Abstract:In order to improve the accuracy of extreme learning machine ( ELM ) model in the prediction of slope stability in Gongchangling Open-pit Mine and effectively solve the problem of poor stability caused by the random connection weights and hidden layer thresholds of ELM model in the training process, the improved particle swarm optimization ( IPSO ) based on random weight method is introduced to optimize, and the improved particle swarm optimization optimization extreme learning machine ( IPSO-ELM ) model is proposed. The model is applied to the monitoring data of Gongchangling Open-pit Mine slope. The prediction results are compared with the prediction values of ELM model and PSO-ELM model. The results show that the prediction value of IPSO-ELM model is close to the measured value, the prediction accuracy is high, the prediction speed is fast, and the model construction is reasonable. It has high feasibility in the prediction of open-pit slope and can be used as a reference method for open-pit slope prediction.