The Role of Neural Networks in Predicting the Thermal Life of Electrical Machines
For a continuous mode of operation, insulating material in an electrical machine is subject to constant thermal, electrical, mechanical and environmental stresses where thermal stress is a major cause of gradual insulation deterioration, which leads to ultimate winding failure. To guarantee a satisf...
| Main Authors: | , , , , , , , |
|---|---|
| Format: | Article |
| Language: | English |
| Published: |
IEEE
2020-01-01
|
| Series: | IEEE Access |
| Subjects: | |
| Online Access: | https://ieeexplore.ieee.org/document/9007468/ |
| _version_ | 1818917948380676096 |
|---|---|
| author | Gulrukh Turabee Muhammad Raza Khowja Paolo Giangrande Vincenzo Madonna Georgina Cosma Gaurang Vakil Chris Gerada Michael Galea |
| author_facet | Gulrukh Turabee Muhammad Raza Khowja Paolo Giangrande Vincenzo Madonna Georgina Cosma Gaurang Vakil Chris Gerada Michael Galea |
| author_sort | Gulrukh Turabee |
| collection | DOAJ |
| description | For a continuous mode of operation, insulating material in an electrical machine is subject to constant thermal, electrical, mechanical and environmental stresses where thermal stress is a major cause of gradual insulation deterioration, which leads to ultimate winding failure. To guarantee a satisfactory lifetime, electrical machines are designed to operate winding temperatures well below their thermal class, which results in an oversized design. Standard methods for thermal lifetime evaluation of electrical machines are based on accelerated aging tests that require several months of testing. This paper proposes an alternative approach relying on a supervised neural network that significantly shortens the time demanded by accelerated aging tests for thermal lifetime evaluation of electrical machines. The supervised neural network is based on a feedforward neural network trained with Bayesian Regularisation Backpropagation (BRP) algorithm. The network predicts the wire insulation resistance with respect to its aging time at aging temperatures of 250°C, 270°C and 290°C, which reveals a good match of prediction outcomes against the experimental findings. The mean time-to-failure at each aging temperature is extracted using the Weibull probability plot in order to compare the Arrhenius curves for both conventional and proposed method and a relative error of 0.125% is achieved in terms of their temperature indexes. In addition, the analysis shows a time saving of 1680 hours (57% time saved of experimental test procedure) when the thermal life of the insulating material is predicted using BRP neural network. |
| first_indexed | 2024-12-20T00:42:11Z |
| format | Article |
| id | doaj.art-cf77e5d8116a4ecebf62695720235903 |
| institution | Directory Open Access Journal |
| issn | 2169-3536 |
| language | English |
| last_indexed | 2024-12-20T00:42:11Z |
| publishDate | 2020-01-01 |
| publisher | IEEE |
| record_format | Article |
| series | IEEE Access |
| spelling | doaj.art-cf77e5d8116a4ecebf626957202359032022-12-21T19:59:32ZengIEEEIEEE Access2169-35362020-01-018402834029710.1109/ACCESS.2020.29759859007468The Role of Neural Networks in Predicting the Thermal Life of Electrical MachinesGulrukh Turabee0https://orcid.org/0000-0002-2336-1912Muhammad Raza Khowja1https://orcid.org/0000-0003-3075-9440Paolo Giangrande2https://orcid.org/0000-0002-2328-5171Vincenzo Madonna3Georgina Cosma4https://orcid.org/0000-0002-4663-6907Gaurang Vakil5Chris Gerada6https://orcid.org/0000-0003-4707-4480Michael Galea7https://orcid.org/0000-0002-9094-611XSchool of Science and Technology, Nottingham Trent University, Nottingham, U.K.Power Electronics, Machines, and Control Research Group, University of Nottingham, Nottingham, U.K.Power Electronics, Machines, and Control Research Group, University of Nottingham, Nottingham, U.K.Power Electronics, Machines, and Control Research Group, University of Nottingham, Nottingham, U.K.Department of Computer Science, School of Science, Loughborough University, Loughborough, U.K.Power Electronics, Machines, and Control Research Group, University of Nottingham, Nottingham, U.K.Power Electronics, Machines, and Control Research Group, University of Nottingham, Nottingham, U.K.Power Electronics, Machines, and Control Research Group, University of Nottingham, Nottingham, U.K.For a continuous mode of operation, insulating material in an electrical machine is subject to constant thermal, electrical, mechanical and environmental stresses where thermal stress is a major cause of gradual insulation deterioration, which leads to ultimate winding failure. To guarantee a satisfactory lifetime, electrical machines are designed to operate winding temperatures well below their thermal class, which results in an oversized design. Standard methods for thermal lifetime evaluation of electrical machines are based on accelerated aging tests that require several months of testing. This paper proposes an alternative approach relying on a supervised neural network that significantly shortens the time demanded by accelerated aging tests for thermal lifetime evaluation of electrical machines. The supervised neural network is based on a feedforward neural network trained with Bayesian Regularisation Backpropagation (BRP) algorithm. The network predicts the wire insulation resistance with respect to its aging time at aging temperatures of 250°C, 270°C and 290°C, which reveals a good match of prediction outcomes against the experimental findings. The mean time-to-failure at each aging temperature is extracted using the Weibull probability plot in order to compare the Arrhenius curves for both conventional and proposed method and a relative error of 0.125% is achieved in terms of their temperature indexes. In addition, the analysis shows a time saving of 1680 hours (57% time saved of experimental test procedure) when the thermal life of the insulating material is predicted using BRP neural network.https://ieeexplore.ieee.org/document/9007468/Neural networkaging timethermal life of insulationaccelerated lifetime test |
| spellingShingle | Gulrukh Turabee Muhammad Raza Khowja Paolo Giangrande Vincenzo Madonna Georgina Cosma Gaurang Vakil Chris Gerada Michael Galea The Role of Neural Networks in Predicting the Thermal Life of Electrical Machines IEEE Access Neural network aging time thermal life of insulation accelerated lifetime test |
| title | The Role of Neural Networks in Predicting the Thermal Life of Electrical Machines |
| title_full | The Role of Neural Networks in Predicting the Thermal Life of Electrical Machines |
| title_fullStr | The Role of Neural Networks in Predicting the Thermal Life of Electrical Machines |
| title_full_unstemmed | The Role of Neural Networks in Predicting the Thermal Life of Electrical Machines |
| title_short | The Role of Neural Networks in Predicting the Thermal Life of Electrical Machines |
| title_sort | role of neural networks in predicting the thermal life of electrical machines |
| topic | Neural network aging time thermal life of insulation accelerated lifetime test |
| url | https://ieeexplore.ieee.org/document/9007468/ |
| work_keys_str_mv | AT gulrukhturabee theroleofneuralnetworksinpredictingthethermallifeofelectricalmachines AT muhammadrazakhowja theroleofneuralnetworksinpredictingthethermallifeofelectricalmachines AT paologiangrande theroleofneuralnetworksinpredictingthethermallifeofelectricalmachines AT vincenzomadonna theroleofneuralnetworksinpredictingthethermallifeofelectricalmachines AT georginacosma theroleofneuralnetworksinpredictingthethermallifeofelectricalmachines AT gaurangvakil theroleofneuralnetworksinpredictingthethermallifeofelectricalmachines AT chrisgerada theroleofneuralnetworksinpredictingthethermallifeofelectricalmachines AT michaelgalea theroleofneuralnetworksinpredictingthethermallifeofelectricalmachines AT gulrukhturabee roleofneuralnetworksinpredictingthethermallifeofelectricalmachines AT muhammadrazakhowja roleofneuralnetworksinpredictingthethermallifeofelectricalmachines AT paologiangrande roleofneuralnetworksinpredictingthethermallifeofelectricalmachines AT vincenzomadonna roleofneuralnetworksinpredictingthethermallifeofelectricalmachines AT georginacosma roleofneuralnetworksinpredictingthethermallifeofelectricalmachines AT gaurangvakil roleofneuralnetworksinpredictingthethermallifeofelectricalmachines AT chrisgerada roleofneuralnetworksinpredictingthethermallifeofelectricalmachines AT michaelgalea roleofneuralnetworksinpredictingthethermallifeofelectricalmachines |