Developing a hybrid adoptive neuro-fuzzy inference system in predicting safety of factors of slopes subjected to surface eco-protection techniques

• Published in: Engineering with computers 2020-10, Vol.36 (4), p.1347-1354
• Main Authors: Sari, Puteri Azura, Suhatril, Meldi, Osman, Normaniza, Mu’azu, M. A., Katebi, Javad, Abavisani, Ali, Ghaffari, Naser, Sadeghi Chahnasir, Esmaeil, Wakil, Karzan, Khorami, Majid, Petkovic, Dalibor
• Format: Article
• Language: English
• Subjects: Adaptive systems; Artificial neural networks; CAE) and Design; Calculus of Variations and Optimal Control; Optimization; Classical Mechanics; Computer Science; Computer-Aided Engineering (CAD; Control; Disasters; Fuzzy logic; Fuzzy systems; Hybrid systems; Inference; Landslides; Math. Applications in Chemistry; Mathematical and Computational Engineering; Neural networks; Original Article; Performance prediction; Probabilistic models; Safety; Slope stability; Slopes; Soil erosion; Soil investigations; Soil properties; Structural stability; Systems Theory
• ISSN: 0177-0667; 1435-5663
• DOI: 10.1007/s00366-019-00768-3

This study predicts the investigation of surface eco-protection techniques for cohesive soil slopes along the selected Guthrie Corridor Expressway stretch by way of analyzing a new set of probabilistic models using a hybrid technique of artificial neural network and fuzzy inference system namely adaptive neuro-fuzzy inference system (ANFIS). Soil erosion and mass movement which induce landslides have become one of the disasters faced in Selangor, Malaysia causing enormous loss affecting human lives, destruction of property and the environment. Establishing and maintaining slope stability using mechanical structures are costly. Hence, biotechnical slope protection offers an alternative which is not only cost effective but also aesthetically pleasing. A parametric study was carried out to discover the relationship between various eco-protection techniques, i.e., application of grasses, shrubs and trees with different soil properties as well as slope angles. Then the data have been used to develop a new hybrid ANFIS technique for prediction of factor of safety (FOS) of slopes. Four inputs were considered in relation to the different vegetation types, i.e., slope angle ( θ ), unit weight ( γ ), effective cohesion ( c ′), effective friction angle (ø′). Then, many hybrid ANFIS models were constructed, trained and tested using various parametric studies. Eventually, a hybrid ANFIS model with a high performance prediction and a low system error was developed and introduced for solving problem of slope stability.