Abstract:To address the difficulty in real-time and accurate prediction of surface roughness during laser drilling of titanium alloy micro-holes, a prediction method based on an Improved Particle Swarm Optimization algorithm optimized Backpropagation (IPSO-BP) neural network is proposed. Taking three key process parameters—laser power, pulse frequency, and focal position deviation—as input features and the surface roughness of micro-holes as the output, an IPSO-BP prediction model was established. The model was trained and validated using 27 sets of simulation data, with 22 sets for training and 5 sets for independent testing. Simulation test results show that the maximum relative error of the prediction model on the test set is 6.89%. To further validate the model"s effectiveness, three sets of laser drilling verification experiments were conducted. The maximum relative error between the measured roughness and the model"s predicted values is 8.50%. The results indicate that the constructed IPSO-BP neural network model can predict the surface roughness of laser-drilled holes with high accuracy. This method can provide effective guidance for process parameter optimization, reduce experimental trial and error, and lower processing costs.