Application of PSO-LSTM Network in The prediction of Tunneling Speed of Shield Machine

The excavation parameters are key indicators reflecting the performance of the shield machine in tunnel engineering construction Unnecessary delay in construction period can result in huge economic losses. To solve the problem that traditional LSTM neural network cannot fully extract data features, this paper establishes a PSO-LSTM network model to predict the excavation speed of the shield machine by combining the particle swarm optimization algorithm (PSO) with its group intelligence and the characteristic of high data extraction of PSO algorithm. The experimental results show that the PSO-LSTM network model has a significant improvement in prediction accuracy compared to the single LSTM model in predicting the excavation speed of the shield machine. The evaluation indicators are mean square error (MSE), root mean square error (RMSE), and average absolute percentage error (MAPE). The prediction errors are reduced by 5.0%, 2.5%, and 6.2%, respectively.