Convolutional neural network-long short term memory optimization for accurate prediction of airflow in a ventilation system

作者：

Highlights：

• CNN-LSTM based air-flow prediction for the underground mine is proposed.

• A simple method for converting the linear signal, i.e., independent on other to the non-linear.

• The hybrid model provides an end-to-end learning solution.

• Self and automatic feature learning.

• Faster convergence and computationally efficient than other CNN models.

摘要

•CNN-LSTM based air-flow prediction for the underground mine is proposed.•A simple method for converting the linear signal, i.e., independent on other to the non-linear.•The hybrid model provides an end-to-end learning solution.•Self and automatic feature learning.•Faster convergence and computationally efficient than other CNN models.

论文关键词：Air-flow prediction,Ventilation system,1D-CNN-LSTM,Machine learning,SHAP analysis

论文评审过程：Received 19 November 2020, Revised 23 November 2021, Accepted 24 January 2022, Available online 8 February 2022, Version of Record 10 February 2022.

论文官网地址：https://doi.org/10.1016/j.eswa.2022.116618