Rock and Soil Mechanics ›› 2023, Vol. 44 ›› Issue (10): 3022-3030.doi: 10.16285/j.rsm.2023.5209

Previous Articles     Next Articles

Prediction of consolidation coefficient of soft soil using an artificial neural network models with biogeography-based optimization

WANG Cai-jin1, WU Meng1, YANG Yang2, CAI Guo-jun1, 3, LIU Song-yu1, HE Huan1, CHANG Jian-xin1   

  1. 1. Institute of Geotechnical Engineering, Southeast University, Nanjing, Jiangsu 211189, China 2. Jiangsu Province Transportation Engineering Construction Bureau, Nanjing, Jiangsu 210004, China; 3. School of Civil Engineering, Anhui Jianzhu University, Hefei, Anhui 230601, China
  • Online:2023-10-21 Published:2023-12-30
  • Contact: CAI Guo-jun, male, born in 1977, PhD, Professor, research interests: in in-situ testing and environmental geotechnical engineering. E-mail:
  • About author:WANG Cai-jin, male, born in 1995, PhD candidate, focusing on in-situ testing and thermal conduction.
  • Supported by:
    the National Science Fund for Distinguished Young Scholars (42225206), the National Natural Science Foundation of China (41877231, 42072299, 52008098), the Jiangsu Province Natural Science Fund (BK20200405) and the Project of Jiangsu Province Transportation Engineering Construction Bureau (7921004042B).

Abstract: The consolidation coefficient Cv of soft soil is an important parameter in geotechnical engineering. The artificial neural network (ANN) model is improved with the biogeography-based optimization algorithm (BBO). And the artificial neural network with biogeography-based optimization (ANN-BBO) model, trained and tested by using the subgrade soft soil data of the reconstruction and expansion project of Lianyungang–Huai’an expressway, has been adopted to calculate the soft soil consolidation coefficient. Using the correlation coefficient matrix and principal component analysis, eleven physical and mechanical parameters were statistically analyzed, seven of which were identified as input parameters of calculation model which was then trained and tested. The model was tested by correlation coefficient, root mean square error, and variance ratio, whose robustness was analyzed by using Monte Carlo simulation. The results show that the ANN-BBO model can be used to calculate the consolidation coefficient of soft soil, the correlation coefficient R2 = 0.947 1, the root mean square error RMSE = 0.165 7×10−3 cm2 /s, and the variance ratio VAF = 94.54%. The ANN-BBO model has significantly higher prediction accuracy and better robustness, compared with the ANN model.

Key words: soft soil, consolidation coefficient, artificial neural network, principal component analysis, robustness