Remaining Service Life Prediction of Lithium-Ion Batteries Based on Randomly Perturbed Traceless Particle Filtering
To address the limitations in the prediction accuracy of the remaining useful life (RUL) of lithium-ion batteries, stemming from model accuracy, particle degradation, and insufficient diversity in the particle filter (PF) algorithm, this paper proposes a battery RUL prediction method utilizing a ran...
Saved in:
| Main Authors: | , , , , , |
|---|---|
| Format: | Article |
| Language: | English |
| Published: |
MDPI AG
2024-11-01
|
| Series: | Energies |
| Subjects: | |
| Online Access: | https://www.mdpi.com/1996-1073/17/21/5482 |
| Tags: |
Add Tag
No Tags, Be the first to tag this record!
|
| _version_ | 1846173425757847552 |
|---|---|
| author | Yan Liu Jun Chen Jun Yong Cheng Yang Liqin Yan Yanping Zheng |
| author_facet | Yan Liu Jun Chen Jun Yong Cheng Yang Liqin Yan Yanping Zheng |
| author_sort | Yan Liu |
| collection | DOAJ |
| description | To address the limitations in the prediction accuracy of the remaining useful life (RUL) of lithium-ion batteries, stemming from model accuracy, particle degradation, and insufficient diversity in the particle filter (PF) algorithm, this paper proposes a battery RUL prediction method utilizing a randomly perturbed unscented particle filter (RP-UPF) algorithm, based on the constructed battery capacity degradation model. The method utilizes evaluation metrics adjusted R-squared (<i>R<sub>adj</sub></i><sup>2</sup>) and the Akaike Information Criterion (<i>AIC</i>) to select the battery capacity decline model C<sub>5</sub> with a higher goodness of fit. The initial values for constructing the C<sub>5</sub> model are obtained using the relevance vector machine (RVM) and nonlinear least squares methods. Based on the constructed battery capacity decline model C<sub>5</sub>, the RP-UPF algorithm is employed to estimate the posterior parameters and iteratively approach the true battery capacity decline curve, thereby predicting the battery’s RUL. The research results indicate that, using battery B0005 as an example and starting the prediction from the 50th cycle, the RUL prediction results obtained with the RP-UPF algorithm demonstrate reductions in absolute error, relative error, and probability density function (PDF) width of 2%, 2.71%, and 10%, respectively, compared to the PF algorithm. Similar conclusions were drawn for batteries B0006 and B0018. Under the constructed battery capacity degradation model C<sub>5</sub>, the RP-UPF algorithm shows higher prediction accuracy for battery RUL and a narrower PDF range compared to the PF algorithm. This approach effectively addresses the issue of particle weight degradation in the PF algorithm, providing a more valuable reference for battery RUL prediction. |
| format | Article |
| id | doaj-art-f1c2d708d67741268fb928e2347f30ec |
| institution | Kabale University |
| issn | 1996-1073 |
| language | English |
| publishDate | 2024-11-01 |
| publisher | MDPI AG |
| record_format | Article |
| series | Energies |
| spelling | doaj-art-f1c2d708d67741268fb928e2347f30ec2024-11-08T14:35:50ZengMDPI AGEnergies1996-10732024-11-011721548210.3390/en17215482Remaining Service Life Prediction of Lithium-Ion Batteries Based on Randomly Perturbed Traceless Particle FilteringYan Liu0Jun Chen1Jun Yong2Cheng Yang3Liqin Yan4Yanping Zheng5College of Automobile and Traffic Engineering, Nanjing Forestry University, Nanjing 210037, ChinaCollege of Automobile and Traffic Engineering, Nanjing Forestry University, Nanjing 210037, ChinaJun Yong-State Grid Dangtu County Power Supply Company, Maanshan 243000, ChinaState Key Laboratory of Space Power-Sources, Shanghai Institute of Space Power-Sources, Shanghai 200245, ChinaState Key Laboratory of Space Power-Sources, Shanghai Institute of Space Power-Sources, Shanghai 200245, ChinaCollege of Automobile and Traffic Engineering, Nanjing Forestry University, Nanjing 210037, ChinaTo address the limitations in the prediction accuracy of the remaining useful life (RUL) of lithium-ion batteries, stemming from model accuracy, particle degradation, and insufficient diversity in the particle filter (PF) algorithm, this paper proposes a battery RUL prediction method utilizing a randomly perturbed unscented particle filter (RP-UPF) algorithm, based on the constructed battery capacity degradation model. The method utilizes evaluation metrics adjusted R-squared (<i>R<sub>adj</sub></i><sup>2</sup>) and the Akaike Information Criterion (<i>AIC</i>) to select the battery capacity decline model C<sub>5</sub> with a higher goodness of fit. The initial values for constructing the C<sub>5</sub> model are obtained using the relevance vector machine (RVM) and nonlinear least squares methods. Based on the constructed battery capacity decline model C<sub>5</sub>, the RP-UPF algorithm is employed to estimate the posterior parameters and iteratively approach the true battery capacity decline curve, thereby predicting the battery’s RUL. The research results indicate that, using battery B0005 as an example and starting the prediction from the 50th cycle, the RUL prediction results obtained with the RP-UPF algorithm demonstrate reductions in absolute error, relative error, and probability density function (PDF) width of 2%, 2.71%, and 10%, respectively, compared to the PF algorithm. Similar conclusions were drawn for batteries B0006 and B0018. Under the constructed battery capacity degradation model C<sub>5</sub>, the RP-UPF algorithm shows higher prediction accuracy for battery RUL and a narrower PDF range compared to the PF algorithm. This approach effectively addresses the issue of particle weight degradation in the PF algorithm, providing a more valuable reference for battery RUL prediction.https://www.mdpi.com/1996-1073/17/21/5482lithium-ion batteriesRULcapacity degradation modelRVMRP-UPF |
| spellingShingle | Yan Liu Jun Chen Jun Yong Cheng Yang Liqin Yan Yanping Zheng Remaining Service Life Prediction of Lithium-Ion Batteries Based on Randomly Perturbed Traceless Particle Filtering Energies lithium-ion batteries RUL capacity degradation model RVM RP-UPF |
| title | Remaining Service Life Prediction of Lithium-Ion Batteries Based on Randomly Perturbed Traceless Particle Filtering |
| title_full | Remaining Service Life Prediction of Lithium-Ion Batteries Based on Randomly Perturbed Traceless Particle Filtering |
| title_fullStr | Remaining Service Life Prediction of Lithium-Ion Batteries Based on Randomly Perturbed Traceless Particle Filtering |
| title_full_unstemmed | Remaining Service Life Prediction of Lithium-Ion Batteries Based on Randomly Perturbed Traceless Particle Filtering |
| title_short | Remaining Service Life Prediction of Lithium-Ion Batteries Based on Randomly Perturbed Traceless Particle Filtering |
| title_sort | remaining service life prediction of lithium ion batteries based on randomly perturbed traceless particle filtering |
| topic | lithium-ion batteries RUL capacity degradation model RVM RP-UPF |
| url | https://www.mdpi.com/1996-1073/17/21/5482 |
| work_keys_str_mv | AT yanliu remainingservicelifepredictionoflithiumionbatteriesbasedonrandomlyperturbedtracelessparticlefiltering AT junchen remainingservicelifepredictionoflithiumionbatteriesbasedonrandomlyperturbedtracelessparticlefiltering AT junyong remainingservicelifepredictionoflithiumionbatteriesbasedonrandomlyperturbedtracelessparticlefiltering AT chengyang remainingservicelifepredictionoflithiumionbatteriesbasedonrandomlyperturbedtracelessparticlefiltering AT liqinyan remainingservicelifepredictionoflithiumionbatteriesbasedonrandomlyperturbedtracelessparticlefiltering AT yanpingzheng remainingservicelifepredictionoflithiumionbatteriesbasedonrandomlyperturbedtracelessparticlefiltering |