Prediction of Availability Indicator of Water Pipes Using Artificial Intelligence
The paper presents the results of artificial neural networks application to the availability indicator prediction. The forecasted results indicate that artificial networks may be used to model the reliability level of the water supply systems. The network was trained using 147 and 173 operational da...
| Main Author: | |
|---|---|
| Format: | Article |
| Language: | English |
| Published: |
EDP Sciences
2017-01-01
|
| Series: | E3S Web of Conferences |
| Online Access: | https://doi.org/10.1051/e3sconf/20171700049 |
| _version_ | 1818855218320769024 |
|---|---|
| author | Kutyłowska Małgorzata |
| author_facet | Kutyłowska Małgorzata |
| author_sort | Kutyłowska Małgorzata |
| collection | DOAJ |
| description | The paper presents the results of artificial neural networks application to the availability indicator prediction. The forecasted results indicate that artificial networks may be used to model the reliability level of the water supply systems. The network was trained using 147 and 173 operational data from one Polish medium-sized city (distribution pipes and house connections, respectively). 50% of all data was chosen for learning, 25% for testing and 25% for validation. In prognosis phase, the best created network used 100% of 114 and 133 values for testing. Following functions were used to activate neurons in hidden and output layers: linear, logistic, hyperbolic tangent, exponential. The learning of the artificial network was performed using following input parameters: material, total length, diameter. In the optimal models hyperbolic tangent was chosen to activate the hidden and output neurons in modeling the availability indicator of house connections during 68 epochs of training. Hidden and output neurons were activated (20 epochs of learning) respectively by hyperbolic tangent and linear function during the prediction of availability indicator of distribution pipes. The maximum relative errors in learning and prognosis step were equal to 0.10% and 1.20% as well as 0.27% and 1.15% for distribution pipes and house connections, respectively. |
| first_indexed | 2024-12-19T08:05:06Z |
| format | Article |
| id | doaj.art-7c07db9fc9cf4b469c2b14e2e2e13ec0 |
| institution | Directory Open Access Journal |
| issn | 2267-1242 |
| language | English |
| last_indexed | 2024-12-19T08:05:06Z |
| publishDate | 2017-01-01 |
| publisher | EDP Sciences |
| record_format | Article |
| series | E3S Web of Conferences |
| spelling | doaj.art-7c07db9fc9cf4b469c2b14e2e2e13ec02022-12-21T20:29:46ZengEDP SciencesE3S Web of Conferences2267-12422017-01-01170004910.1051/e3sconf/20171700049e3sconf_eko2017_00049Prediction of Availability Indicator of Water Pipes Using Artificial IntelligenceKutyłowska Małgorzata0Wrocław University of Science and Technology, Faculty of Environmental EngineeringThe paper presents the results of artificial neural networks application to the availability indicator prediction. The forecasted results indicate that artificial networks may be used to model the reliability level of the water supply systems. The network was trained using 147 and 173 operational data from one Polish medium-sized city (distribution pipes and house connections, respectively). 50% of all data was chosen for learning, 25% for testing and 25% for validation. In prognosis phase, the best created network used 100% of 114 and 133 values for testing. Following functions were used to activate neurons in hidden and output layers: linear, logistic, hyperbolic tangent, exponential. The learning of the artificial network was performed using following input parameters: material, total length, diameter. In the optimal models hyperbolic tangent was chosen to activate the hidden and output neurons in modeling the availability indicator of house connections during 68 epochs of training. Hidden and output neurons were activated (20 epochs of learning) respectively by hyperbolic tangent and linear function during the prediction of availability indicator of distribution pipes. The maximum relative errors in learning and prognosis step were equal to 0.10% and 1.20% as well as 0.27% and 1.15% for distribution pipes and house connections, respectively.https://doi.org/10.1051/e3sconf/20171700049 |
| spellingShingle | Kutyłowska Małgorzata Prediction of Availability Indicator of Water Pipes Using Artificial Intelligence E3S Web of Conferences |
| title | Prediction of Availability Indicator of Water Pipes Using Artificial Intelligence |
| title_full | Prediction of Availability Indicator of Water Pipes Using Artificial Intelligence |
| title_fullStr | Prediction of Availability Indicator of Water Pipes Using Artificial Intelligence |
| title_full_unstemmed | Prediction of Availability Indicator of Water Pipes Using Artificial Intelligence |
| title_short | Prediction of Availability Indicator of Water Pipes Using Artificial Intelligence |
| title_sort | prediction of availability indicator of water pipes using artificial intelligence |
| url | https://doi.org/10.1051/e3sconf/20171700049 |
| work_keys_str_mv | AT kutyłowskamałgorzata predictionofavailabilityindicatorofwaterpipesusingartificialintelligence |