| Title |
Machine Learning Enhancements For Electric Vehicles: Fault Detection Through Deep Echo State Networks (Esn) Model |
| ID_Doc |
35955 |
| Authors |
Buyukbicakci E.; Atli C.; Gedik I.; Dumanli M.; Bulat S.; Nithiya C.; Gulati M. |
| Year |
2024 |
| Published |
8th International Conference on Electronics, Communication and Aerospace Technology, ICECA 2024 - Proceedings |
| DOI |
http://dx.doi.org/10.1109/ICECA63461.2024.10801032 |
| Abstract |
Electric vehicles (EVs) are generally considered to be more eco-friendly than traditional forms of mobility. Smart cities are environmentally conscious, and their operation is based on the conversion of electrical energy into mechanical energy using different kinds of motors. Motors in electric vehicles get electricity from renewable energy (RE) sources through power electronics-based interface connections in order to spin and provide mechanical power. The proposed approach incorporates preprocessing, feature extraction, and training of the model. Data cleansing, data noise reduction, data slicing, and integration are the primary components of data preparation. The principle of sparse principal component analysis (SPCA) is used for statistical analysis and analysis of multivariate datasets in order to identify features. The DESN model was utilized consistently throughout the training process. This state-of-the-art method outperforms SVM and LSTM with an average accuracy of 9 5. 6 5 %. © 2024 IEEE. |
| Author Keywords |
Deep Echo State Network (DESN); Electric Vehicle Fault Detection; Sparse Principal Component Analysis (SPCA) |
