收藏切换
Research on Multi-Step Prediction of Roadway Deformation Based on AE-TCN-Transformer Parallel Model
收藏切换
Longfei WANG1, Junzhi CHEN1, Chunfang REN1, Chuanchuan CAI1, Xiaowen XU1, Yang LIU2, Changyao HE2
Mining Research and Development | 2026, 46(4) : 84 - 93
Less
收藏切换
Mining Research and Development | 2026, 46(4): 84-93
Research on Multi-Step Prediction of Roadway Deformation Based on AE-TCN-Transformer Parallel Model
Full
Longfei WANG1, Junzhi CHEN1, Chunfang REN1, Chuanchuan CAI1, Xiaowen XU1, Yang LIU2, Changyao HE2
Affiliations
  • 1.Faculty of Land Resources Engineering, Kunming University of Science and Technology, Kunming, Yunnan 650093, China
  • 2.Faculty of Public Safety and Emergency Management, Kunming University of Science and Technology, Kunming, Yunnan 650093, China
Published: 2026-04-25
Outline
收藏切换

To achieve accurate prediction of roadway deformation, a parallel prediction model that combines a Temporal Convolutional Network (TCN) and a Transformer, optimized using the Alpha evolution (AE) algorithm was proposed. This model integrated TCN and Transformer architectures through a parallel framework. The TCN utilized dilated causal convolutions to extract local temporal features, while the Transformer employed a multi-head self-attention mechanism to enhance the capture of long-term temporal patterns. Finally, the model output results through a dynamic multi-model feature fusion mechanism guided by temporal attention. At the same time, the AE algorithm was introduced to optimize hyper parameters, leveraging adaptive evolutionary paths and a two-step mechanism to enhance the model's robustness as handling complex time-series data. Experimental validation was conducted using roadway displacement monitoring data from three different monitoring points in the middle levels of an iron ore in Yunnan. The results show that when the prediction step size ranges from 6 to 48, the AE-TCN-Transformer model maintains a root mean square error (RMSE) below 0.013 2 mm, a symmetric mean absolute percentage error (SMAPE) below 0.09%, and a coefficient of determination (R2) above 0.97. These performance metrics significantly outperform those of single models such as TCN, Transformer, LSTM, and other single-model approaches. This fully validates the accuracy and reliability of the AE-TCN-Transformer model in roadway deformation prediction and provides a new approach for precise prediction of roadway deformation.

Prediction of roadway deformation  /  AE-TCN-Transformer parallel model  /  Temporal convolutional network  /  Alpha evolution algorithm  /  Multi-scale feature fusion
王龙飞, 陈俊智, 任春芳, 蔡川川, 徐晓文, 刘洋, 何昌耀. 基于AE-TCN-Transformer并行模型的巷道变形多步预测研究. 矿业研究与开发, 2026 , 46 (4) : 84 -93 .
Longfei WANG, Junzhi CHEN, Chunfang REN, Chuanchuan CAI, Xiaowen XU, Yang LIU, Changyao HE. Research on Multi-Step Prediction of Roadway Deformation Based on AE-TCN-Transformer Parallel Model[J]. Mining Research and Development, 2026 , 46 (4) : 84 -93 .
Year 2026 volume 46 Issue 4
38
13
Cite this Article
BibTeX
Article Info
  • Receive Date:2025-05-14
  • Online Date:2026-10-29
  • Published:2026-04-25
Article Data
Affiliations
History
  • Received:2025-05-14
Funding
Affiliations
    1.Faculty of Land Resources Engineering, Kunming University of Science and Technology, Kunming, Yunnan 650093, China
    2.Faculty of Public Safety and Emergency Management, Kunming University of Science and Technology, Kunming, Yunnan 650093, China
References
Share
https://castjournals.cast.org.cn/joweb/kyyjykf/EN/
Share to
QR

Scan QR to access full text

Cite this article
BibTeX
Citations
表12种不同金属材料的力学参数
科
Family
属数
Number of
genus
种数
Number of
species
占总种数比例
Percentage of
total species (%)
属
Genus
种数
Number of
species
占总种数比例
Percentage of total
species (%)
鹅膏菌科Amanitaceae 2 11 5.26 鹅膏菌属 Amanita 10 4.78
小菇科 Mycenaceae 2 12 5.74 丝盖伞属 Inocybe 5 2.39
多孔菌科 Polyporaceae 8 14 6.70 蜡蘑属 Laccaria 5 2.39
红菇科 Russulaceae 3 23 11.00 小皮伞属 Marasmius 6 2.87
小菇属 Mycena 11 5.26
光柄菇属 Pluteus 5 2.39
红菇属 Russula 17 8.13
栓菌属 Trametes 5 2.39
关闭全屏
  • BibTeX
  • EndNote
  • RefWorks
  • TxT