Semi-Markov Reliability, Maintainability and Profit Analysis of a Raw Mill System in Cement Manufacturing

This paper develops a data-based stochastic reliability model for the Raw Mill system considered in a cement-manufacturing case study. The analysis uses 80 structured failure, inspection and preventive-maintenance events over 2,900.38 h. A semi-Markov and regenerative-point framework is used because the system can move among full operation, degraded operation, inspection, corrective repair, preventive maintenance and complete failure, while repair duration does not satisfy a simple exponential assumption. Inter-failure time is represented by an exponential model with an estimated rate of 0.021085 h-1, whereas the Weibull distribution gives the best parametric approximation for repair time. The estimated mean time to system failure is 95.9448 h and steady-state operational availability is 0.9268. Reliability falls from 0.7205 at 24 h to 0.3238 at 96 h. Separator, Grinding and Feeding create the largest combined operational burden. Under normalized economic assumptions, long-run expected profit is 355.7148 units/h; a coordinated improvement scenario raises it to 366.1774 units/h. The results show that failure prevention, quicker restoration and condition-based intervention should be evaluated together rather than as separate maintenance decisions.

© 2026 — Authors retain the copyright of this article. This is an open access article distributed under the Creative Commons Attribution License (CC BY 4.0) , which permits unrestricted use, distribution, and reproduction in any medium, provided the original work is properly cited.