Determination of strength and modulus of elasticity of heterogenous sedimentary rocks: An ANFIS predictive technique. (October 2018)

• Record Type: Journal Article
• Authors: Umrao, Ravi Kumar; Sharma, L.K.; Singh, Rajesh; Singh, T.N.
• Is Part Of: Measurement. Volume 126(2018)
• Page Start: 194
• Page End: 201
• Publication Date: 2018-10
• Subjects: ANFIS -- Modulus of elasticity -- Unconfined compressive strength -- RMSE -- VAF; Weights and measures -- Periodicals; Measurement -- Periodicals; Measurement; Weights and measures; Periodicals; 530.8
• DOI: 10.1016/j.measurement.2018.05.064
• Languages: English
• ISSNs: 0263-2241

Abstract

Graphical abstract: Highlights: Prediction of UCS and E using density, porosity and Vp. Effect of input and output membership functions type on the performance of model. All proposed models stand statistically excellent through four performance indices. Proposed ANFIS models have superb predictability even in less datasets. Abstract: The properties of sedimentary rocks, in term of strength and deformation, are significant for various purposes in different fields such as in mine planning and design, reservoir stability evaluation, surface and sub-surface structure designs. This study proposes suitable predictive models for estimation of unconfined compressive strength (UCS) and modulus of elasticity (E) of sedimentary rocks using easy and economically determinable key geomechanical properties. A total of 45 dataset of geomechanical properties including density, porosity, P-wave velocity (Vp), UCS and E were determined through rigorous laboratory tests on samples from Umrer sandstone, Singrauli sandstone and Kutch limestone. In proposed predictive models, density, porosity and Vp were considered as input parameters for prediction of output parameters (UCS and E) using adaptive neuro-fuzzy inference system (ANFIS). The prediction performance of ANFIS models checked through evaluating different membership functions. The suitability of models and their robustness examined by the coefficient of determination ( R 2 ), and performance indices such as the mean absolute percentage error (MAPE), variance account for (VAF) and root mean square error (RMSE). Among the five proposed models for UCS, the model 3 was best suited with performance indices MAPE, VAF, and RMSE calculated as 16.53%, 95.60%, and 4.69 respectively and R 2 equal to 0.935. Model 3 was best suited for the proposed models for E with MAPE, VAF, and RMSE calculated as 17.84%, 95.43%, and 2.26 respectively and R 2 equal to 0.955. The high-performance indices and R 2 of proposed models for UCS and E of sedimentary rocks using ANFIS can be confidently used in the field of geotechnical engineering.