scholarly journals Application of modern methods: modeling of sedimentary soil ESP content

2019 ◽  
Author(s):  
Sorush Niknamian
Keyword(s):  
Fuzzy Inference ◽  
Evaluation Criteria ◽  
Exchange Capacity ◽  
Fuzzy Inference Systems ◽  
Sodic Soils ◽  
Connection Weight ◽  
Neuro Fuzzy ◽  
Weight Method ◽  
Inference Systems ◽  
Clay Percentage

Knowing the exchangeable sodium percentage (ESP) variations and its values in sodic or saline-sodic soils is essential in order to estimate the amount of soil amendments and better land management. ESP calculated from cation exchange capacity (CEC), and since CEC measurement is difficult and time-consuming, ESP computation is costly and subject to error. Thus, presenting a method to estimate ESP indirectly, by an easily available index is much more efficient and economical. In this study, 296 soil samples collected and analyzed from Sistan plain, southeastern Iran. Soil ESP were predicted by using artificial neural networks (ANNs), comprising radial basis functions (RBFN) and multilayer perceptron (MLP) and adaptive neuro-fuzzy inference systems (ANFIS), and results compared with stepwise linear regression (SLR) method. Results indicated that the SLR models performed poorly in order to estimate ESP (R2 ≤ 0.58 and root mean square error (RMSE ≥ 4.31). Applying fewer inputs (electrical conductivity (EC and pH), ANFIS showed better results (R2=0.80, RMSE=2.34), while increasing inputs (clay and organic carbon) decreased the accuracy (R2=0.82, RMSE=4.20). Using more inputs, RBFN resulted in better performance in comparison with other methods (R2=0.83, RMSE=2.85). Sensitivity analysis using the connection weight method demonstrated that EC, pH, clay percentage and bulk density are the most important variables in order to explain ESP variability in the region, respectively. Generally, considering the evaluation criteria and the number of used variables of models, ANFIS (with EC and pH as inputs) is the most appropriate method for estimating ESP in Sistan plain.

scholarly journals Application of Modern Methods: Modeling of Sedimentary Soil ESP Content

2019 ◽  
Vol 1 (1) ◽  
pp. 1-17
Author(s):  
Sorush Niknamian
Keyword(s):  
Linear Regression ◽  
Fuzzy Inference ◽  
Evaluation Criteria ◽  
Exchange Capacity ◽  
Linear Regression Method ◽  
Linear Regression Models ◽  
Sodic Soils ◽  
Connection Weight ◽  
Inference Systems ◽  
Clay Percentage

Knowing the exchangeable sodium percentage (ESP) variations and its values in sodic or saline-sodic soils is essential in order to estimate the amount of soil amendments and better land management. ESP calculated from cation exchange capacity (CEC), and since CEC measurement is difficult and time-consuming, ESP computation is costly and subject to error. Thus, presenting a method to estimate ESP indirectly, by an easily available index is much more efficient and economical. In this study, 296 soil samples collected and analyzed from Sistan plain, southeastern Iran. Soil ESP were predicted by using artificial neural networks, comprising radial basis functions (RBFN) and multilayer perceptron (MLP) and adaptive neuro-fuzzy inference systems (ANFIS), and results compared with stepwise linear regression method. Results indicated that the linear regression models performed poorly in order to estimate ESP (R2 ≤ 0.58 and root mean square error (RMSE) ≥ 4.31). Applying fewer inputs (electrical conductivity (EC) and pH), ANFIS showed better results (R2=0.80, RMSE=2.34), while increasing inputs (clay and organic carbon) decreased the accuracy (R2=0.82, RMSE=4.20). Using more inputs, RBFN resulted in better performance in comparison with other methods (R2=0.83, RMSE=2.85). Sensitivity analysis using the connection weight method demonstrated that EC, pH, clay percentage and bulk density are the most important variables in order to explain ESP variability in the region, respectively. Generally, considering the evaluation criteria and the number of used variables of models, ANFIS (with EC and pH as inputs) is the most appropriate method for estimating ESP in Sistan plain.

scholarly journals Application of modern methods: modeling of sedimentary soil ESP content

2019 ◽  
Author(s):  
Sorush Niknamian
Keyword(s):  
Linear Regression ◽  
Fuzzy Inference ◽  
Evaluation Criteria ◽  
Exchange Capacity ◽  
Linear Regression Method ◽  
Linear Regression Models ◽  
Sodic Soils ◽  
Connection Weight ◽  
Inference Systems ◽  
Clay Percentage

Knowing the exchangeable sodium percentage (ESP) variations and its values in sodic or saline-sodic soils is essential in order to estimate the amount of soil amendments and better land management. ESP calculated from cation exchange capacity (CEC), and since CEC measurement is difficult and time-consuming, ESP computation is costly and subject to error. Thus, presenting a method to estimate ESP indirectly, by an easily available index is much more efficient and economical. In this study, 296 soil samples collected and analyzed from Sistan plain, southeastern Iran. Soil ESP were predicted by using artificial neural networks, comprising radial basis functions (RBFN) and multilayer perceptron (MLP) and adaptive neuro-fuzzy inference systems (ANFIS), and results compared with stepwise linear regression method. Results indicated that the linear regression models performed poorly in order to estimate ESP (R2 ≤ 0.58 and root mean square error (RMSE) ≥ 4.31). Applying fewer inputs (electrical conductivity (EC) and pH), ANFIS showed better results (R2=0.80, RMSE=2.34), while increasing inputs (clay and organic carbon) decreased the accuracy (R2=0.82, RMSE=4.20). Using more inputs, RBFN resulted in better performance in comparison with other methods (R2=0.83, RMSE=2.85). Sensitivity analysis using the connection weight method demonstrated that EC, pH, clay percentage and bulk density are the most important variables in order to explain ESP variability in the region, respectively. Generally, considering the evaluation criteria and the number of used variables of models, ANFIS (with EC and pH as inputs) is the most appropriate method for estimating ESP in Sistan plain.

scholarly journals CANFIS based DSTATCOM modelling for solving power quality problems

2021 ◽  
Vol 4 (2) ◽  
Author(s):  
B. B. Bukata ◽  
R. A. Gezawa
Keyword(s):  
Power Quality ◽  
Fuzzy Inference ◽  
System Structure ◽  
Fuzzy Inference Systems ◽  
Neuro Fuzzy ◽  
Two Factors ◽  
Voltage Swell ◽  
Artificial Neural Network Ann ◽  
Inference Systems ◽  
Distribution Grids

Devolution of the power grid into smart grid was necessitated by the proliferation of sensitive load profiles into the system, as well as incessant environmental challenges. These two factors culminated into aggravated disturbances that cause serious havoc along the entire system structure. The traditional proportional-plus-integral-plus-derivative (PID) solution offered by the distribution synchronous compensator (DSTATCOM) could no longer hold. As such, this paper proposes some soft-computing framework for redesigning DSTATCOM to automatically deal with power quality (PQ) problems in smart distribution grids. A recipe of artificial neural network (ANN) and coactive neuro-fuzzy inference systems (CANFIS) was fabricated for the objective. The system was modelled, simulated, and validated in MATLAB/Simulink SimPowerSystems environment. The performance of the CANFIS against adaptive neuro-fuzzy inference systems (ANFIS), ANN and fuzzy logic controllers’ algorithms proved superior in handling PQ issues like voltage sag, voltage swell and harmonics.

Sign in / Sign up

Export Citation Format

Share Document