Res 15(1):1929–1958
Sundermeyer M, Schlüter R, Ney H (2012) LSTM neural networks for language modeling. In: Thirteenth Annual Conference of the International Speech Communication Association
Sutskever I, Vinyals O, Le QV (2014) Sequence to sequence learning with neural networks. In: Advances in neural information processing systems, pp 3104–3112
TensorFlow (2018) TensorFlow. Available at: https://www.tensorflow.org/. Accessed 31 Jan 2018
Upton E, Halfacree G (2014) Raspberry Pi user guide. Wiley, Chichester
Wright GL, Wright MA (2015) U.S. Patent No. 8,983,677. Washington, DC: U.S. Patent and Trademark Office
Wu SJ, Gebraeel N, Lawley MA, Yih Y (2007) A neural network integrated decision support system for condition-based optimal predictive maintenance policy. IEEE Trans Syst Man Cybern Part A Syst Hum 37(2):226–236 CrossRef
Yang W, Tavner PJ, Crabtree CJ, Feng Y, Qiu Y (2014) Wind turbine condition monitoring: technical and commercial challenges. Wind Energy 17(5):673–693 CrossRef
- Applying Sound-Based Analysis at Porsche Production: Towards Predictive Maintenance of Production Machines Using Deep Learning and Internet-of-Things Technology
Matthias Auf der Mauer
Neuer Inhalt/© ITandMEDIA