Hardware-in-the-Loop Assessment of a Data-Driven State of Charge Estimation Method for Lithium-Ion Batteries in Hybrid Vehicles
This paper presents the design and hardware-in-the-loop (HIL) experimental validation of a data-driven estimation method for the state of charge (<i>SOC</i>) in the lithium-ion batteries used in hybrid electric vehicles (HEVs). The considered system features a 1.25 kWh 48 V lithium-ion b...
| Main Authors: | , , , |
|---|---|
| Format: | Article |
| Language: | English |
| Published: |
MDPI AG
2021-11-01
|
| Series: | Electronics |
| Subjects: | |
| Online Access: | https://www.mdpi.com/2079-9292/10/22/2828 |
| _version_ | 1797510543475474432 |
|---|---|
| author | Sara Luciani Stefano Feraco Angelo Bonfitto Andrea Tonoli |
| author_facet | Sara Luciani Stefano Feraco Angelo Bonfitto Andrea Tonoli |
| author_sort | Sara Luciani |
| collection | DOAJ |
| description | This paper presents the design and hardware-in-the-loop (HIL) experimental validation of a data-driven estimation method for the state of charge (<i>SOC</i>) in the lithium-ion batteries used in hybrid electric vehicles (HEVs). The considered system features a 1.25 kWh 48 V lithium-ion battery that is numerically modeled via an RC equivalent circuit model that can also consider the environmental temperature influence. The proposed estimation technique relies on nonlinear autoregressive with exogenous input (NARX) artificial neural networks (ANNs) that are properly trained with multiple datasets. Those datasets include modeled current and voltage data, both for charge-sustaining and charge-depleting working conditions. The investigated method is then experimentally validated using a Raspberry Pi 4B card-sized board, on which the estimation algorithm is actually deployed, and real-time hardware, on which the battery model is developed, namely a Speedgoat baseline platform. These hardware platforms are used in a hardware-in-the-loop architecture via the UPD communication protocol, allowing the system to be validated in a proper testing environment. The resulting estimation algorithm can estimate the battery <i>SOC</i> in real-time, with 2% accuracy during real-time hardware testing. |
| first_indexed | 2024-03-10T05:33:41Z |
| format | Article |
| id | doaj.art-d4debc727c9646eeaa79fbff5aa501f1 |
| institution | Directory Open Access Journal |
| issn | 2079-9292 |
| language | English |
| last_indexed | 2024-03-10T05:33:41Z |
| publishDate | 2021-11-01 |
| publisher | MDPI AG |
| record_format | Article |
| series | Electronics |
| spelling | doaj.art-d4debc727c9646eeaa79fbff5aa501f12023-11-22T23:07:42ZengMDPI AGElectronics2079-92922021-11-011022282810.3390/electronics10222828Hardware-in-the-Loop Assessment of a Data-Driven State of Charge Estimation Method for Lithium-Ion Batteries in Hybrid VehiclesSara Luciani0Stefano Feraco1Angelo Bonfitto2Andrea Tonoli3Department of Mechanical and Aerospace Engineering, Politecnico di Torino, 10129 Torino, ItalyDepartment of Mechanical and Aerospace Engineering, Politecnico di Torino, 10129 Torino, ItalyDepartment of Mechanical and Aerospace Engineering, Politecnico di Torino, 10129 Torino, ItalyDepartment of Mechanical and Aerospace Engineering, Politecnico di Torino, 10129 Torino, ItalyThis paper presents the design and hardware-in-the-loop (HIL) experimental validation of a data-driven estimation method for the state of charge (<i>SOC</i>) in the lithium-ion batteries used in hybrid electric vehicles (HEVs). The considered system features a 1.25 kWh 48 V lithium-ion battery that is numerically modeled via an RC equivalent circuit model that can also consider the environmental temperature influence. The proposed estimation technique relies on nonlinear autoregressive with exogenous input (NARX) artificial neural networks (ANNs) that are properly trained with multiple datasets. Those datasets include modeled current and voltage data, both for charge-sustaining and charge-depleting working conditions. The investigated method is then experimentally validated using a Raspberry Pi 4B card-sized board, on which the estimation algorithm is actually deployed, and real-time hardware, on which the battery model is developed, namely a Speedgoat baseline platform. These hardware platforms are used in a hardware-in-the-loop architecture via the UPD communication protocol, allowing the system to be validated in a proper testing environment. The resulting estimation algorithm can estimate the battery <i>SOC</i> in real-time, with 2% accuracy during real-time hardware testing.https://www.mdpi.com/2079-9292/10/22/2828battery monitoring systemstate of chargeartificial neural networkshardware-in-the-loopreal-time hardwaremodeling |
| spellingShingle | Sara Luciani Stefano Feraco Angelo Bonfitto Andrea Tonoli Hardware-in-the-Loop Assessment of a Data-Driven State of Charge Estimation Method for Lithium-Ion Batteries in Hybrid Vehicles Electronics battery monitoring system state of charge artificial neural networks hardware-in-the-loop real-time hardware modeling |
| title | Hardware-in-the-Loop Assessment of a Data-Driven State of Charge Estimation Method for Lithium-Ion Batteries in Hybrid Vehicles |
| title_full | Hardware-in-the-Loop Assessment of a Data-Driven State of Charge Estimation Method for Lithium-Ion Batteries in Hybrid Vehicles |
| title_fullStr | Hardware-in-the-Loop Assessment of a Data-Driven State of Charge Estimation Method for Lithium-Ion Batteries in Hybrid Vehicles |
| title_full_unstemmed | Hardware-in-the-Loop Assessment of a Data-Driven State of Charge Estimation Method for Lithium-Ion Batteries in Hybrid Vehicles |
| title_short | Hardware-in-the-Loop Assessment of a Data-Driven State of Charge Estimation Method for Lithium-Ion Batteries in Hybrid Vehicles |
| title_sort | hardware in the loop assessment of a data driven state of charge estimation method for lithium ion batteries in hybrid vehicles |
| topic | battery monitoring system state of charge artificial neural networks hardware-in-the-loop real-time hardware modeling |
| url | https://www.mdpi.com/2079-9292/10/22/2828 |
| work_keys_str_mv | AT saraluciani hardwareintheloopassessmentofadatadrivenstateofchargeestimationmethodforlithiumionbatteriesinhybridvehicles AT stefanoferaco hardwareintheloopassessmentofadatadrivenstateofchargeestimationmethodforlithiumionbatteriesinhybridvehicles AT angelobonfitto hardwareintheloopassessmentofadatadrivenstateofchargeestimationmethodforlithiumionbatteriesinhybridvehicles AT andreatonoli hardwareintheloopassessmentofadatadrivenstateofchargeestimationmethodforlithiumionbatteriesinhybridvehicles |