Battery Remaining Useful Life Prediction with Inheritance Particle Filtering
Accurately forecasting a battery’s remaining useful life (RUL) plays an important role in the prognostics and health management of rechargeable batteries. An effective forecast is reported using a particle filter (PF), but it currently suffers from particle degeneracy and impoverishment de...
| Main Authors: | , , , |
|---|---|
| Format: | Article |
| Language: | English |
| Published: |
MDPI AG
2019-07-01
|
| Series: | Energies |
| Subjects: | |
| Online Access: | https://www.mdpi.com/1996-1073/12/14/2784 |
| _version_ | 1818039369120874496 |
|---|---|
| author | Lin Li Alfredo Alan Flores Saldivar Yun Bai Yun Li |
| author_facet | Lin Li Alfredo Alan Flores Saldivar Yun Bai Yun Li |
| author_sort | Lin Li |
| collection | DOAJ |
| description | Accurately forecasting a battery’s remaining useful life (RUL) plays an important role in the prognostics and health management of rechargeable batteries. An effective forecast is reported using a particle filter (PF), but it currently suffers from particle degeneracy and impoverishment deficiencies in RUL evaluations. In this paper, an inheritance PF is developed to predict lithium-ion battery RUL for the first time. A battery degradation model is first mapped onto a PF problem using the genetic algorithm (GA) framework. Then, a Lamarckian inheritance operator is designed to improve the light-weight particles by heavy-weight ones and thus to tackle particle degeneracy. In addition, the inheritance mechanism retains certain existing information to tackle particle impoverishment. The performance of the inheritance PF is compared with an elitism GA-based PF. The former has fewer tuning parameters than the latter and is less sensitive to tuning parameters. Both PFs are applied to the prediction of lithium-ion battery RUL, which is validated using capacity degradation data from the NASA Ames Research Center. The experimental results show that the inheritance PF method offers improved RUL prediction and wider applications. Further improvement is obtained with one-step ahead prediction when the charging and discharging cycles move along. |
| first_indexed | 2024-12-10T07:57:32Z |
| format | Article |
| id | doaj.art-951911527f6045bc8223cb1658d9b5bb |
| institution | Directory Open Access Journal |
| issn | 1996-1073 |
| language | English |
| last_indexed | 2024-12-10T07:57:32Z |
| publishDate | 2019-07-01 |
| publisher | MDPI AG |
| record_format | Article |
| series | Energies |
| spelling | doaj.art-951911527f6045bc8223cb1658d9b5bb2022-12-22T01:56:52ZengMDPI AGEnergies1996-10732019-07-011214278410.3390/en12142784en12142784Battery Remaining Useful Life Prediction with Inheritance Particle FilteringLin Li0Alfredo Alan Flores Saldivar1Yun Bai2Yun Li3Industry 4.0 Artificial Intelligence Laboratory, School of Computer Science and Technology, Dongguan University of Technology, Dongguan 523808, ChinaIndustry 4.0 Artificial Intelligence Laboratory, School of Computer Science and Technology, Dongguan University of Technology, Dongguan 523808, ChinaIndustry 4.0 Artificial Intelligence Laboratory, School of Computer Science and Technology, Dongguan University of Technology, Dongguan 523808, ChinaIndustry 4.0 Artificial Intelligence Laboratory, School of Computer Science and Technology, Dongguan University of Technology, Dongguan 523808, ChinaAccurately forecasting a battery’s remaining useful life (RUL) plays an important role in the prognostics and health management of rechargeable batteries. An effective forecast is reported using a particle filter (PF), but it currently suffers from particle degeneracy and impoverishment deficiencies in RUL evaluations. In this paper, an inheritance PF is developed to predict lithium-ion battery RUL for the first time. A battery degradation model is first mapped onto a PF problem using the genetic algorithm (GA) framework. Then, a Lamarckian inheritance operator is designed to improve the light-weight particles by heavy-weight ones and thus to tackle particle degeneracy. In addition, the inheritance mechanism retains certain existing information to tackle particle impoverishment. The performance of the inheritance PF is compared with an elitism GA-based PF. The former has fewer tuning parameters than the latter and is less sensitive to tuning parameters. Both PFs are applied to the prediction of lithium-ion battery RUL, which is validated using capacity degradation data from the NASA Ames Research Center. The experimental results show that the inheritance PF method offers improved RUL prediction and wider applications. Further improvement is obtained with one-step ahead prediction when the charging and discharging cycles move along.https://www.mdpi.com/1996-1073/12/14/2784lithium-ion batterybattery remaining useful lifeparticle filterevolutionary computation |
| spellingShingle | Lin Li Alfredo Alan Flores Saldivar Yun Bai Yun Li Battery Remaining Useful Life Prediction with Inheritance Particle Filtering Energies lithium-ion battery battery remaining useful life particle filter evolutionary computation |
| title | Battery Remaining Useful Life Prediction with Inheritance Particle Filtering |
| title_full | Battery Remaining Useful Life Prediction with Inheritance Particle Filtering |
| title_fullStr | Battery Remaining Useful Life Prediction with Inheritance Particle Filtering |
| title_full_unstemmed | Battery Remaining Useful Life Prediction with Inheritance Particle Filtering |
| title_short | Battery Remaining Useful Life Prediction with Inheritance Particle Filtering |
| title_sort | battery remaining useful life prediction with inheritance particle filtering |
| topic | lithium-ion battery battery remaining useful life particle filter evolutionary computation |
| url | https://www.mdpi.com/1996-1073/12/14/2784 |
| work_keys_str_mv | AT linli batteryremainingusefullifepredictionwithinheritanceparticlefiltering AT alfredoalanfloressaldivar batteryremainingusefullifepredictionwithinheritanceparticlefiltering AT yunbai batteryremainingusefullifepredictionwithinheritanceparticlefiltering AT yunli batteryremainingusefullifepredictionwithinheritanceparticlefiltering |