Traditional rate of penetration （ROP） prediction models have often been constrained by issues such as high data dimensionality and feature correlation， resulting in limited efficiency and accuracy of ROP prediction. To address these issues， a ROP prediction algorithm model based on particle swarm optimization （PSO） with integrated feature selection has been proposed in this paper. Based on data preprocessing， 3 key parameters， threshold_1， threshold_2， and threshold_3， have been chosen as optimization targets， and a fitness function has been constructed by combining historical data and the PSO algorithm， thereby establishing the ROP prediction model. Subsequently， the proposed ROP prediction method has been validated using actual drilling data and compared with traditional machine learning algorithm models. Experimental results show that the proposed PSO-based integrated feature selection algorithm achieves higher efficiency and accuracy in feature selection. Compared to before optimization， the accuracy of the 4 machine learning ROP prediction models trained using the optimized integrated feature selection results is improved by 59%， 1%， 3%， and 1%， respectively. Compared to models trained using all features， the accuracy has been improved by 24%， 2%， 4%， and 3%， respectively. This paper provides an effective feature selection method for cases where too many feature parameters have been extracted in drilling engineering. It offers significant guidance for the practical application of feature selection algorithms in the engineering field.