Regular Papers

International Journal of Control, Automation, and Systems 2024; 22(2): 705-721

https://doi.org/10.1007/s12555-022-0104-x

© The International Journal of Control, Automation, and Systems

RCLSTMNet: A Residual-convolutional-LSTM Neural Network for Forecasting Cutterhead Torque in Shield Machine

Chengjin Qin*, Gang Shi, Jianfeng Tao*, Honggan Yu, Yanrui Jin, Dengyu Xiao, and Chengliang Liu

Shanghai Jiaotong University

Abstract

During tunneling process, it is of critical importance to dynamically adjust operation parameters of shield machine due to changes of geological conditions. Cutterhead torque is one of the key load parameters, and its accurate prediction could adjust operational parameters including cutterhead rotational speed and tunneling speed in advance and avoid potential cutterhead jamming. Based on operation and state data collected by the monitoring system, we propose a residual-convolutional-LSTM neural network (RCLSTMNet) for forecasting cutter head torque in shield machine. On the basis of correlation analysis, parameters closely related to cutter head torque are selected as inputs by employing cosine similarity, which significantly reduces input dimension. Convolutional-LSTM neural network is fused and constructed for extracting deep useful features, while residual network module is utilized to avoid gradient disappearing and improve regression performance. Comparisons with recent data-driven cutterhead torque prediction methods are made on the actual engineering datasets, which demonstrate the presented RCLSTMNet outperforms the other data driven models in most cases. Moreover, the predicted curves of cutterhead torque using the proposed RCLSTMNet coincide with the actual curves much better than predicted curves using the other models. Meanwhile, the highest and average accuracy of RCLSTMNnet reach 98.1% and 95.6%, respectively.

Keywords Cosine similarity, cutterhead torque prediction, residual-convolutional-LSTM neural network, shield machine.

Article

Regular Papers

International Journal of Control, Automation, and Systems 2024; 22(2): 705-721

Published online February 1, 2024 https://doi.org/10.1007/s12555-022-0104-x

Copyright © The International Journal of Control, Automation, and Systems.

RCLSTMNet: A Residual-convolutional-LSTM Neural Network for Forecasting Cutterhead Torque in Shield Machine

Chengjin Qin*, Gang Shi, Jianfeng Tao*, Honggan Yu, Yanrui Jin, Dengyu Xiao, and Chengliang Liu

Shanghai Jiaotong University

Abstract

During tunneling process, it is of critical importance to dynamically adjust operation parameters of shield machine due to changes of geological conditions. Cutterhead torque is one of the key load parameters, and its accurate prediction could adjust operational parameters including cutterhead rotational speed and tunneling speed in advance and avoid potential cutterhead jamming. Based on operation and state data collected by the monitoring system, we propose a residual-convolutional-LSTM neural network (RCLSTMNet) for forecasting cutter head torque in shield machine. On the basis of correlation analysis, parameters closely related to cutter head torque are selected as inputs by employing cosine similarity, which significantly reduces input dimension. Convolutional-LSTM neural network is fused and constructed for extracting deep useful features, while residual network module is utilized to avoid gradient disappearing and improve regression performance. Comparisons with recent data-driven cutterhead torque prediction methods are made on the actual engineering datasets, which demonstrate the presented RCLSTMNet outperforms the other data driven models in most cases. Moreover, the predicted curves of cutterhead torque using the proposed RCLSTMNet coincide with the actual curves much better than predicted curves using the other models. Meanwhile, the highest and average accuracy of RCLSTMNnet reach 98.1% and 95.6%, respectively.

Keywords: Cosine similarity, cutterhead torque prediction, residual-convolutional-LSTM neural network, shield machine.

IJCAS
February 2024

Vol. 22, No. 2, pp. 347~729

Stats or Metrics

Share this article on

  • line

IJCAS

eISSN 2005-4092
pISSN 1598-6446