Adaptive VMD and multi-stage stabilized transformer-based long-distance forecasting for multiple shield machine tunneling parameters

Abstract

Achieving multivariate long-distance forecasting of shield machine tunneling parameters remains a challenge due to the huge number of tunneling parameters and the complexity of the variation pattern. To solve this problem, a long-distance forecasting method called Adaptive Variational Mode Decomposition and Multi-Stage Stabilized Transformer-based (AVMD-MST) for multiple tunneling parameters is proposed. It uses adaptive VMD and normalization to stabilize the pre-processed tunneling parameters, and the stabilized transformer is designed to establish relationships between historical and future data. The results on two different projects show that the MAPE of the proposed method decreases on average by 12.31%–36.8% for the 180th step predictions compared to the state-of-the-art algorithms. Therefore, the idea of stabilization-prediction-inverse stabilization can achieve high precision multi-variable long-distance forecasting. In the future, geological information overcasting will be carried out on the basis of the multivariate long-distance forecasting model, which can help the driver to determine the tunneling strategy.