This is an open access article distributed under the CC BY-NC-ND 4.0 terms and conditions.
Volume 10 article 227 pages: 107 - 115
Using CM, we have past data for describing damage initiation & development and current data for describing the current condition of a component/machine. Data describing possible behaviour of the condition in the close future are usually lack in the available commercial systems although it is important for planning production/maintenance actions, reducing failures/accidents, & consequently reducing losses & production cost. In general, accurate maintenance decisions prolong life length of components/machines and maintain production continuity which adds competitive advantages. When CM parameter exceeds a significant (warning) level, it demands a clear understanding of what happened to avoid failures. Also, reliable answers concerning; what is the probability of failure of a component, its residual life and when is the most profitable time of conducting maintenance are necessary. In this paper, a new innovative eMDSS consists of three strategies for cost-effective maintenance & production processes is introduced and discussed. The major focus is given on one strategy (Accurate Maintenance Decisions). This strategy offers opportunity to achieve Just on Time Dynamic & Cost-effective Maintenance by selecting the most profitable time for maintenance is developed, tested in case companies and discussed. It offers unique solutions to increase maintenance profitability by enhancing maintenance decision accuracy via;
1. Predicting the value of CM parameter, e.g. vibration, level, PreVib.
2. Estimating the probability of failure at the close future and component residual life,ProLife.
3. Using this new information, it will easily estimate the most profitable time for maintenance action.
Accurate Maintenance Decisions provides data about future situation in addition to the current & past data, which is necessary for production and maintenance successful planning. This toolset; predicts the vibration level (PreVib), assesses the probability of failure of equipment and its residual life (ProLife), and consequently it becomes possible to determine the best time of maintenance action. It has been tested in several Swedish and European companies within the branches of car manufacturing, production machine manufacturer and process industry. This study was partly funded by EU-IP DYNAMITE (Dynamic Decisions in Maintenance ) 2005-2009 and partly by E-maintenance Sweden AB. The major conclusions are; applying this toolset it is possible to reduce failures appreciably, prolongs the life length of components/equipment, and perform profitable maintenance.
This study was partly funded by EU-IP DYNAMITE (Dynamic Decisions in Maintenance) 2005-2009 and partly by E-maintenance Sweden AB.
Al-Najjar B (2009) A computerised model for assessing the return on investment in maintenance: Following up maintenance contribution in company profit. WCEAM 2009, page 137-145, Greece, Athens.
Al-Najjar, B. (1997). Condition-based maintenance: Selection and improvement of a costeffective vibration-based policy in rolling element bearings. Doctoral thesis, ISSN 0280-722X, ISRN LUTMDN/TMIO—1006— SE, ISBN 91-628-2545-X, Lund University, Inst. of Industrial Engineering, Sweden.
Al-Najjar, B. (2000) Accuracy, effectiveness and improvement of Vibration-based Maintenance in Paper Mills; Case Studies. Journal of Sound and Vibration, 229(2), p. 389-410.
Al-Najjar, B. (2001) Prediction of the vibration level when monitoring rolling element bearings in paper mill machines. International Journal of COMADEM 4 (2), p. 19-27
Al-Najjar, B. (2003) Total Time on Test, TTT- plots for condition monitoring of rolling element bearings in paper mills. International Journal of COMADEM 6 (2), p. 27-32.
Holmberg, K., Jantunen, E., Adgar, A., Mascolo, J., Arnaiz, A. and Mekid, S. (2010) E-Maintenance. Springer-Verlag London Limited 2010.
Xiaodong, Z. and Xu, R. and Chiman, K. and Liang, S.Y. and Qiulin, X. and Haynes, L. (2005). An integrated approach to bearing fault diagnostics and prognostics, American Control Conference, 2005. Proceedings of the 2005, p. 2750-2755
Wu, S. and Gebraeel, N. and Lawley, M. A. and Yih, Y (2007). A Neural Network Integrated Decision Support System for Condition-Based Optimal Predictive Maintenance Policy, IEEE Transactions on Systems, Man, and Cybernetics - Part A: Systems and Humans, p. 226-236, Vol 37, Number 2
Wang, W. (2002). A model to predict the residual
life of rolling element bearings given monitored condition information to
date. IMA Journal of Management Mathematics, p. 3-16, Vol 13, Number 1