A platform for research: civil engineering, architecture and urbanism
A platform for research: civil engineering, architecture and urbanism
Prediction of Shear Modulus from Adaptive Neuro-fuzzy Inference System
https://orcid.org/http://orcid.org/0000-0002-7583-374X
https://orcid.org/http://orcid.org/0000-0002-8921-2979
Shear modulus (G) of soil is an important parameter in considering the effect of soil–structure interaction while analyzing the response of structure against earthquake motions. Cyclic tri-axial test gives best laboratory results for shear modulus. However, this test is expensive and has to be conducted for many days continuously. In general, shear modulus is related to mass density of soil and shear wave velocity of the soil strata. In the present study, adaptive neuro-fuzzy inference system (ANFIS) is developed for the prediction of shear modulus of the soil. For this system, input parameters are Dry Density, Moisture Content and SPT-N value of soil. ANFIS model is used for automated rule generation and parameter optimization. For this research, vast data of shear modulus from different site locations were used and trained for three models. The results have shown that the ANFIS model is the best choice for the prediction of the shear modulus and represent the relationship between soil properties and shear modulus.
Prediction of Shear Modulus from Adaptive Neuro-fuzzy Inference System
https://orcid.org/http://orcid.org/0000-0002-7583-374X
https://orcid.org/http://orcid.org/0000-0002-8921-2979
Shear modulus (G) of soil is an important parameter in considering the effect of soil–structure interaction while analyzing the response of structure against earthquake motions. Cyclic tri-axial test gives best laboratory results for shear modulus. However, this test is expensive and has to be conducted for many days continuously. In general, shear modulus is related to mass density of soil and shear wave velocity of the soil strata. In the present study, adaptive neuro-fuzzy inference system (ANFIS) is developed for the prediction of shear modulus of the soil. For this system, input parameters are Dry Density, Moisture Content and SPT-N value of soil. ANFIS model is used for automated rule generation and parameter optimization. For this research, vast data of shear modulus from different site locations were used and trained for three models. The results have shown that the ANFIS model is the best choice for the prediction of the shear modulus and represent the relationship between soil properties and shear modulus.
Prediction of Shear Modulus from Adaptive Neuro-fuzzy Inference System
https://orcid.org/http://orcid.org/0000-0002-7583-374X
https://orcid.org/http://orcid.org/0000-0002-8921-2979
Shear modulus (G) of soil is an important parameter in considering the effect of soil–structure interaction while analyzing the response of structure against earthquake motions. Cyclic tri-axial test gives best laboratory results for shear modulus. However, this test is expensive and has to be conducted for many days continuously. In general, shear modulus is related to mass density of soil and shear wave velocity of the soil strata. In the present study, adaptive neuro-fuzzy inference system (ANFIS) is developed for the prediction of shear modulus of the soil. For this system, input parameters are Dry Density, Moisture Content and SPT-N value of soil. ANFIS model is used for automated rule generation and parameter optimization. For this research, vast data of shear modulus from different site locations were used and trained for three models. The results have shown that the ANFIS model is the best choice for the prediction of the shear modulus and represent the relationship between soil properties and shear modulus.
Prediction of Shear Modulus from Adaptive Neuro-fuzzy Inference System
Lecture Notes in Civil Engineering
Latha Gali, Madhavi (editor) / P., Raghuveer Rao (editor) / Phani Kumar, V. (author) / Saikiran, K. (author)
2020-09-19
9 pages
Article/Chapter (Book)
Electronic Resource
English
Prediction of concrete elastic modulus using adaptive neuro-fuzzy inference system
| Online Contents | 2006
Prediction of concrete elastic modulus using adaptive neuro-fuzzy inference system
| British Library Online Contents | 2006