Abstract:For the problems of the parts accuracy and the technological parameters selection in selective laser sintering and the defects of BP neural network,a accuracy prediction model was proposed through the improved BP neutral network. Firstly, considering the characteristics of SLS process and factors affecting the accuracy of the parts, the accuracy data of multigroup parts under different laser powers, scanning speeds, scanning pitches and layer thicknesses were obtained through experiments, and the singleobjective idea based on multiobjective function optimization was used to deal with them. Then, the optimal solution obtained by particle swarm optimization was used as the initial weight and threshold of BP neural network. The optimized BP neural network prediction model established in MATLAB was used to predict the accuracy function model, and the prediction results were compared with those obtained by traditional BP neural network. The results show that the neural network model with particle swarm optimization has good global search ability and convergence, and its accuracy prediction is more accurate, and it has some practical guidance for SLS printed parts.