IoT-Enabled Risk Warning and Maintenance Strategy Optimization for Tunnel-Induced Ground Settlement

With the continuous development of underground space, the vigorous development of underground rail transport has become an effective way to relieve the pressure of urban traffic. However, ground settlement caused by tunnels can lead to cracks, settlements, and collapses of nearby buildings, resulting in serious economic losses. To solve the problems of poor generalization performance of risk warning models and uneven allocation of maintenance resources in Prognostic and Health Management (PHM) for ground settlement in existing studies, an Internet of Things (IoT)-enabled risk warning and maintenance strategy optimization method is proposed in this article. In risk warning, first, a weight optimization method with the decision objectives of variance maximization, correlation minimization, and estimation error minimization is introduced to find the optimal weights of the base learners in ensemble learning prediction. Second, a 1-D convolutional neural network-bidirectional long and short-term memory network (1-D CNN-BiLSTM) is used to make further predictions on the prediction residuals. In maintenance strategy optimization, threshold-based optimization and cost-based risk-importance maintenance strategies are proposed based on the risk warning results of ground settlement. To test the enhanced effectiveness of the proposed method, a set of comprehensive simulations is carried out in Ningbo city rail transit as an example. The results show that the proposed risk warning method has smaller MAE, MAPE, and RMSE compared to other baseline methods. In addition, the proposed maintenance strategy reduces 12.5%, 16.3%, and 85.7% in terms of cost compared to the baseline method. Overall, the simulation results confirm the advantages of the proposed framework for IoT-enabled risk warning and maintenance strategy optimization in PHM.