A Superposed Log-Linear Failure Intensity Model for Repairable Artillery Systems

Multi‐system reliability trend analysis model using incomplete data with application to tank maintenance

“…Using the approximation value in Equation 16, V 1 , the confidence interval of (t) at the confidence level 100…”

“…To confirm the applicability of PLP to cases I and II data, we check whether the data are regarded as a monotonic nonhomogeneous Poisson process 16 using the Laplace test and the MIL-Handbook-189 test. 21,22 The test results shown in Table 6 confirm that cases I and II data are monotonic nonhomogeneous Poisson process and can be modeled as PLPs.…”

“…While there are some models considering the heterogeneity of machines, [14][15][16] we assume that all machines are homogenous in our model and claim that our model can be practically used when the working condition and environment of machines are not so different from each other. The tank maintenance case in this paper can be an example.…”

A New Model for Repairable Systems with Nonmonotone Intensity Function

“…Thus, lifetime failure data, in many situations, could be described with models that allow for changes in the state of the system over time or dependence between failures over time . The reliability analysis of repairable systems can be described as a failure intensity process, including a decreasing phase, an increasing phase, and an accommodation phase . In our literature review, a few models propose to describe the bathtub‐shaped intensity, such as a combined model called LLP‐PLP, which is superposing log‐linear process and power law process, the superposed power law process (S‐PLP) model by Pulcini, and the bounded bathtub intensity process (BBIP) model by Guida and Pulcini…”

“…1 The reliability analysis of repairable systems can be described as a failure intensity process, including a decreasing phase, an increasing phase, and an accommodation phase. [2][3][4][5] In our literature review, a few models propose to describe the bathtub-shaped intensity, such as a combined model called LLP-PLP, 6 which is superposing log-linear process 7 and power law process 8 , the superposed power law process (S-PLP) model by Pulcini,9 and the bounded bathtub intensity process (BBIP) model by Guida and Pulcini. 10 The PLPs proposed by Crow 8 with decreasing and increasing intensity functions are the most popular models in reliability analyses based on the nonhomogeneous Poisson process (NHPP).…”