Reliability Analysis of Layered Soil Slope Stability using ANFIS and MARS Soft Computing Techniques

2021 ◽  
Vol 17 (7) ◽  
pp. 647
Author(s):  
Ray Rahul ◽  
Choudhary Shiva Shankar ◽  
Roy Lal Bahadur
Keyword(s):  
Slope Stability ◽  
Reliability Analysis ◽  
Soft Computing ◽  
Layered Soil ◽  
Soil Slope ◽  
Soft Computing Techniques

Reliability analysis of soil slope stability using ANFIS soft computing technique

2021 ◽  
pp. 180-187
Author(s):  
Rahul Ray ◽  
Lal Bahadur Roy ◽  
Shiva Shankar Choudhary
Keyword(s):  
Slope Stability ◽  
Soft Computing ◽  
Probabilistic Approach ◽  
Model Performance ◽  
Unit Weight ◽  
Research Approach ◽  
Soil Slope ◽  
Inference System ◽  
Computing Technique ◽  
Soft Computing Technique

Soil is a heterogeneous medium and due to which the parameters on which soil slope stability depends are having high variability, which makes the analysis a complex problem. With time to take into account the variability in soil parameter the research approach has shifted from deterministic approach towards the probabilistic approach. This paper describes the application of probabilistic approach using soft-computing technique i.e. Adaptive Network Fuzzy Inference System (ANFIS) to study the soil slope reliability based on slope stability. The slope stability of soil depends on the parameters c (cohesion), ? (angle of shearing resistance) and ? (unit weight), which are taken as input variables and Factor of Safety of soil slope (FOS) as output. Also the model performance assessed using performance indices i.e. R2, VAF, MAPE, RPD, RMSE etc. The results analysis showed that ANFIS performed good. Therefore, ANFIS can be used as reliable soft computing technique for analyzing slope stability of soil.

scholarly journals Reliability Analysis of Pile Foundation Using Soft Computing Techniques: A Comparative Study

Processes ◽  
2021 ◽  
Vol 9 (3) ◽  
pp. 486
Author(s):  
Manish Kumar ◽  
Abidhan Bardhan ◽  
Pijush Samui ◽  
Jong Wan Hu ◽  
Mosbeh R. Kaloop
Keyword(s):  
Comparative Study ◽  
Bearing Capacity ◽  
Reliability Analysis ◽  
Soft Computing ◽  
Pile Foundation ◽  
Group Method ◽  
Anfis Model ◽  
Inference System ◽  
Reliability Indices ◽  
Soft Computing Techniques

Uncertainty and variability are inherent to pile design and consequently, there have been considerable researches in quantifying the reliability or probability of failure of structures. This paper aims at examining and comparing the applicability and adaptability of Minimax Probability Machine Regression (MPMR), Emotional Neural Network (ENN), Group Method of Data Handling (GMDH), and Adaptive Neuro-Fuzzy Inference System (ANFIS) in the reliability analysis of pile embedded in cohesionless soil and proposes an AI-based prediction method for bearing capacity of pile foundation. To ascertain the homogeneity and distribution of the datasets, Mann–Whitney U (M–W) and Anderson–Darling (AD) tests are carried out, respectively. The performance of the developed soft computing models is ascertained using various statistical parameters. A comparative study is implemented among reliability indices of the proposed models by employing First Order Second Moment Method (FOSM). The results of FOSM showed that the ANFIS approach outperformed other models for reliability analysis of bearing capacity of pile and ENN is the worst performing model. The value of R2 for all the developed models is close to 1. The best RMSE value is achieved for the training phase of the ANFIS model (0 in training and 2.13 in testing) and the poorest for the ENN (2.03 in training and 31.24 in testing) model. Based on the experimental results of reliability indices, the developed ANFIS model is found to be very close to that computed from the original data.

Sign in / Sign up

Export Citation Format

Share Document