Информационные технологии интеллектуальной поддержки принятия решений, Информационные технологии интеллектуальной поддержки принятия решений 2018

Размер шрифта: 
An Artificial Neural Network for Automated Fault Detection
Evgenia Rusak, Julian Bitterwolf, Sebastian Reiter, Alexander Viehl, Oliver Bringmann

Изменена: 2018-06-20

Аннотация


Intelligent and interconnected cyber physical systems are a key enabler for future cost-efficient, automated and flexible industrial production systems. Predictive maintenance and condition monitoring are important techniques in order to reduce costs associated with unnecessary maintenance or premature breakdowns. In this paper, we propose techniques from supervised learning for automated malfunctioning detection. For that purpose, we train an artificial neural network on time series data representing the internal system behavior. We present experimental results from an industrial motor control system. We use a digital twin of the electronic component that models the relevant features of the physical system. The obtained information can be used during the runtime of technical systems and installations for a criticality analysis and the subsequent selection of measures.

Ключевые слова


neural networks; fault detection; industrial production systems

Литература


1.         An introduction to predictive maintenance. / Mobley, R. K.  Butterworth-Heinemann, 2002.

2.         Susto G.A., et al. Machine learning for predictive maintenance: A multiple classifier approach. // IEEE Trans. Ind. Informat. 2015. Vol 11 № 3 (2015)

3.         Li H. et al. Improving rail network velocity: A machine learning approach to predictive maintenance. // Transp. Res. Part C Emerg. Technol. 2014. Vol 45.

4.         Schaaf, J. C. et al. Systems Concept Development with Virtual Prototyping // Proc. of the 29th conference on Winter simulation 1997. P. 941–947.

5.         Oetjens J-H., et al. Safety evaluation of automotive electronics using virtual prototypes: State of the art and research challenges. // Proc. of the 51st Annual Design Automation Conference. ACM, 2014.

6.         De Sa, Gomes A., Zachmann G. Virtual reality as a tool for verification of assembly and maintenance processes. // CG 1999. Vol. 23 № 3 P. 389-403.

7.         Fu T.C. A review on time series data mining // Eng. Appl. Artif. Intell. 2011. Vol. 24 P. 164-181

8.         Bagnall, A. et al. The great time series classification bake off: a review and experimental evaluation of recent algorithmic advances. // Data Min. Knowl. Discov. 2017. Vol. 31 № 3 P. 606-660.

9.         Wang, Z., Yan W., Oates T. Time Series Classification from Scratch with Deep Neural Networks: A Strong Baseline. arXiv:1611.06455

10.       Zhong J., Zhixin Y., Wong S.F. Machine condition monitoring and fault diagnosis based on support vector machine.//  Industrial Engineering and Engineering Management (IEEM), 2010 .

11.       Shulian Y. et al. Intelligent condition monitoring and fault diagnosis of a gearbox based on Artificial Neural Network. // Proc of the ICEMI'07, IEEE, 2007.

12.       Aydin I.et.al. A simple and efficient method for fault diagnosis using time series data mining. // Proc. to IEMDC 2007, IEEE International

13.       Yang J., Sun Z., Chen Y. Fault Detection Using the Clustering-kNN Rule for Gas Sensor Arrays. // Sensors (Basel) 2016. Vol. 12. P. 2069.

14.       Campbell B., McDonald J.R. The use of artificial neural networks for condition monitoring of electrical power transformers // Neurocomputing  1998. Vol 23 № 1-3 (1998) P.97-109.

15.       Sreejith B., Verma A. K., Srividya A. Fault diagnosis of rolling element bearing using time-domain features and neural networks // Proc.of the ICIIS’2008

16.       Li, Z. et al. Virtual prototype and experimental research on gear multi-fault diagnosis using wavelet-autoregressive model and principal component analysis method // MSPP 2011. Vol 25 № 7

17.       Reiter S. et al. Fault injection ecosystem for assisted safety validation of automotive systems. // High Level Design Validation and Test Workshop (HLDVT), 2016 IEEE International.

18.       http://statistik.mathematik.uni-wuerzburg.de/fileadmin/10040800/user_upload/time_series/the_book/2012-August-01-times.pdf (дата обращения: 31.03.2018).

19.       Yaodong Z., Glass J. A piecewise aggregate approximation lower-bound estimate for posteriorgram-based dynamic time warping. // Proc. of the 12th Annual Conference of the International Speech Communication Association. 2011.

20.       Kingma D. P., Ba J. Adam: A method for Stochastic Optimization. https://arxiv.org/abs/1412.6980