Computational Tools

Description

Automated Weep Hole Crack Detection Using Neural Networks Weep holes are found in the risers of wing structures in C-141 aircraft. Two types of fatigue cracks have been observed to emanate from these holes, top cracks which emanate upward and bottom cracks which propagate downward toward the wing surface. Due to constraints on the placement of transducers, special ultrasonic inspection techniques were investigated for detecting and sizing cracks at bottom and top locations. A neural network assisted, automated inspection technique for bottom and top crack detection of weep holes was implemented. Toward achieving this goal, the value of numerical simulation, experimentation and training using samples representing in-field variation, in-field demonstration, parametric sensitivity studies, and probability of detection validation is demonstrated. The performance of the automated procedure was found to exceed prescribed requirements and inspection through viewing C-scan images. For more information, see Chapter 3: Case Study for the Implementation of an Automated Ultrasonic Technique to Detect Fatigue Cracks in Aircraft Weep Holes . Refined Detction of Cracks in Weep Holes Using Spatial Signal Variation Typical C-scan inspection for bottom cracks was found to miss certain small cracks. A technique was developed which examined the variation in the A-scan signals as the transducer is incrementally moved across the hole. The advantage of this refined B-scan technique is the ability to detect superimposed signals independently from the shape of the transient pulse. Figure 1. Diagram and adjusted signal plots displaying spatial signal variation procedure for four cases (a) no bottom crack, (b) with bottom, (c) no crack case with poor interface and a square pulser, (d) with small bottom crack For more information, see Chapter 2: Improving Detection of Bottom Cracks in Weep Holes Using Spatial Measurements by a Moving Transducer .

Companies nearby