Aiming at the problem of high-speed milling force prediction of aerospace materials such as TC4 titanium alloy， 7574 aluminum alloy， AISI304 stainless steel， and 45^# steel in the process of high-speed milling， this paper introduced the grey wolf algorithm （GWO） to improve the extreme learning machine （ELM） model to build the high-speed milling force prediction model， the second-order multiple regression model was used to analyze and determine the number of hidden layer nodes， the prediction results were compared with seven prediction models and experimental results， such as BP， RBF， ELM， etc. The research results show that the number of hidden layer nodes of the high-speed milling force prediction model based on GWO-ELM can be determined by the second-order multiple regression model， the accuracy of the prediction model is 98.8%， and the determination coefficient of 0.988 71 is better than other prediction models. Therefore， the high-speed milling force prediction model based on GWO-ELM is feasible and accurate. The research results of this paper provide a reference for the determination of the number of hidden layer nodes of the GWO-ELM model and the selection of the high-speed milling force prediction model.