Improvements to a Machine Learning Machining Feature Recognition System

Abstract

Pre-processing and training techniques were applied to improve the performance of a model trained with an existing machining feature recognition approach by Yeo et al. [20] using a smaller dataset that more effectively mimics the complexity of CAD models used in industry. Three improvements to the feature recognition algorithm developed by Yeo et al. were explored: the incorporation of dropout to improve model stability and accuracy, the incorporation of ID3 tree pre-classification to reduce training time by reducing the size of the deep learning dataset, and the incorporation of crossover data generation to improve classification accuracy by reducing over-fitting due to insufficient training data. Incorporating dropout improved stability and improved 5-fold cross validation accuracy. Further, incorporating a 2-deep ID3 decision tree pre-classification only marginally improved classification performance but was effective in reducing the size of deep learning training dataset. Crossover data generation did not improve model performance. Using the model trained on the generic CAD dataset, and incorporating 10% dropout and a 2-deep ID3 tree, models from the real-world dataset were classified. This classifier was effective in classifying some simple features, but had poor accuracy overall. To improve this accuracy, an incremental learning technique was applied. The generic model was re-trained using samples from the real-world dataset, which improved the classification accuracy of the system.