Saved in:
| Main Authors: | , , |
|---|---|
| Format: | Recurso digital |
| Language: | |
| Published: |
Zenodo
2025
|
| Subjects: | |
| Online Access: | https://doi.org/10.5281/zenodo.14623346 |
| Tags: |
Add Tag
No Tags, Be the first to tag this record!
|
| _version_ | 1866901453252067328 |
|---|---|
| author | Rafiqul Islam Roky Shahin Shaikh Md Nazmulhuda |
| author_facet | Rafiqul Islam Roky Shahin Shaikh Md Nazmulhuda |
| contents | <p>This paper introduces an enhanced Unscented Kalman Filter (UKF) algorithm integrated with<br>Radial Basis Function (RBF) neural networks to advance the accuracy of nonlinear state<br>estimation in dynamic systems. Our approach specifically addresses the estimation of the State<br>of Charge (SOC) of a battery, leveraging a second-order equivalent circuit model to capture<br>the battery’s complex behavior. The innovation of our method lies in the integration of RBF<br>neural networks into the UKF framework, which enhances the algorithm’s capability to model<br>nonlinearities and improve prediction accuracy.The standard UKF algorithm, while robust in<br>handling nonlinear systems, often struggles with certain nonlinearities inherent in battery SOC<br>estimation. By incorporating an RBF neural network, which excels at approximating complex,<br>nonlinear relationships, our proposed UKF-RBF algorithm achieves superior performance. The<br>RBF network is trained to capture the nonlinear Open Circuit Voltage (OCV) vs. SOC<br>relationship, which is crucial for accurate SOC estimation.Experimental results demonstrate<br>that the UKF-RBF algorithm significantly outperforms the traditional UKF in terms of Mean<br>Squared Error (MSE), Root Mean Square Error (RMSE), and Mean Absolute Error (MAE).<br>The UKF-RBF algorithm shows marked improvements in SOC estimation accuracy across<br>varying operating conditions and temperatures, making it a robust solution for practical<br>applications in battery management systems. The integration of RBF neural networks into the<br>UKF framework represents a novel approach that bridges the gap between traditional Kalman<br>filtering and modern neural network techniques, providing a substantial enhancement in the<br>estimation of nonlinear states.</p> |
| format | Recurso digital |
| id | zenodo_https___doi_org_10_5281_zenodo_14623346 |
| institution | Zenodo |
| language | |
| publishDate | 2025 |
| publisher | Zenodo |
| record_format | zenodo |
| spellingShingle | Enhanced Nonlinear Estimation with Unscented Kalman Filter and RBF Neural Networks Rafiqul Islam Roky Shahin Shaikh Md Nazmulhuda UKF-RBF <p>This paper introduces an enhanced Unscented Kalman Filter (UKF) algorithm integrated with<br>Radial Basis Function (RBF) neural networks to advance the accuracy of nonlinear state<br>estimation in dynamic systems. Our approach specifically addresses the estimation of the State<br>of Charge (SOC) of a battery, leveraging a second-order equivalent circuit model to capture<br>the battery’s complex behavior. The innovation of our method lies in the integration of RBF<br>neural networks into the UKF framework, which enhances the algorithm’s capability to model<br>nonlinearities and improve prediction accuracy.The standard UKF algorithm, while robust in<br>handling nonlinear systems, often struggles with certain nonlinearities inherent in battery SOC<br>estimation. By incorporating an RBF neural network, which excels at approximating complex,<br>nonlinear relationships, our proposed UKF-RBF algorithm achieves superior performance. The<br>RBF network is trained to capture the nonlinear Open Circuit Voltage (OCV) vs. SOC<br>relationship, which is crucial for accurate SOC estimation.Experimental results demonstrate<br>that the UKF-RBF algorithm significantly outperforms the traditional UKF in terms of Mean<br>Squared Error (MSE), Root Mean Square Error (RMSE), and Mean Absolute Error (MAE).<br>The UKF-RBF algorithm shows marked improvements in SOC estimation accuracy across<br>varying operating conditions and temperatures, making it a robust solution for practical<br>applications in battery management systems. The integration of RBF neural networks into the<br>UKF framework represents a novel approach that bridges the gap between traditional Kalman<br>filtering and modern neural network techniques, providing a substantial enhancement in the<br>estimation of nonlinear states.</p> |
| title | Enhanced Nonlinear Estimation with Unscented Kalman Filter and RBF Neural Networks |
| topic | UKF-RBF |
| url | https://doi.org/10.5281/zenodo.14623346 |