A Repairable System Subjected to Hierarchical Competing Risks: Modeling and Applications

• Published in: IEEE access Vol. 7; pp. 171707 - 171723
• Main Authors: Louzada, Francisco, Alegria, Luis F. A., Colombo, Danilo, Martins, David E. A., Santos, Hugo F. L., Cuminato, Jose A., Rodriguez, Oscar M. H., Tomazella, Vera L. D., Ferreira, Paulo H., Ramos, Pedro L., Niaki, Seyed R. A., Gonzatto, Oilson A., Perissini, Ivan C.
• Format: Journal Article
• Language: English
• Published: Piscataway IEEE 2019; The Institute of Electrical and Electronics Engineers, Inc. (IEEE)
• Subjects: Bias; Bias correction; Butterfly valves; competing risks; Confidence intervals; Data models; Estimators; hierarchical systems; Maintenance engineering; Maximum likelihood estimation; Maximum likelihood method; Modelling; Parameter estimation; Periodic structures; power-law process; Reliability engineering; Statistical analysis; Structural hierarchy; Valves
• ISSN: 2169-3536; 2169-3536
• DOI: 10.1109/ACCESS.2019.2954767

In this paper, we propose modeling for a single repairable system with a hierarchical structure under the assumption that the failures follow a nonhomogeneous Poisson process (which corresponds to minimal repair action) with a power-law intensity function. The properties of the new model are discussed in detail. The parameter estimators are obtained using the maximum likelihood method. A corrective approach is used to remove bias with order O(n -1 ), and the respective exact confidence intervals are proposed. A simulation study is conducted to show that our estimators are bias-free. The proposed modeling is illustrated via a toy example on a butterfly valve system, an example of an early-stage real project related to the traction system of an in-pipe robot, and also a real example on a blowout preventer system.