This paper introduces the development and application of Artificial Intelligence (AI) network structures for predicting tool wear during high-speed dry turning of high-hardness SDK11 steel. Two network structures were considered, Back-Propagation Network (BPN) with Gradient Descent (GD) algorithm and Artificial Neural Network (ANN) combined with Particle Swarm Optimization algorithm (PSO). The dataset was compiled from 289 practical experiments for network modeling. Both the BPN and PSO-ANN structures were evaluated using regression metrics, such as R2, MSE, RMSE, and MAPE. The results revealed that the PSO-ANN network offers higher prediction accuracy, outperforming the traditional BPN model.