Abstract
Spare-part management has a significant effect on the productivity of mining equipment. The required number of spare parts can be estimated using failure and repair data collected under the name of reliability data. In the mining industry, failure and repair times are decided by the operational environment, rock properties, and the technical and functional behavior of the system. These conditions are heterogeneous and may change significantly from time to time. Such heterogeneity can change equipment’s reliability performance and, consequently, the required number of spare parts. Hence, it is necessary for effective spare-part planning to check the heterogeneity among the reliability data. After that, if needed, such heterogeneity should be modeled using an adequate statistical model. Heterogeneity can be categorized into observed and unobserved caused by risk factors. Most spare-part estimation studies ignore the effect of heterogeneity, which can lead to unrealistic estimations. In this study, we introduce the application of a frailty model for modeling the effect of observed and unobserved risk factors on the required number of spare parts for mining equipment. Studies indicate that ignoring the effect of unobservable risk factors can cause a significant bias in estimation.
Highlights
Spare-part estimation plays a crucial role in logistic management
Studies have shown that, in addition to time between failure (TBF) and time to repair (TTR) data, the operational conditions in which the equipment is working should be considered in spare-part planning [3]
Based on the nature of collected data, if there is an unobservable risk factor, the frailty model is appropriate; otherwise, the Proportional Hazard Model (PHM) and its extension can be used for reliability analysis
Summary
Spare-part estimation plays a crucial role in logistic management. Effective spare-part planning reduces equipment downtime and prevents unnecessary inventory, one of the most critical wastes in the production process. After presenting the reliability analysis algorithm with time data in the context of mining studies, Kumar, in collaboration with Klefsjo [6,7], proposed the Proportional Hazard Model (PHM) to analyze the effect of observable risk factors in reliability analysis This model was used in later years by various researchers in the field of mining, such as Ghodrati [8,9,10,11,12], Abbas Barabadi [5], and Nouri Qarahasanlou [13,14,15,16,17], to analyze the reliability of mining equipment and the required number of spare parts.
Talk to us
Join us for a 30 min session where you can share your feedback and ask us any queries you have