An in-process machined surface roughness classification using an ensemble learning algorithm based on extracted automated features from real-time surface images in milling process

In the realm of machining, the surface finish of the final product serves as a pivotal quality indicator, signifying the excellence of the manufactured component. Consequently, a pressing requirement exists for dependable and precise predictive models that can effectively oversee the surface finish of machined parts throughout the in-process stage. This study presents a novel ensemble learning model, specifically the Convolutional Neural Network-Extreme Gradient Boosting (CNN-XG Boost), to classify the ongoing machined surface finish. To this end, a dataset containing images of machined surfaces was harnessed for training various traditional machine learning algorithms, encompassing Decision Tree (DT), Random Forest (RF), XGB, and K-Nearest Neighbors (KNN). Notably, XGB exhibited the highest accuracy at 41.6%. Expanding upon this, a deep learning CNN algorithm was trained, manifesting an elevated accuracy of 62.5% compared to its counterparts. The pinnacle of this endeavor entailed training ensemble algorithms such as CNN + DT, CNN + RF, CNN + XGB, and CNN + KNN. Among these, CNN + XGB stood out by achieving a remarkable prediction accuracy of 98%.