Fleet heterogeneity, from manufacturing variations and diverse operating conditions, complicates reliability analysis by obscuring true failure patterns in aero-engines. This is a critical challenge in an industry as inaccurate Mean Time Between Failures (MTBF) estimates threaten safety and inflate operational costs, by forcing a choice between inefficiently conservative maintenance or the risk of in-service failures. Conventional analysis often fails by pooling all fleet data. To address this, our paper presents an analytical framework that improves predictive accuracy by filtering, rather than aggregating statistical noise. The methodology uses a Randomized Block Design (RBD) and ANOVA hypothesis test to screen a diverse dataset and isolate statistically homogeneous subgroups. This filtration identifies a core fleet with a consistent failure signature, providing a purified dataset for modeling. This refined data is then modeled using both Weibull and the Exponentiated Inverse Weibull distributions to ensure the results are robust and not model-dependent.
Applying this framework to a 25-engine dataset that experienced 66 failures, we isolated a stable failure pattern, yielding a primary MTBF of 171.16 hours and a cross-validated MTBF of 176.35 hours. The close 3% convergence between these models validates our approach. By providing a dependable MTBF, this work establishes a stronger foundation for data-driven Reliability Centered Maintenance (RCM). It empowers maintenance planners to move toward evidence-based intervals, safely extending engine time-on-wing, optimizing spare parts inventory, and significantly reducing direct operational costs for airlines.