收藏切换
Prediction of Uniaxial Compressive Strength of Rocks Based on Multi Algorithm Comparison
收藏切换
Yajuan WU1, 2, Dexin HUANG1, 2, Tao WEN1, 2, 3, Wenjun JIA1, 2
Mining Research and Development | 2025, 45(11) : 141 - 150
Less
收藏切换
Mining Research and Development | 2025, 45(11): 141-150
Prediction of Uniaxial Compressive Strength of Rocks Based on Multi Algorithm Comparison
Full
Yajuan WU1, 2, Dexin HUANG1, 2, Tao WEN1, 2, 3, Wenjun JIA1, 2
Affiliations
  • 1.School of Geosciences, Yangtze University, Wuhan, Hubei 430100, China
  • 2.International Cooperation Center for Mountain Multi-Disasters Prevention and Engineering Safety, Wuhan, Hubei 430100, China
  • 3.Jiacha County Branch of Hubei Yangtze University Technology Development Co., Ltd., Shannan, Xizang 856499, China
Published: 2025-11-25
Outline
收藏切换

Reasonably and effectively determining the uniaxial compressive strength of rocks is of great significance for ensuring the safety of mining rock engineering. Based on two groups of rock uniaxial compressive strength datasets including longitudinal wave velocity, Schmidt hammer rebound value, point load strength, Schmidt hardness, and other indirect indicators, four combination algorithms including PSO-BP, PSO-LSTM, CNN-LSTM, and PSO-BILSTM, were selected. And the optimal rock uniaxial compressive strength prediction algorithm was comprehensively evaluated through 7 evaluation indicators. The results show that the PSO-LSTM algorithm fits well with the predicted values and actual values on two datasets, and all evaluation indicators are high. Based on the metric scoring method to quantitatively analyze the predictive performance of various algorithms, PSO-LSTM can achieve a total high score of 27 and 21 on Dataset 1 and Dataset 2, respectively, demonstrating the highest prediction accuracy. The analysis of input parameter correlation shows that the point load strength has the greatest impact on the prediction of uniaxial compressive strength in Dataset 1, with a correlation degree of 0.735 5. The tensile strength has the greatest impact on the prediction of uniaxial compressive strength in Dataset 2, with a correlation coefficient of 0.829 2. Meanwhile, the predictive performance of each algorithm in Dataset 2 is better, indicating that using input parameters with high correlation with uniaxial compressive strength can effectively improve the predictive performance. The research results can provide a reference for determining the uniaxial compressive strength of rocks.

Uniaxial compressive strength  /  Algorithm prediction  /  PSO-LETM  /  Correlation  /  Indirect indicator
吴亚娟, 黄德昕, 温韬, 贾文君. 基于多算法对比的岩石单轴抗压强度预测. 矿业研究与开发, 2025 , 45 (11) : 141 -150 .
Yajuan WU, Dexin HUANG, Tao WEN, Wenjun JIA. Prediction of Uniaxial Compressive Strength of Rocks Based on Multi Algorithm Comparison[J]. Mining Research and Development, 2025 , 45 (11) : 141 -150 .
Year 2025 volume 45 Issue 11
109
49
Cite this Article
BibTeX
Article Info
  • Receive Date:2024-12-19
  • Online Date:2026-10-28
  • Published:2025-11-25
Article Data
Affiliations
History
  • Received:2024-12-19
Funding
Affiliations
    1.School of Geosciences, Yangtze University, Wuhan, Hubei 430100, China
    2.International Cooperation Center for Mountain Multi-Disasters Prevention and Engineering Safety, Wuhan, Hubei 430100, China
    3.Jiacha County Branch of Hubei Yangtze University Technology Development Co., Ltd., Shannan, Xizang 856499, 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