A VMD-EWT-LSTM-based multi-step prediction approach for shield tunneling machine cutterhead torque
作者：
Highlights：
• We present a VMD-EWT-LSTM-based multi-step prediction method for cutterhead torque.
• VMD and EWT decomposes original input sequence into relatively simple subsequences.
• The appropriate mode quantity K of VMD could be determined adaptively.
• It only deals with one input reducing calculation time and improving efficiency.
• Its five-step average accuracy reaches 97.7%, 97.2%, 96.9%, 96.7% and 96.3%.
摘要
•We present a VMD-EWT-LSTM-based multi-step prediction method for cutterhead torque.•VMD and EWT decomposes original input sequence into relatively simple subsequences.•The appropriate mode quantity K of VMD could be determined adaptively.•It only deals with one input reducing calculation time and improving efficiency.•Its five-step average accuracy reaches 97.7%, 97.2%, 96.9%, 96.7% and 96.3%.
论文关键词：Shield tunneling machine,Multi-step cutterhead torque prediction,Variational mode decomposition,Empirical wavelet transform,LSTM neural network
论文评审过程：Received 8 March 2021, Revised 12 May 2021, Accepted 9 June 2021, Available online 19 June 2021, Version of Record 27 June 2021.
论文官网地址：https://doi.org/10.1016/j.knosys.2021.107213
