ANN and Neuro-Fuzzy Modeling for Shear Strength Characterization of Soils
- PDF / 630,696 Bytes
- 7 Pages / 595.276 x 790.866 pts Page_size
- 76 Downloads / 145 Views
RESEARCH ARTICLE
ANN and Neuro-Fuzzy Modeling for Shear Strength Characterization of Soils Kumar Venkatesh1
· Yeetendra Kumar Bind2
Received: 24 January 2019 / Revised: 9 August 2020 / Accepted: 12 August 2020 © The National Academy of Sciences, India 2020
Abstract We examine the outcome of popular artificial neural network (ANN) and adaptive neuro-fuzzy inference system (ANFIS) for estimating the shear strength parameters of c−φ soil. A matrix of one hundred twelve datasets collected using in situ and laboratory tests to train and test the ANN and ANFIS models. Standard penetration test number of blows value along with the soil properties taken as input vectors, whereas shear strength parameters like cohesion (c) and angle of internal friction (ϕ) used as target vectors. The minimum validation error has been employed as the stopping criterion to avoid over fitting in the analysis. Out of four developed models, predicted values through two ANN models were close to actual value in comparison to ANFIS models. Statistical parameters such as coefficient of correlation, root mean square error and average absolute error were used as performance evaluation measures. Based on statistical measures it was observed that performances of ANN and ANFIS models were in accordance with the experimental results and it could substitute tedious laboratory work provided sufficient and reliable data source are offered. The results through performance evaluation measures also reveal that ANN and ANFIS models are effective, versatile and useful way to measure the shear strength parameters of soils. Keywords ANN · ANFIS · Shear strength · Cohesion · Angle of internal friction · Soils
& Kumar Venkatesh [email protected] 1
Department of Civil Engineering, Motilal Nehru National Institute of Technology Allahabad, Prayagraj, India
2
Department of Civil Engineering, SHUATS, Prayagraj, India
1 Introduction Soil derives its shear strength from two sources, cohesion and frictional resistance. Where, cohesion is stress independent component but friction is stress dependent component. Therefore, shear strength parameters, i.e., cohesion and angle of internal friction are largely influenced by physical and engineering properties of soil [1–3]. Conventional methods are not capable of including such a large soil property catalog in characterizing shear strength of soil, whereas computational methods are gaining popularity these days because of its capability and robustness while working with massive input problem domain. Present study is the upcoming of applying such techniques like artificial neural network (ANN) and neurofuzzy system to study the effect of soil properties on shear strength parameters. Though variety of ANN and neurofuzzy methods (depending on anatomy of connection) are available but well known back propagation neural network (BPNN) and ANFIS neuro-fuzzy method are applied in this study. ANFIS embodies so-called Sugeno or Takagi– Sugeno–Kang (TSK) [4] method of fuzzy inference system (FIS) to develop adaptive neuro-fuzzy
Data Loading...
