Development and Validation of an Adaptive Quantile Monitoring Framework for Alpha Power Weibull Process under Censoring

ABSTRACT Monitoring systems are critical tools across scientific and engineering domains for detecting shifts in lifetime or performance‐related phenomena, especially under censoring conditions. In renewable energy systems, statistical control charts for censored data play a pivotal role in tracking wind speed distributions to identify operational anomalies, particularly when Supervisory Control and Data Acquisition (SCADA) sensors fail, are removed for maintenance, or data is intermittently lost. This study introduces a novel Adaptive framework for the Alpha Power Weibull distribution's Quantile under progressive type‐II Censored data. The proposed scheme leverages the Quantile Function of the Alpha Power Weibull Distribution (APWD) and an adaptive exponentially weighted moving average (AEWMA) chart, specifically tailored for wind turbine performance monitoring. Maximum likelihood estimators for APWD parameters under PT‐II censoring form the foundation of the novel scheme. A comprehensive simulation study evaluates in‐control and out‐of‐control performance using average run length, while application to real‐world wind turbine SCADA data confirms its ability to detect out‐of‐control signals. The framework is extensible to Weibull, generalized exponential, Rayleigh, and exponential distributions across various censoring schemes.