Impact damage detection in carbon fibre composites using HTS SQUIDs and neural networks

A neural network-based data analysis tool, developed to speed the damage detection process for the NDE of impact damaged carbon fibre composites, is discussed. A feature extraction method utilising a gradient threshold search function and a feed forward neural network for pattern recognition were used to develop the system. Impact damaged carbon composite sample plates were scanned with an eddy current-based NDE setup using HTS SQUID gradiometers and double-D excitation coils. Detection of damage sites in data affected by noise spikes caused by environmental disturbances is demonstrated. Finally, a possible design for a future entirely automated scanning system is also introduced.