Case Study for the Implementation of an Automated Ultrasonic Technique to Detect Fatigue Cracks in Aircraft Weep Holes

Weep holes in C-141 aircraft have been found to be locations for the initiation of fatigue crack growth. Eddy current testing of weep holes in C-141 aircraft requires fuel tank entry by a technician and is a costly and time consuming process. This paper describes the implementation of a neural network assisted, automated ultrasonic testing technique from the outside of the wing. Toward achieving this goal of field implementation of an automated testing technique, this work demonstrates the value of numerical simulation, laboratory studies and algorithm training with samples representing infield variation, infield demonstration, parametric sensitivity studies and probability of detection (POD) validation. The testing capability for the automated procedure was found to exceed both the defined testing requirements and the ability of testing through viewing C-scan images. Field implementation would eliminate the fuel tank entry requirement, drastically reduce weep hole testing costs for the US Air Force and reduce detection variability between technicians in making classification calls.