Use of artificial neural networks to detect damage in composite laminates
Zachary Kral. (2012). Use of Artificial Neural Networks to Detect Damage in Composite Laminates. -- In Proceedings: 8th Annual Symposium: Graduate Research and Scholarly Projects. Wichita, KS: Wichita State University, p.37-38
A novel method of damage detection in composite laminates through the use of using artificial neural networks to interpret ultrasonic sensor signals has been investigated for this research. Four sensors were placed 4.25 in apart. In a pitch-catch method, strain waves produced by one sensor, used as an actuator, passed through the material and were received by the other three sensors. The received waves are then analyzed by artificial neural networks and a damages severity and position were predicted. This system has been trained to identify damage location using as orderly collection of known simulated damage for actuator signals ranging from 50 kHz to 100 kHz. The system of four sensors was demonstrated to predict the damage location with high accuracy, compared to other methods. The research presented is a novel method of interpreting ultrasonic signal analysis with artificial neural networks to locate damage within a four sensor region.
Paper presented to the 8th Annual Symposium on Graduate Research and Scholarly Projects (GRASP) held at the Marcus Welcome Center, Wichita State University, April 18, 2012.
Research completed at the Department of Aerospace Engineering, College of Engineering