A statistical investigation and optimization of an industrial radiography inspection process for aero-engine components

Abstract

Obtaining a high-quality radiographic image is imperative in a radiography inspection process as it improves the identification of flaws in aero-engine parts, which in turn enhances the reliability and safety of aircrafts. Existing methods to improve the radiographic inspection process are ad hoc and rely heavily on the experiences of radiographers. The radiographic images obtained from X-rays have dual conflicting quality features, contrast sensitivity and spatial resolution, and have to satisfy a density reading constraint. This paper investigates an industrial radiography inspection process using statistical design of experiments (DOE) and analysis to determine optimal design settings for the process. The investigation adapts from the standard response surface methodology (RSM) and provides a promising alternative to the current methods. It has several key features such as the sequential DOE to first determine the feasible region imposed by the film density constraint, a sliding-level system design to handle the irregular region, and an optimization formulation to optimize the dual image quality responses simultaneously. It provides a systematic approach to analyzing processes with secondary response constraints, and provides a quantitative basis for selecting optimum process settings. To evaluate the effectiveness of the statistical models obtained for industrial radiography, the probability of detection methodology is used to compare the optimum process settings recommended. Copyright © 2005 John Wiley & Sons, Ltd.