Prediction of Machines Health with Application of an Intelligent Approach – a Mining Machinery Case Study

Abstract:

Machine field services depend on sensor-driven management systems that provide alerts, alarms and indicators. At the moment the alarm is sounded, it’s sometimes too late to prevent the failure. There is no alert provided that looks at degradation over time. If we could monitor degradation, then we would forecast upcoming situations, and perform maintenance tasks when necessary. In our research we chose to focus on intelligent maintenance system, which is defined as the prediction and forecast of equipment performance. Predictive maintenance, on the other hand, focuses on machine performance features. Data come from two sources: sensors mounted on the machine to gather the machine feature information, and information from the entire manufacturing system, including machine productivity, past history and trending. By correlating data from these sources — current and historical — predictions can be made about future performance. In this article case study of coal mining machinery health prediction is presented. Health of water pumping unit was considered. Such units placed in old mine shafts are crucial to avoid flooding working ones. As an effect of predictive maintenance it can be possible to improve safety and reduce costs incurred from accidents.

• Periodical: Key Engineering Materials (Volumes 293-294)
• Pages: 661-668
• DOI: https://doi.org/10.4028/www.scientific.net/KEM.293-294.661
• Online since: September 2005
• Authors: Mariusz Gibiec
• Keywords: Machines Health Prediction, Mining Industry Case Study, Neural Networks Based Algorithms

References

[1] C. Cempel: Wibroakustyczna diagnostyka maszyn (WNT, 1992).

[2] B. Żółtowski: Podstawy diagnostyki maszyn (Wydawnictwo Uczelniane ATR Bydgoszcz 1996).

[3] A. Ikonomopoulos, R.E. Uhrig, T.H. Tsoukalas: Use of Neural Networks to Monitor Power Plants Components, (Proc. of the 54th American Power Conference, Chicago, IL, April 1, 1992).

[4] P. J. Brocwell, R. Davis: Introduction to Time Series and Forecasting (Springer-Verlag New York 2002).

[5] W. Batko, M. Gibiec: Neural Networks for Automatic Machine Condition Assessement, Proc. of the IASTED International Conference MODELLING, IDENTIFICATION AND CONTROL, Innsbruck (2000), pp.578-584.

[6] R. Tadeusiewicz i in.: Biocybernetyka i inżynieria biomedyczna 2000 - Tom 6 - Sieci neuronowe; (Akademicka Oficyna Wydawnicza EXIT/2000).

[7] J. Korbicz, D. Uciński, A. Obuchowicz: Sztuczne sieci neuronowe podstawy i zastosowania, (Akademicka Oficyna Wydawnicza PLJ, Warszawa 1994).

[8] F. Stulajter: Prediction in Time Series Using Regression Models, (Springer-Verlag New York 2002).