Development and validation using of artificial intelligence algorithms for tool wear forecasting in the CNC turning process of 7075 Al alloy with tungsten carbide tool

Abstract This paper investigates the application of Gradient Boosting Model (GƁM), Gaussian Process (GƤ), and Decision Tree (ƊT) algorithms to analyze and predict the progression of crater tool wear (CTW) in CNC turning processes. Experiments were conducted using tungsten carbide cutting tools on 7075 aluminum alloy, focusing on the effects of corner radius, cutting speed, depth of cut, and feed rate on tool crater wear. CTW measurements were obtained using an optical microscope. A total of 45 experiments were performed, with 36 used to train the models and the remaining 9 for evaluation. Additionally, a validation experiment was carried out under different cutting conditions to assess the accuracy of the selected model. The novelty of this study lies in its results, which outperform previous literature, and it is the first to evaluate three distinct AI models in the context of tool wear analysis. The findings show that the GBM model provided the most accurate predictions, with performance indices of R 2 = 0.986, RAE = 0.015, MAE = 0.004, RMSE = 0.065, and RSE = 0.046, and an average difference of 5.02% between the predicted and actual CTW values. These forecasts can help manufacturing companies prevent tool failure, boost productivity, and optimize costs by balancing cycle time with tool adjustment and replacement expenses.