Yazar "Sihag, Parveen" seçeneğine göre listele

Listeleniyor 1 - 2 / 2
  • Küçük Resim Yok
    Öğe
    Prediction of aeration efficiency of parshall and modified venturi flumes: application of soft computing versus regression models
    (Iwa Publishing, 2021) Sihag, Parveen; Dursun, Omer Faruk; Sammen, Saad Shauket; Malik, Anurag; Chauhan, Anita
    In this study, the potential of soft computing techniques namely Random Forest (RF), M5P, Multivariate Adaptive Regression Splines (MARS), and Group Method of Data Handling (GMDH) was evaluated to predict the aeration efficiency (AE(20)) at Parshall and Modified Venturi flumes. Experiments were conducted for 26 various Modified Venturi flumes and one Parshall flume. A total of 99 observations were obtained from experiments. The results of soft computing models were compared with regression-based models (i.e., MLR: multiple linear regression, and MNLR: multiple nonlinear regression). Results of the analysis revealed that the MARS model outperformed other soft computing and regression-based models for predicting the AE(20) at Parshall and Modified Venturi flumes with Pearson's correlation coefficient (CC) = 0.9997, and 0.9992, and root mean square error (RMSE) = 0.0015, and 0.0045 during calibration and validation periods. Sensitivity analysis was also carried out by using the best executing MARS model to assess the effect of individual input variables on AE(20) of both flumes. Obtained results on sensitivity examination indicate that the oxygen deficit ratio (r) was the most effective input variable in predicting the AE(20) at Parshall and Modified Venturi flumes.
  • Küçük Resim Yok
    Öğe
    Soft computing-based model development for estimating the aeration efficiency through Parshall flume and Venturi flumes
    (Springernature, 2023) Puri, Diksha; Sihag, Parveen; Sadeghifar, Tayeb; Dursun, Omer Faruk; Thakur, Mohindra Singh
    This study compares the efficacy of soft computing techniques namely, Random Forest, M5P tree and Adaptive Neuro Fuzzy Inference System to predict the aeration efficiency through a combined dataset of Parshall and modified Venturi Flumes. For the development and validation of the model, in all, 99 experimental observations were used. The model's development and validation were done by utilizing six independent variables, discharge, throat width, throat length, sill height, oxygen deficit ratio and the exponent factor as inputs whereas aeration efficiency was considered as a target. The performance of developed models is measured using six different goodness of fit parameters which are correlation coefficient, coefficient of determination, mean absolute error, mean squared error, root mean square error and mean absolute percentage error. Outcomes of the present analysis revealed that all developed models are capable of handling prediction due to their higher correlation coefficient (CC) values. However, Random Forest model outperformed other soft computing-based models for estimating the aeration efficiency with a correlation coefficient of 0.9981, mean absolute error value of 0.0023, and a mean squared error being 0.00 in the testing stage. Further, results obtained from sensitivity investigation indicate that the oxygen deficit ratio which contains the elements of saturated oxygen concentration, upstream oxygen concentration, and downstream oxygen concentration is the most effective input variable for estimating the aeration efficiency using this data set. Since oxygen deficit is highly sensitive to aeration efficiency, the values of saturated oxygen concentration, upstream and downstream oxygen concentration require due consideration.