The goal of this effort is to investigate methods using KBSI’s data fusion technology to increase the accuracy of non-destructive inspection imaging technology. Using both ultrasonic and eddy current images of KC-135 lap joint coupons, KBSI developed image processing techniques, both classical and wavelet-based, for the pre-processing of image data prior to corrosion quantification and fusion. Once the image pre-processing is complete, improve and automate corrosion quantification using an artificial neural network. Finally, develop a pixel level NDI data fusion model to further improve the quantification of hidden corrosion.

By improving on the accuracy and reliability of NDI imaging, the United States Military anticipates millions of dollars in savings from speedier corrosion assessments and inspections on their aging aircraft fleet and assets.