Performance evaluation of ANN and ANFIS models for estimating velocity and pressure in water distribution networks
In this study, two artificial intelligence techniques: (1) artificial neural networks (ANNs) using different algorithms such as Lavenberg–Marquardt (LM), Bayesian Regularization (BR), and Scaled Conjugate Gradient (SCG) and (2) Adaptive Neuro-Fuzzy Inference System (ANFIS) are used to predict veloci...
| Main Authors: | , |
|---|---|
| Format: | Article |
| Language: | English |
| Published: |
IWA Publishing
2023-09-01
|
| Series: | Water Supply |
| Subjects: | |
| Online Access: | http://ws.iwaponline.com/content/23/9/3925 |
| _version_ | 1797661322014359552 |
|---|---|
| author | Abu Rashid Sangeeta Kumari |
| author_facet | Abu Rashid Sangeeta Kumari |
| author_sort | Abu Rashid |
| collection | DOAJ |
| description | In this study, two artificial intelligence techniques: (1) artificial neural networks (ANNs) using different algorithms such as Lavenberg–Marquardt (LM), Bayesian Regularization (BR), and Scaled Conjugate Gradient (SCG) and (2) Adaptive Neuro-Fuzzy Inference System (ANFIS) are used to predict velocity and pressure for Gadhra (DMA-5) real water distribution network (WDN), East Singhbhum district of Jharkhand, India. In case 1, flow rate and diameter are used as independent variables to predict velocity. In case 2, elevation and demand are used as independent variables to predict pressure. 80% of the data are used to train, test, and validate the ANN and ANFIS prediction models, while 20% of the data are used to evaluate data-driven models. Sensitivity analysis is performed in ANN-LM to understand the relationship between the independent and dependent variables. The performance indices of RMSE, MAE, and R2 are evaluated for ANN and ANFIS for different combinations. The ANN-LM, with 2-16-1 architecture, is found as a superior to predict velocity and ANN-LM with architecture 2-17-1 is found as a superior to predict pressure. ANN-LM had the best prediction in estimating velocity (RMSE = 0.0189, MAE = 0.0122, R2 = 0.9568) and pressure (RMSE = 0.3244, MAE = 0.2176, R2 = 0.9773).
HIGHLIGHTS
Hydraulic simulation is performed in WaterGEMS for Gadhra WDN (DMA-5).;
Predictions of the data-driven models are performed in MATLAB using ANFIS and ANN using LM, BR, and SCG.;
Based on statistical performance, a best model is selected for sensitivity analysis.;
Sensitivity analysis is done using ANN-LM to evaluate the impact of independent variables: diameter, flowrate, elevation, and demand on velocity and pressure.; |
| first_indexed | 2024-03-11T18:42:49Z |
| format | Article |
| id | doaj.art-795d17bcd945454d9836b02df898a250 |
| institution | Directory Open Access Journal |
| issn | 1606-9749 1607-0798 |
| language | English |
| last_indexed | 2024-03-11T18:42:49Z |
| publishDate | 2023-09-01 |
| publisher | IWA Publishing |
| record_format | Article |
| series | Water Supply |
| spelling | doaj.art-795d17bcd945454d9836b02df898a2502023-10-12T07:34:52ZengIWA PublishingWater Supply1606-97491607-07982023-09-012393925394910.2166/ws.2023.224224Performance evaluation of ANN and ANFIS models for estimating velocity and pressure in water distribution networksAbu Rashid0Sangeeta Kumari1 Department of Civil Engineering, NIT, Jamshedpur, Jharkhand, India Department of Civil Engineering, NIT, Jamshedpur, Jharkhand, India In this study, two artificial intelligence techniques: (1) artificial neural networks (ANNs) using different algorithms such as Lavenberg–Marquardt (LM), Bayesian Regularization (BR), and Scaled Conjugate Gradient (SCG) and (2) Adaptive Neuro-Fuzzy Inference System (ANFIS) are used to predict velocity and pressure for Gadhra (DMA-5) real water distribution network (WDN), East Singhbhum district of Jharkhand, India. In case 1, flow rate and diameter are used as independent variables to predict velocity. In case 2, elevation and demand are used as independent variables to predict pressure. 80% of the data are used to train, test, and validate the ANN and ANFIS prediction models, while 20% of the data are used to evaluate data-driven models. Sensitivity analysis is performed in ANN-LM to understand the relationship between the independent and dependent variables. The performance indices of RMSE, MAE, and R2 are evaluated for ANN and ANFIS for different combinations. The ANN-LM, with 2-16-1 architecture, is found as a superior to predict velocity and ANN-LM with architecture 2-17-1 is found as a superior to predict pressure. ANN-LM had the best prediction in estimating velocity (RMSE = 0.0189, MAE = 0.0122, R2 = 0.9568) and pressure (RMSE = 0.3244, MAE = 0.2176, R2 = 0.9773). HIGHLIGHTS Hydraulic simulation is performed in WaterGEMS for Gadhra WDN (DMA-5).; Predictions of the data-driven models are performed in MATLAB using ANFIS and ANN using LM, BR, and SCG.; Based on statistical performance, a best model is selected for sensitivity analysis.; Sensitivity analysis is done using ANN-LM to evaluate the impact of independent variables: diameter, flowrate, elevation, and demand on velocity and pressure.;http://ws.iwaponline.com/content/23/9/3925anfisannbayesian regularizationlevenberg–marquardtscaled conjugate gradientsensitivity analysis |
| spellingShingle | Abu Rashid Sangeeta Kumari Performance evaluation of ANN and ANFIS models for estimating velocity and pressure in water distribution networks Water Supply anfis ann bayesian regularization levenberg–marquardt scaled conjugate gradient sensitivity analysis |
| title | Performance evaluation of ANN and ANFIS models for estimating velocity and pressure in water distribution networks |
| title_full | Performance evaluation of ANN and ANFIS models for estimating velocity and pressure in water distribution networks |
| title_fullStr | Performance evaluation of ANN and ANFIS models for estimating velocity and pressure in water distribution networks |
| title_full_unstemmed | Performance evaluation of ANN and ANFIS models for estimating velocity and pressure in water distribution networks |
| title_short | Performance evaluation of ANN and ANFIS models for estimating velocity and pressure in water distribution networks |
| title_sort | performance evaluation of ann and anfis models for estimating velocity and pressure in water distribution networks |
| topic | anfis ann bayesian regularization levenberg–marquardt scaled conjugate gradient sensitivity analysis |
| url | http://ws.iwaponline.com/content/23/9/3925 |
| work_keys_str_mv | AT aburashid performanceevaluationofannandanfismodelsforestimatingvelocityandpressureinwaterdistributionnetworks AT sangeetakumari performanceevaluationofannandanfismodelsforestimatingvelocityandpressureinwaterdistributionnetworks |