Siyuan Wang
ABSTRACT
Plasticity index is essential for engineering applications, obtaining which would be carried out from situ-fields to the laboratory costly and time-consuming. Cone penetration tests (CPTs), fast, low-cost, reliable and output near-continuous measurement, are widely used in geological and geotechnical engineering, and shallow neural networks can learn and build models of complex nonlinear relationships. This paper presents a methodology of predicting soil plasticity index by CPT using optimized artificial neural networks (SNNs) for reducing laboratory work that represents a significant saving of both time and money. Gathered from fields in Western Henan province in central China, 237 sets of laboratory results and CPT tests divided into 20 groups were used to train, test, and validate the optimization ANN models with single and double hidden layers. A criterion ensuring without underfitting or overfitting is set up by regression coefficient distribution. The optimization covers 12 train functions, four process functions, divide functions and divide models, 2 to 20 neurons selected for two hidden layers. Of the results with double hidden layers, the largest minimum and 2-norm regression coefficients and the least maximum and 2-norm mean square errors are 0.640, 1.318 and 0.775, 1.078 individually, which distinctly larger than the corresponding values in with a single layer, thus indicates improved performances. The influence on the regression values and MSEs is presented.
- Arama ZA, Yücel M, Akın MS, Nuray SE and Alten O. 2020. Prediction of Soil Plasticity Index with the Use of Regression Analysis and Artificial Neural Networks: A Specific Case for Bakırköy District. International Conference on Harmony Search Algorithm. Springer, Singapore, 281-293Google Scholar
- Ghaderi A, Abbaszadeh Shahri A and Larsson S. 2018. An artificial neural network based model to predict spatial soil type distribution using piezocone penetration test data (CPTu). Bulletin of Engineering Geology and the Environment.78(6):4579-88.Google ScholarCross Ref
- Farhadi MS and Länsivaara T. 2021. Development of an integrated game theory-optimization subground stratification model using cone penetration test (CPT) measurements. Engineering with Computers. Jan (21):1-6Google Scholar
- Alshibli KA, Okeil AM, Alramahi B and Zhang Z. 2009. Statistical assessment of repeatability of CPT measurements. Contemporary Topics in In Situ Testing, Analysis, and Reliability of Foundations. 87-94.Google ScholarCross Ref
- Bong T and Stuedlein AW. 2018. Effect of Cone Penetration Conditioning on Random Field Model Parameters and Impact of Spatial Variability on Liquefaction-Induced Differential Settlements. Journal of Geotechnical and Geoenvironmental Engineering, 144(5), 04018018–. doi:10.1061/(ASCE)GT.1943-5606.0001863 Journal of Geotechnical and Geoenvironmental Engineering. 2018;144(5):04018018.Google ScholarCross Ref
- Hird CC and Springman SM. 2006. Comparative performance of 5 cm2 and 10 cm2 piezocones in a lacustrine clay. Géotechnique.56(6):12Google ScholarCross Ref
- T L and P M. 2007. Stratigraphic delineation by three dimensional clustering of piezocone data. Georisk. 1(2):18.Google Scholar
- Robertson P. 2016. CPT-based Soil Behaviour Type (SBT) Classification System –an update Canadian Geotechnical Journal.53(12):18.Google Scholar
- Shahri AA. 2016. An optimized artificial neural network structure to predict clay sensitivity in a high landslide prone area using piezocone penetration test (CPTu) data: a case study in southwest of Sweden. Geotechnical and Geological Engineering. 34(2):745-58.Google ScholarCross Ref
- Kurup PU and Griffin EP. 2006. Prediction of soil composition from CPT data using general regression neural network. Journal of Computing in Civil Engineering. 20(4):281-9.Google ScholarCross Ref
- Zhu A-X, Yang L, Li B, Qin C, Pei T and Liu B. 2010. Construction of membership functions for predictive soil mapping under fuzzy logic. Geoderma. 155(3-4):164-74.Google ScholarCross Ref
- Pásztor L, Laborczi A, Takács K, Szatmári G, Fodor N, Illés G, 2017. Compilation of functional soil maps for the support of spatial planning and land management in Hungary. Soil Mapping and Process Modeling for Sustainable Land Use Management: Elsevier. Jan (1):293-317.Google Scholar
- Choobbasti A, Farrokhzad F, Rahim Mashaie S and Azar P. 2015. Mapping of soil layers using artificial neural network (case study of Babol, northern Iran). Journal of the South African Institution of Civil Engineering. 57(1):59-66.Google ScholarCross Ref
- Arel E. 2012. Predicting the spatial distribution of soil profile in Adapazari/Turkey by artificial neural networks using CPT data. Computers & Geosciences. 43:90-100.Google ScholarDigital Library
- Reale C, Gavin K, Librić L and Jurić-Kaćunić D. 2018. Automatic classification of fine-grained soils using CPT measurements and Artificial Neural Networks. Advanced Engineering Informatics. 36:207-15.Google ScholarCross Ref
- DO O. 2014. An intelligent system for soil classification using supervised learning approach. J Comput Eng Intell Syst. 5(11):12.Google Scholar
- B B and DP S. 2006. Machine learning in soil classification. J Neural Netw. 29(2):10.Google Scholar
- Kanwar N, Goswami AK and Mishra S. 2019. Design Issues in Artificial Neural Network (ANN). 2019 4th International Conference on Internet of Things: Smart Innovation and Usages (IoT-SIU). IEEE. Apr (18):1-4.Google Scholar
- Robertson PK. 2009. Interpretation of cone penetration tests—a unified approach. Canadian geotechnical journal. 46(11):1337-55.Google Scholar
- Robertson P. 1991. Soil classification using the cone penetration test: Reply. Canadian Geotechnical Journal. 28(1):176-8.Google ScholarCross Ref
- Shallow-neural-network Optimization for Predicting Plasticity Index of Loess with Cone Penetration Test Data
Recommendations
Cultural Particle Swarm Optimization Neural Network and Its Application in Soft-Sensing Modeling
ICNC '09: Proceedings of the 2009 Fifth International Conference on Natural Computation - Volume 03Combining particle swarm optimization algorithm (PSO) with cultural algorithm (CA), a new cultural particle swarm optimization algorithm (CPSO) is proposed by this paper. Then, Both CPSO and PSO are used to resolve the optimization problems of five ...
Towards XAI: Interpretable Shallow Neural Network Used to Model HCP’s fMRI Motor Paradigm Data
Bioinformatics and Biomedical EngineeringAbstractUnder the concept of explainable artificial intelligence (XAI), this study explores the usage of shallow neural networks (SNN) to model and predict motor processes in the brain. Two main goals are considered: the suitability of independent ...
Modeling Axonal Plasticity in Artificial Neural Networks
AbstractAxonal growth and pruning are the brain’s primary method of controlling the structured sparsity of its neural circuits. Without long-distance axon branches connecting distal neurons, no direct communication is possible. Artificial neural networks ...
Comments