Automated Copper Alloy Grain Size Evaluation using a Deep-Learning Convolutional Neural Network

Moog Inc. has automated the evaluation of copper (Cu) alloy grain size using a deep-learning convolutional neural network (CNN). The automated image acquisition and batch-wise image processing has reduced the labor, improved accuracy of grain evaluation, and decreased the overall turnaround time for approving Cu alloy bar stock for use in flight critical aircraft hardware. A classification accuracy of approximately 90% on individual sub-images of the Cu alloy coupons has been achieved. Process development included minimizing the variation in acquired image color, brightness, and resolution, and then optimizing the CNN hyper-parameters using statistical design of experiments (DoE).

Over the development of the automated Cu alloy grain size evaluation, a degree of ‘explainability’ in the artificial intelligence (XAI) output was realized, based on the decomposition of the large raw images into many smaller dataset sub-images, through the ability to explain the CNN ensemble image output via inspection of the classification results from the individual smaller sub-images.