Geomechanics and Engineering

Techno-Press (테크노프레스)
권호 표지
DOI QR코드

DOI QR Code

Stability evaluation model for loess deposits based on PCA-PNN

  • Li, Guangkun (Geotechnical and Structural Engineering Research Center, Shandong University) ;
  • Su, Maoxin (Geotechnical and Structural Engineering Research Center, Shandong University) ;
  • Xue, Yiguo (Geotechnical and Structural Engineering Research Center, Shandong University) ;
  • Song, Qian (Geotechnical and Structural Engineering Research Center, Shandong University) ;
  • Qiu, Daohong (Geotechnical and Structural Engineering Research Center, Shandong University) ;
  • Fu, Kang (Geotechnical and Structural Engineering Research Center, Shandong University) ;
  • Wang, Peng (Geotechnical and Structural Engineering Research Center, Shandong University)
  • Received : 2021.01.22
  • Accepted : 2021.10.15
  • Published : 2021.12.25
⟨ Previous Next ⟩

Abstract

Due to the low strength and high compressibility characteristics, the loess deposits tunnels are prone to large deformations and collapse. An accurate stability evaluation for loess deposits is of considerable significance in deformation control and safety work during tunnel construction. 37 groups of representative data based on real loess deposits cases were adopted to establish the stability evaluation model for the tunnel project in Yan'an, China. Physical and mechanical indices, including water content, cohesion, internal friction angle, elastic modulus, and poisson ratio are selected as index system on the stability level of loess. The data set is randomly divided into 80% as the training set and 20% as the test set. Firstly, principal component analysis (PCA) is used to convert the five index system to three linearly independent principal components X1, X2 and X3. Then, the principal components were used as input vectors for probabilistic neural network (PNN) to map the nonlinear relationship between the index system and stability level of loess. Furthermore, Leave-One-Out cross validation was applied for the training set to find the suitable smoothing factor. At last, the established model with the target smoothing factor 0.04 was applied for the test set, and a 100% prediction accuracy rate was obtained. This intelligent classification method for loess deposits can be easily conducted, which has wide potential applications in evaluating loess deposits.

Keywords

Acknowledgement

Research in this paper is supported by the National Natural Science Foundation of China (grant numbers 41877239, 51379112, 51422904, 40902084 and 41772298), and Fundamental Research Fund for the Central Universities (grant number 2018JC044), and Shandong Provincial Natural Science Foundation (grant number JQ201513).

References

  1. Adams, M. (1971), "The single woman in today's society: A reappraisal", Am. J. Orthopsychiatry, 41, 776-786. https://doi.org/10.1111/j.1939-0025.1971.tb00741.x.
  2. Burland, J.B. (1990), "On the compressibility and shear strength of natural clay, Rankine lecture", Geotechnique, 40(3), 329-378. https://doi.org/10.1680/geot.1990.40.3.329.
  3. Chen, M. (2013), "Matlab neural network principles and detailed examples", Tsinghua University Press, Beijing, China
  4. Chen, N., Sun, F.C., Ding, L.G. and Wang, H.Q. (2019), "An adaptive pnn-ds approach to classification using multi-sensor information fusion", Neural Comput. Appl., 31, 693-705. https://doi.org/10.1007/s00521-008-0221-3.
  5. Cochrane, P. and Weatherall, D.J. (1972), "The variation of neutrophil alkaline phosphatase during the menstrual cycle", J. Obstet. Gynaecol. Br. Commonw., 79, 1002-1008, https://doi.org/10.1111/j.1471-0528.1972.tb11878.x.
  6. Cui, G.Y., Ma, J.F. and Wang, D.Y. (2021), "A large 3D laboratory test on the deformation characteristic of shallow loess tunnel under different plastic states", Bull. Eng. Geology Environ., 80, 7577-7590 https://doi.org/10.1007/s10064-021-02375-3
  7. Din, N., Zhang, H. and Saeed, W. (2020), "Porosity prediction from model-based seismic inversion by using probabilistic neural network (pnn) in mehar block, pakistan", Episodes, 43(4), 935-946. https://doi.org/10.18814/epiiugs/2020/020055.
  8. Ding, H.H., Wu, Q., Zhao, D.K., Mu W.P. and Yu, S. (2019), "Risk assessment of karst collapse using an integrated fuzzy analytic hierarchy process and grey relational analysis model", Geomech. Eng., 18(5), 515-525, http://doi.org/10.12989/gae.2019.18.5.515.
  9. Faradonbeh, R.S. and Taheri, A. (2019), "Long-term prediction of rockburst hazard in deep underground openings using three robust data mining techniques", Eng. with Comput., 35, 659-675, https://doi.org/10.1007/s00366-018-0624-4.
  10. Fatemi, S.A., Ahmadi, M. and Rostami, J. (2018), "Evaluation of tbm performance prediction models and sensitivity analysis of input parameters", Bull. Eng. Geology Environ., 77, 501-513. https://doi.org/10.1007/s10064-016-0967-2.
  11. Feda, J. (1988), "Collapse of loess upon wetting", Eng. Geology, 25, 263-269. https://doi.org/10.1016/0013-7952(88)90031-2.
  12. Feng, S.J., Du, F.L., Shi, Z.M., Shui, W.H. and Tan, K. (2015), "Field study on the reinforcement of collapsible loess using dynamic compaction", Eng. Geology, 185, 105-115, https://doi.org/10.1016/j.enggeo.2014.12.006.
  13. Fernandez-Delgado, M., Cernadas, E., Barro, S. and Amorim, D. (2014), "Do we need hundreds of classifiers to solve real world classification problems?", J. Machine Learning Res., 15, 3133-3181
  14. Graziani, A. and Boldini, D. (2012), "Remarks on axisymmetric modeling of deep tunnels in argillaceous formations. I: Plastic clays", Tunn. Undergr. Sp. Tech., 28, 70-79. https://doi.org/10.1016/j.tust.2011.09.006.
  15. Grzymala-Busse, J.W. and Ziarko, W. (2000), "Data mining and rough set theory", Commun. ACM, 43(4), 108-109. https://doi.org/10.1145/332051.332082.
  16. Hotelling, H. (1933), "Analysis of a complex of statistical variables into principal components", J. Educational Psychology, 24, 417-441. https://doi.org/10.1037/h0071325.
  17. Jiang, C., Zhang, H.Y., Zhang, Z.D. and Wang, D.W. (2019), "Model-based assessment soil loss by wind and water erosion in China's Loess Plateau: Dynamic change, conservation effectiveness, and strategies for sustainable restoration", Global Planetary Change, 172, 396-413. https://doi.org/10.1016/j.gloplacha.2018.11.002.
  18. Joshaghani, A., Balapour, M. and Ramezanianpour, A.A. (2018), "Effect of controlled environmental conditions on mechanical, microstructural and durability properties of cement mortar", Constr. Build. Mater., 164, 134-149. https://doi.org/10.1016/j.conbuildmat.2017.12.206.
  19. Kruse, G., Dijkstra, T. and Schokking, F. (2007), "Effects of soil structure on soil behaviour: Illustrated with loess, glacially loaded clay and simulated flaser bedding examples", Eng. Geology, 91, 34-45. https://doi.org/10.1016/j.enggeo.2006.12.011.
  20. Li, Y.R. (2018), "A review of shear and tensile strengths of the malan loess in china", Eng. Geology, 236, 4-10. https://doi.org/10.1016/j.enggeo.2017.02.023.
  21. Lu, Q., Xiao, Z.P., Ji, J., Zheng, J. and Shang, Y.Q. (2017), "Moving least squares method for reliability assessment of rock tunnel excavation considering ground-support interaction", Comput. Geotech., 84, 88-100, https://doi.org/10.1016/j.compgeo.2016.11.019.
  22. Ng, C.W.W., Hong, Y., Liu, G.B. and Liu, T. (2012), "Ground deformations and soil-structure interaction of a multi-propped excavation in shanghai soft clays", Geotechnique, 62, 907-921, https://doi.org/10.1680/geot.10.P.072.
  23. Pu, Y.Y., Apel, D.B. and Xu, H.W. (2019), "Rockburst prediction in kimberlite with unsupervised learning method and support vector classifier", Tunn. Undergr. Sp. Tech., 90, 12-18. https://doi.org/10.1016/j.tust.2019.04.019.
  24. Pawlak, Z. (1998), "Rough set theory and its applications to data analysis", Cybernetics Syst., 29(7), 661-688. https://doi.org/10.1080/019697298125470.
  25. Ren, X. and Yu, X. (2011), "Multivariate statistical analysis (Version 2)", China Statistics Press, Beijing, China
  26. Ren, X.C., Lai, Y.M., Zhang, F.Y. and Hu, K. (2015), "Test method for determination of optimum moisture content of soil and maximum dry density", Ksce J. Civil Eng., 19, 2061-2066. https://doi.org/10.1007/s12205-015-0163-0.
  27. Rogers, CDF., Dijkstra, T.A. and Smalley, I.J. (1994), "Particle packing from an earth-science viewpoint", Earth-Sci. Reviews, 36, 59-82. https://doi.org/10.1016/0012-8252(94)90008-6.
  28. Sharifzadeh, M., Kolivand, F., Ghorbani, M. and Yasrobi, S. (2013), "Design of sequential excavation method for large span urban tunnels in soft ground-Niayesh tunnel", Tunn. Undergr. Sp. Tech., 35, 178-188. https://doi.org/10.1016/j.tust.2013.01.002
  29. Specht, D.F. (1990), "Probabilistic neural networks and the polynomial adaline as complementary techniques for classification", IEEE T. Neural Networ., 1, 111-121, https://doi.org/10.1109/72.80210
  30. Tuo, D.F., Xu, M.X., Li, Q. and Liu, S.H. (2017), "Soil aggregate stability and associated structure affected by long-term fertilization for a loessial soil on the loess plateau of china", Polish J. Environ. Studies, 26, 827-835. https://doi.org/10.15244/pjoes/66716.
  31. Wang, C.L., Li, C.F., Chen, Z., Liao, Z.F., Zhao, G.M., Shi, F. and Yu, W.J. (2020), "Experimental investigation on multi-parameter classification predicting degradation model for rock failure using bayesian method", Geomech. Eng., 20(2), 113-120. https://doi.org/10.12989/gae.2020.20.2.113
  32. Witten, I.H. and Frank, E. (2002), "Data mining: Practical machine learning tools and techniques with Java implementations", ACM SIGMOD Record, 31(1), 76-77, https://doi.org/10.1145/507338.507355.
  33. Xie, Z. (2010), "Matlab statistical analysis and application: 40 case studies", Beihang University Press, Beijing,China
  34. Xu, Z.G., Cai, N.G., Li, X.F., Xian, M.T. and Dong, T.W. (2021), "Risk assessment of loess tunnel collapse during construction based on an attribute recognition model", Bull. Eng. Geology Environ., 80, 6205-6220. https://doi.org/10.1007/s10064-021-02300-8.
  35. Xue, Y., Zhang, X., Li, S., Qiu, D., Su, M., Li, L., Li, Z. and Tao, Y. (2018a), "Analysis of factors influencing tunnel deformation in loess deposits by data mining: A deformation prediction model", Eng. Geology, 232, 94-103. https://doi.org/10.1016/j.enggeo.2017.11.014
  36. Xue, Y.G., Bai, C.H., Qiu, D.H., Kong, F.M. and Li, Z.Q. (2020) "Predicting rockburst with database using particle swarm optimization and extreme learning machine", Tunn. Undergr. Sp. Tech., 98, https://doi.org/10.1016/j.tust.2020.103287.
  37. Xue, Y.G., Zhang, X.L., Li, S.C., Qiu, D.H., Su, M.X., Li, L.P., Li, Z.Q. and Tao, Y.F. (2018b), "Analysis of factors influencing tunnel deformation in loess deposits by data mining: A deformation prediction model", Eng. Geology, 232, 94-103. https://doi.org/10.1016/j.enggeo.2017.11.014.
  38. Yates, K., Fenton, C.H. and Bell, D.H. (2018), "A review of the geotechnical characteristics of loess and loess-derived soils from canterbury, south island, new Zealand", Eng. Geology, 236, 11-21, https://doi.org/10.1016/j.enggeo.2017.08.001.
  39. Zhang, C.F., Peng, K.X. and Dong, J. (2020), "An incipient fault detection and self-learning identification method based on robust svdd and rbm-pnn", J. Process Control, 85, 173-183, https://doi.org/10.1016/j.jprocont.2019.12.002.
  40. Zhang, X.L., Xue, Y.G., Qiu, D.H., Yang, W.M., Su, M.X., Li, Z.Q. and Zhou, B.H. (2019), "Multi-index classification model for loess deposits based on rough set and bp neural network", Polish J. Environ. Studies, 28, 953-963, https://doi.org/10.15244/pjoes/85303.
  41. Zhao, Y., Li, G. and Yu, Y. (2011), "Loess tunnel engineering", China Railway Press, Beijing, China.
  42. Ziegel, E.R. (2005), "Discovering knowledge in data/next generation of data-mining applications", Technometrics, 47(4), 528-529.
  43. Zhou, B.H., Xue, Y.G., Li, S., Qiu, D., Tao, Y., Zhang, K. and Xia, T. (2020), "Probabilistic analysis of tunnel collapse: Bayesian method for detecting change points", Geomech. Eng., 22(4), 291-303. https://doi.org/10.12989/gae.2020.22.4.291.